ART-Plan's indicated target population is cancer patients for whom radiotherapy treatment has been prescribed. In this population, any patient for whom relevant modality imaging data is available.

ART-Plan is not intended for patients less than 18 years of age.

The indicated users are trained medical professionals including, but not limited to, radiotherapists, radiation oncologists, medical physicists, dosimetrists and medical professionals involved in the radiation therapy process.

The indicated use environments are, but not limited to, hospitals, clinics and any health facility involved in radiation therapy.

Device Description

The ART-Plan application consists of three key modules: SmartFuse,Annotate and AdaptBox, allowing the user to display and visualise 3D multi-modal medical image data. The user may process, render, review, store, display and distribute DICOM 3.0 compliant datasets within the system and/or across computer networks.

Compared to Ethos Treatment, 2.1; Ethos Treatment Planning, 1.1 (primary predicate), the following additional feature has been added to ART-Plan v2.1.0:

generation of synthetic CT from MR images. This does not represent an additional . claim as the technological characteristics are the same and it does not raise different questions of safety and effectiveness. Also, this feature is already covered by reference and previous version of the device ART-Plan v1.10.1.

The ART-Plan technical functionalities claimed by TheraPanacea are the following:

. Proposing automatic solutions to the user, such as an automatic delineation, automatic multimodal image fusion, etc. towards improving standardization of processes/ performance / reducing user tedious / time consuming involvement.
. Offering to the user a set of tools to assist semi-automatic delineation, semi-automatic registration towards modifying/editing manually automatically generated structures and addina/removing new/undesired structures or imposing user-provided correspondences constraints on the fusion of multimodal images.
. Presenting to the user a set of visualization methods of the delineated structures, and registration fusion maps.
. Saving the delineated structures / fusion results for use in the dosimetry process.
. Enabling rigid and deformable registration of patients images sets to combine information contained in different or same modalities.
Allowing the users to generate, visualize, evaluate and modify pseudo-CT from MRI and CBCT images.
. Allowing the users to generate, visualize and analyze dose on images of CT modality (only within the AdatpBox workflow)
. Presenting to the user metrics to define if there is a need for replanning or not.

AI/ML Overview

The provided document describes the acceptance criteria and the study that proves the ART-Plan device meets these criteria across its various modules (Autosegmentation, SmartFuse, AdaptBox, Synthetic-CT generation, and Dose Engine).

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

Autosegmentation Tool

Acceptance Criteria Type	Acceptance Criteria	Reported Device Performance
Quantitative (DSC)	a) DSC (mean) ≥ 0.8 (AAPM criterion) ORb) DSC (mean) ≥ 0.54 (inter-expert variability) OR DSC (mean) ≥ mean (DSC inter-expert) + 5%	Duodenum: DICE diff inter-expert = 1.32% (Passed)Large bowel: DICE diff inter-expert = 1.19% (Passed)Small bowel: DICE diff inter-expert = 2.44% (Passed)
Qualitative (A+B%)	A+B % ≥ 85% (A: acceptable without modification, B: acceptable with minor modifications/corrections, C: requires major modifications)	Right lacrimal gland: A+B = 100% (Passed)Left lacrimal gland: A+B = 100% (Passed)Cervical lymph nodes VIA: A+B = 97% (Passed)Cervical lymph nodes VIB: A+B = 100% (Passed)Pharyngeal constrictor muscle: A+B = 100% (Passed)Anal canal: A+B = 98.68% (Passed)Bladder: A+B = 93.42% (Passed)Left femoral head: A+B = 100% (Passed)Right femoral head: A+B = 100% (Passed)Penile bulb: A+B = 96.05% (Passed)Prostate: A+B = 92.10% (Passed)Rectum: A+B = 100% (Passed)Seminal vesicle: A+B = 94.59% (Passed)Sigmoid: A+B = 98.68% (Passed)

SmartFuse Module (Image Registration)

Acceptance Criteria Type	Acceptance Criteria	Reported Device Performance
Quantitative (DSC)	a) DSC (mean) ≥ 0.81 (AAPM criterion) ORb) DSC (mean) ≥ 0.65 (benchmark device)	No specific DSC performance values are directly listed for SmartFuse, but the qualitative evaluations imply successful registration leading to acceptable contours.
Qualitative (A+B%)	Propagated Contours: A+B% ≥ 85% for deformable, A+B% ≥ 50% for rigid.Overall Registration Output: A+B% ≥ 85% for deformable, A+B% ≥ 50% for rigid.	for tCBCT - sCT (Overall Registration Output): Rigid: A+B%=95.56% (Passed); Deformable: A+B%=97.78% (Passed)for tsynthetic-CT - sCT (Propagated Contours): Deformable: A+B%=94.06% (Passed)for tCT - sSCT (Overall Registration Output): Rigid: A+B%=70.37% (Passed)
Geometric	2) Jacobian Determinant must be positive.3) Target Registration Error (TRE) < 2mm (POPI database)	Not explicitly detailed in the performance summary table, but the document states "The results show that both types of fusion algorithms (Rigid & Deformable) in SmartFuse pass the performed tests, and provide valid results for further clinical use in radiotherapy."

Synthetic-CT Generation (from MR images)

Acceptance Criteria Type	Acceptance Criteria	Reported Device Performance
Gamma Passing Criteria	a) Median 2%/2mm gamma passing criteria ≥ 95%b) Median 3%/3mm gamma passing criteria ≥ 99.0%	Not explicitly listed in the performance table, but the document implies meeting criteria based on overall "Passed" status for AdaptBox functionality.
Mean Dose Deviation	c) Mean dose deviation (synthetic-CT compared to standard CT) ≤ 2% in ≥ 88% of patients	Not explicitly listed in the performance table, but the document implies meeting criteria based on overall "Passed" status for AdaptBox functionality.

Synthetic-CT Generation (from CBCT images)

Acceptance Criteria Type	Acceptance Criteria	Reported Device Performance
Gamma Passing Criteria	a) Median 2%/2mm gamma passing criteria ≥ 92%b) Median 3%/3mm gamma passing criteria ≥ 93.57%	Gamma index: 2%/2mm = 98.85 (Passed); 3%/3mm = 99.43 (Passed)
Mean Dose Deviation	c) Mean dose deviation (synthetic-CT compared to standard CT) ≤ 2% in ≥ 76.7% of patients	DVH parameters (PTV): < 0.199% in 100% of the cases (Passed)

Dose Engine Function (within AdaptBox)

Acceptance Criteria Type	Acceptance Criteria	Reported Device Performance
Dose Deviation	a) DVH or median dose deviation ≤ 24.4% for Lung tissue or ≤ 4.4% for other organs	DVH parameters (PTV): < 1.29% (Passed)DVH parameters (OARs): < 3.9% (Passed)
Gamma Passing Criteria	b) Median 2%/2mm gamma passing rate ≥ 86.3%c) Median 3%/3mm gamma passing criteria ≥ 91.75%	Gamma index: 2%/2mm = 97.22% (Passed); 3%/3mm = 99.50% (Passed)

2. Sample sizes used for the test set and data provenance

The document provides "Min sample size for evaluation method" for various tests, and then states the actual "Sample size" used, which generally exceeds the minimum.

Autosegmentation Tool:
- Quantitative (DSC) tests (Duodenum, Large bowel, Small bowel): Sample size = 25 for each, Data Provenance: Retrospective, actual clinical data (implied from "real-world retrospective data which were initially used for treatment of cancer patients"). Country of origin is not explicitly stated but implied to be diverse based on training data representing "market share of the different vendors in EU & USA".
- Qualitative (A+B%) tests (various organs): Sample sizes range from 20 to 38 for different organs. Data Provenance: Retrospective, clinical data. Country of origin: Not explicitly stated, but includes both US and non-US data for performance evaluation.
SmartFuse Module:
- tCBCT - sCT: Sample size = 45. Data Provenance: Retrospective, clinical data.
- tsynthetic-CT - sCT: Sample size = 30. Data Provenance: Retrospective, clinical data.
- tCT - sSCT: Sample size = 27. Data Provenance: Retrospective, clinical data.
Synthetic-CT Generation (from CBCT):
- Sample size = 20. Data Provenance: Retrospective, clinical data.
Dose Engine Function:
- Sample size = 272 total (Brain: 42, H&N: 70, Chest: 44, Breast: 26, Pelvis: 90). Data Provenance: Retrospective, clinical data.

All data for testing derived from "real-world retrospective data which were initially used for treatment of cancer patients." The document emphasizes that the data was pseudo-anonymized and collected from various centers, with efforts to ensure representation of "market share of the different vendors in EU & USA" and equivalent performance between non-US and US populations, suggesting a multi-national provenance for both training and testing.

3. Number of experts used to establish the ground truth for the test set and their qualifications

The document states ground truth contours were produced by "different delineators (clinical experts)" and assessment of "intervariability," and "ground truth contours provided by the centers and validated by a second expert of the center." It also mentions "qualitative evaluation and validation of the contours."

Number of Experts: Not a fixed number, but implies multiple "clinical experts" for initial contouring and a "second expert" for validation. For qualitative evaluations in the performance tests, the column "Qualitative evaluation by experts" is used, implying multiple experts participate in the A/B/C scoring. For instance, usability testers are described as "European medical physicists who have participated in the evaluation have at least an equivalent expertise level compared to a junior US medical physicist (MP), and responsibilities in the radiotherapy clinical workflow are equivalent."
Qualifications: "Clinical experts," "medical physicists," "radiation oncologists," and "dosimetrists." The specific number for each test isn't enumerated, but it implies a panel of qualified professionals for qualitative assessment and ground truth establishment.

4. Adjudication method for the test set

The ground truth establishment involved a mix of:

Contouring guidelines confirmed with data-providing centers.
Data created by "different delineators (clinical experts)."
Assessment of inter-variability among experts.
Ground truth contours provided by centers and "validated by a second expert of the center."
Qualitative evaluation and validation of contours by experts (A, B, C scale). This qualitative assessment serves as a form of adjudication for the performance of the device against expert opinion.

This suggests a consensus-based approach with a "2+1" or similar structure where two initial delineations (or one and a validation by a second expert) contribute to building the ground truth, which is then further evaluated qualitatively. No explicit numerical "2+1" or "3+1" is given, but the description aligns with a multi-reader, consensus-driven process.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and its effect size

The document does not explicitly present a formal MRMC comparative effectiveness study demonstrating how much human readers improve with AI vs. without AI assistance. The studies focus on the performance of the device itself (standalone, or how its output (e.g., auto-segmentations, registrations) is perceived by human experts.

The qualitative evaluations done by experts (A+B% scores) are a form of assessment of the AI's output by multiple readers/experts on multiple cases, but they do not directly measure improvement of human reader performance with AI assistance compared to performance without AI assistance. The qualitative evaluations are on the AI's output, not on the human reader's workflow with AI.

Therefore, no effect size for human reader improvement with AI assistance is provided.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, standalone performance was extensively evaluated. The entire set of acceptance criteria and performance study results (DSC scores, gamma passing rates, mean dose deviations, and qualitative evaluation of the AI-generated contours/registrations) directly pertain to the algorithm's performance without a human in the loop during the generation process. The human element comes into play for evaluating the algorithm's output, not for assisting its real-time operation in these specific performance metrics.

For example, the auto-segmentation tests measure the quality of contours generated solely by the AI model. The synthetic-CT generation and dose engine also measure the performance of the algorithm itself.

7. The type of ground truth used

The ground truth used is a combination of:

Expert Consensus/Delineation: For auto-segmentation, ground truth contours were established by "clinical experts," often validated by "a second expert of the center," and confirmed with "contouring guidelines." This aligns with expert consensus.
Imaging Metrics/Physical Measurement Comparisons: For synthetic-CT generation, ground truth involved comparison to "real planning CTs for the same patients," coupled with dose calculations and gamma passing criteria, which are objective quantitative metrics. For the dose engine, measurements on a Linac were compared with the dose engine results.

8. The sample size for the training set

The training set sizes are provided separately for different functionalities:

Auto-segmentation tool: 246,226 samples (corresponding to 8,950 total patients).
Synthetic-CT from MR images: 6,195 samples.
Synthetic-CT from CBCT images: 1,467 samples.

The document clarifies that "one patient can be associated with more images (e.g. CT, MR) and that each image (anatomy) has the delineation of several structures (OARs and lymph nodes) which increases the number of samples used for training and validation."

9. How the ground truth for the training set was established

The ground truth for the training set was established through a rigorous process involving:

Clinical Expert Delineation: Contours for auto-segmentation were produced by "different delineators (clinical experts)."
Guideline Adherence: The contouring guidelines followed were confirmed with the centers providing the data, ensuring consistency and adherence to established medical practices.
Expert Validation: The ground truth contours were provided by the centers and "validated by a second expert of the center."
Qualitative Evaluation: There was also a qualitative evaluation and validation of the contours to ensure clinical acceptability.
Retrospective Real-World Data: The data came from "real-world retrospective data which were initially used for treatment of cancer patients," ensuring clinical relevance.
For Synthetic-CTs: "Clinical evaluation as part of the 'truthing-process' guidelines followed to produce and validate the synthetic-CTs were extracted from the literature and confirmed with the centers which provided the data and helped in the performance evaluation." This involved "imaging metrics based comparison between synthetic-CTs and real planning CTs for the same patients."

Summary

{0}------------------------------------------------

December 22, 2023

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" in a square and the words "U.S. FOOD & DRUG ADMINISTRATION".

TheraPanacea % Bhairavi Ajachandra QA/RA Manager 7 bis boulevard Bourdon Paris. 75004 FRANCE

Re: K232479

Trade/Device Name: ART-Plan Regulation Number: 21 CFR 892.5050 Regulation Name: Medical Charged-Particle Radiation Therapy System Regulatory Class: Class II Product Code: MUJ Dated: November 20, 2023 Received: November 20, 2023

Dear Bhairavi Ajachandra:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming

{1}------------------------------------------------

product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Locon Weidner

Lora D. Weidner, Ph.D. Assistant Director Radiation Therapy Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K232479

Device Name ART-Plan

Indications for Use (Describe)

ART-Plan's indicated target population is cancer patients for whom radiotherapy treatment has been prescribed. In this population, any patient for whom relevant modality imaging data is available.

ART-Plan is not intended for patients less than 18 years of age.

The indicated use environments are, but not limited to, hospitals, clinics and any health facility involved in radiation therapy.

Type of Use (Select one or both, as applicable)
❌ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) Summary

This 510(k) Summary is submitted in accordance with 21 CFR Part 807, Section 807.92.

Level of documentation:

Enhanced

Submitter's Name:

TheraPanacea SAS

Submitter's Address:

7 bis boulevard Bourdon 75004 Paris France

Telephone: +33 9 62 52 78 19

Establishment Registration Number:

3019834893

Contact Person:

Bhairavi Ajachandra

Telephone: +33 (0) 620604982

Date Prepared:

10 Aug 2023

Below summaries the Device Classification Information regarding the TheraPanacea ART-Plan:

Primary Product Code:

RegulationNumber	Device	DeviceClass	ProductCode	ClassificationPanel
892.5050	Medical charged-particleradiation therapy system	Class II	MUJ	Radiology

Device Trade Name:

ART-Plan

Device Common Name:

ART-Plan

{4}------------------------------------------------

Intended Use:

ART-Plan is a software intended to be used by trained clinicians who are familiar with radiation therapy, such as medical physicists, medical dosimetrists and radiation oncologists. The software consists of different applications, each used for specific purposes at a different phase of radiation treatment planning.

ART-Plan offers the following tools to aid in the workflow of radiotherapy treatment:

Multi-modal visualization and rigid- and deformable registration of anatomical and . functional images such as CT, MR, PET-CT, 4D-CT, CBCT and synthetic-CT generated from CBCT
Display of fused and non-fused images to facilitate the comparison and delineation of image data by the user
Manual generation, modification and semi-automatic generation of contours for the ● regions of interest
Automatic generation of contours for organs at risk and healthy lymph nodes, based ● on medical practices, on medical images such as CT and MR images
Generation of synthetic-CT from MR images for supported anatomies
Generation of synthetic-CT from CBCT images for supported anatomies ●
Dose computation on CT and/or synthetic-CT images for external beam irradiation ● with photon beams
Assisted CBCT-based off-line adaptation decision-making for supported anatomies

The device is intended to be used in a radiation therapy clinical setting, by trained professionals only.

Indications for Use:

ART-Plan's indicated target population is cancer patients for whom radiotherapy treatment has been prescribed. In this population, any patient for whom relevant modality imaging data is available.

ART-Plan is not intended for patients less than 18 years of age.

The indicated users are trained medical professionals includinq, but not limited to, radiotherapists, radiation oncologists, medical physicists, dosimetrists and medical professionals involved in the radiation therapy process.

The indicated use environments include, but are not limited to, hospitals, clinics and any health facility involved in radiation therapy.

{5}------------------------------------------------

Summary of Substantial Equivalence:

The following predicate devices have been that the ART-Plan can claim equivalence with and these are detailed below in Table 1. Summary of Substantial Equivalence.

General Comparison

	General Information
Property	Proposed DeviceART-Plan v2.1.0	Primary PredicateEthos TreatmentManagement, 2.1;Ethos TreatmentPlanning, 1.1	Reference deviceART-Planv1.10.1	ReferencedeviceECLIPSEWITH AAA	ReferencedeviceEclipse TreatmentPlanning System	Comment
CommonName	System, Planning,Radiation TherapyTreatment	accelerator, linear,medical	Radiological imageprocessing softwarefor radiation therapy	System, Planning,Radiation TherapyTreatment	System, Planning,Radiation TherapyTreatment	The proposed device shares the samecommon name "System, Planning,Radiation Therapy Treatment" with theprimary predicate, especially EthosTreatment Planning, 1.1 (that has"MUJ" as a product code in its 510(k)summary) and with some of thereference devices.
DeviceManufacturer	TheraPanacea SAS	Varian MedicalSystems, Inc	TheraPanacea SAS	Varian MedicalSystems(nowVarian MedicalSystems, Inc)	Varian MedicalSystems, Inc	N/A
510k	N/A	K212294	K230023	K041403	K102011	N/A
DeviceClassification	II	II	II	II	II	N/AThe proposed device, primarypredicate and reference deviceshave identical device classification.
PrimaryProductCode	MUJ	IYE, MUJ	QKB	MUJ	MUJ	The primary product code is MUJ for"System, Planning, Radiation TherapyTreatment" as it is a software used inthe planning of radiotherapy treatmentlike the primary predicate, especiallyEthos Treatment Planning, 1.1 (thathas "MUJ" as a product code in its510(k) summary) and some referencedevices use it as their primary orsecondary code
SecondaryProductCode	QKB, LLZ	LLZ, MUJ		LHN	As secondary product code:- QKB (Radiological imageprocessing software for radiationtherapy) has been included as thesoftware uses Al algorithms and isintended for radiation therapy. It isalso the primary code of thereference device ART-Planv1.10.1 of which ART-Plan 2.1.0 isan update;- LLZ (System, Image Processing,Radiological) has been includedas the software is used in imageprocessing and it is also thesubsequent code of the referencedevice ART-Plan v1.10.1 of whichART-Plan 2.1.0 is an update.
TargetPopulation	ART-Plan'sindicated targetpopulation is cancerpatients for whomradiotherapytreatment has beenprescribed. In thispopulation, anypatient for whomrelevant modalityimaging data isavailable.	The patient targetgroups are thepatients for whomradiation therapy isindicated.	ART-Plan's indicatedtarget population iscancer patients forwhom radiotherapytreatment has beenprescribed. In thispopulation, any patientfor whom relevantmodality imaging datais available.	Not stated	Any patients withmalignant or benigndiseases	The proposed device and the primarypredicate have identical targetpopulations.
Environment	Hospital	Hospital	Hospital	Hospital	Hospital	The proposed device, primarypredicate and reference deviceshave identical target environments.
IntendedUse/Indicationfor Use	Intended UseART-Plan is asoftware intended tobe used by trainedclinicians who arefamiliar withradiation therapy,such as medicalphysicists, medicaldosimetrists and	Intended UseEthos TreatmentManagement isused to manageand monitorradiation therapytreatment plansand sessions; it isintended to be used	Intended UseART-Plan is asoftware formulti-modalvisualization,contouring andprocessing of 3Dimages of cancerpatients for whom	Intended UseThe Varian Eclipsedevice is atreatment planningsystem used fordiagnostic imageanalysis,contouring andsegmentation,geometrical	Intended useNot available in thesummary:Indication for useThe EclipseTreatment PlanningSystem (EclipseTPS) is used toplan radiotherapy	The intended use and indicationsfor use of the proposed device,ART-Plan v2.1.0 and the primarypredicate (especially EthosTreatment Planning, 1.1) aresimilar as they are both softwaresintended to be used in the planningof radiotherapy treatment¹:
radiationoncologists. Thesoftware consists ofdifferentapplications, eachused for specificpurposes at adifferent phase ofradiation treatmentplanning.	with a treatmentplanning system.Ethos TreatmentPlanning is used togenerate andmodify radiationtherapy treatmentplans.	radiotherapy treatmenthas been prescribed.It allows the user toview, create andmodify contours forthe regions of interest.It also allows togenerateautomatically, andbased on medicalpractices, the contoursfor the organs at riskand healthy lymphnodes and to registercombinations ofanatomical andfunctional images.Contours and imagesrequire verifications,potentialmodifications, andsubsequently thevalidation of a traineduser with professionalqualifications inanatomy andradiotherapy beforetheir export to aTreatment PlanningSystem.	planning, photonand electron dosecalculation andplan review.	treatments forpatients withmalignant or benigndiseases. EclipseTPS is used to planexternal beamirradiation withphoton, electronand proton beamA,as well as forinternal irradiation(brachytherapy)treatments. Inaddition, theEclipse Proton Eyealgorithm specificallyindicated forplanning protontreatment ofneoplasms of theeye.	they allow multi-modal visualisationrigid- and deformableregistration for the same modalitiesof images (CT, MR and PET)
ART-Plan offers thefollowing tools to aidin the workflow ofradiotherapytreatment:Multi-modalvisualization andrigid- anddeformableregistration ofanatomical andfunctional imagessuch as CT, MR,PET-CT, 4D-CT,CBCT andsynthetic-CTgenerated fromCBCTDisplay of fusedand non-fusedimages tofacilitate thecomparison anddelineation ofimage data by theuserManualgeneration,modification andsemi-automaticgeneration ofcontours for theregions of interest	Indications forUseEthos TreatmentManagement isindicated for use inmanaging andmonitoringtreatment plansand sessions.Ethos TreatmentPlanning isindicated for use ingenerating andmodifying radiationtherapy treatmentplans.	ART-Plan offers thefollowing visualization,contouring andmanipulation tools toaid in the preparationof radiotherapytreatment:	Indication for useThe Varian Eclipsedevice is used toplan photon andelectron radiationtherapy treatmentsemploying linearaccelerators andother similarteletherapydevices with x-rayenergies from 1-50MV, as well asCobalt-60, andelectron energiesfrom 1-50 MeV.Eclipse will planthe 3Dradiotherapytreatmentapproaches tocombined modalityplans, coplanarand non-coplanarfields, static andARC fields, beammodifiers, andbeam intensitymodulators.Eclipse alsoincludes tools fortreatmentpreparation(diagnostic imageand analysis,contouring andsegmentation) andplan review.		they allow displaying fused andnon-fused images to facilitate thecomparison and delineation of imagedata by the userthey allow manual generation,modification and semi-automaticgeneration of contours for theregions of interestthey allow automatic segmentationon medical images using AIalgorithmsthey allow generation of synthetic-CTfrom CBCT imagesthey allow dose computation on CTand/or synthetic-CT images forexternal beam irradiation with photonbeamsthey allow assisted CBCT-basedoff-line adaptation decision-makingfor supported anatomiesthey allow the import, manipulation,visualisation, generation and theexport of DICOM imagesThe intended use for the proposeddevice has been adapted toprovide a more specific descriptionof the proposed device but doesnot represent a new intended use,except for the additional modalityfor the same claim as compared tothe primary predicate as:
		- Multi-modalvisualization and rigid-and deformableregistration ofanatomical andfunctional images

{6}------------------------------------------------

1 Information found on the previous 510(k) summaries, labelling and its manufacturer's (Varian Medical Systems, Inc) website.

{7}------------------------------------------------

{8}------------------------------------------------

Automaticgenerationofcontoursfororgans at risk andhealthy lymphnodes, based onmedical practices,on medicalimages such asCT and MRimages	such as CT, MR,PET-CT, 4D-CT andCBCT- Display of fused andnon-fused images tofacilitate thecomparison anddelineation of imagedata by the user- Manual modificationand semi-automaticgeneration of contoursfor the regions ofinterest- Automatic generationof contours for organsat risk and healthylymph nodes, basedon medical practices,on medical imagessuch as CT and MRimages.- Generation ofpseudo-CT forsupported anatomies	- it can generate synthetic CT fromCBCT and MR images whereas it isnot possible with Ethos TreatmentPlanning, 1.1 to do so with MRimages. This does not represent anadditional claim as the technologicalcharacteristics are the same and itdoes not raise different questions ofsafety and effectiveness. Also, thisfeature is covered by the referencedevice ART-Plan v1.10.1, which isthe previous version cleared of theproposed device ART-Plan v2.1.0.
Generationofsynthetic-CT fromMR images forsupportedanatomies	The device is intendedto be used in aradiation therapyclinical setting, bytrained professionalsonly.
Generationofsynthetic-CT fromCBCT images forsupportedanatomies
Dose computationon CT and/orsynthetic-CTimages forexternal beamirradiation withphoton beams
AssistedCBCT-basedoff-line adaptationdecision-makingfor supportedanatomies
The device isintended to be usedin a radiationtherapy clinicalsetting, by trainedprofessionals only.	Indications for UseART-Plan is indicatedfor cancer patients forwhom radiationtreatment has beenplanned. It is intendedto be used by trainedmedical professionalsincluding, but notlimited to radiologists.
population is cancerpatients for whomradiotherapytreatment has beenprescribed. In thispopulation, anypatient for whomrelevant modalityimaging data isavailable.	radiation oncologists,dosimetrists, andmedical physicists.ART-Plan is asoftware applicationintended to displayand visualize 3Dmulti-modal medicalimage data. The usermay import, define,display, transform andstore DICOM 3.0compliant datasets(including regions ofinterest structures).These images,contours and objectscan subsequently beexported/distributedwithin the system,across computernetworks and/or toradiation treatmentplanning systems.Supported modalitiesinclude CT, PET-CT,CBCT, 4D-CT and MRimages.ART-Plan supportsAI-based contouringon CT and MR imagesand offerssemi-automatic andmanual tools forsegmentation.To help the userassess changes inimage data and toobtain combinedmulti-modal imageinformation, ART-Planallows the registrationof anatomical and
ART-Plan is notintended forpatients less than18 years of age.
The indicated usersare trained medicalprofessionalsincluding, but notlimited to,radiotherapists,radiationoncologists, medicalphysicists,dosimetrists andmedicalprofessionalsinvolved in theradiation therapyprocess.
The indicated useenvironmentsinclude, but are notlimited to, hospitals,clinics and anyhealth facilityinvolved in radiationtherapy.

Page 6 of 31

{9}------------------------------------------------

{10}------------------------------------------------

	functional images anddisplay of fused andnon-fused images tofacilitate thecomparison of patientimage data by theuser.
	With ART-Plan, usersare also able togenerate, visualize,evaluate and modifypseudo-CT from MRIimages.

{11}------------------------------------------------

System Information Comparison

	System Information
Property	Proposed DeviceART-Plan v2.1.0	Primary PredicateEthosTreatmentManagement, 2.1;EthosTreatmentPlanning, 1.1	Reference deviceART-Planv1.10.1	ReferencedeviceECLIPSE WITHAAA	Reference deviceEclipse TreatmentPlanning System	Comment
MethodofUse	Standalonesoftware applicationaccessed via acompliant browser(Chrome, MozillaFirefox and Edge)on apersonalcomputer, tablet orphone (In case ofconnection to theplatform with ascreen of a phoneor a tablet, the usermust choose theoption for thedesktop site of hiscommunicationdevice.Theplatform is optimallyused with 17 inchesand up screen.Facilitates displayand visualization ofdata by user.	Standalone softwaredevice	Standalonesoftware applicationaccessed via acompliantbrowser(Chrome or MozillaFirefox) on apersonal computer,tablet or phone (Incase of connectionto the platform witha screen of a phoneor a tablet, the usermust choose theoption for thedesktop site of hiscommunicationdevice. The platformis optimally usedwith 17 inches andup screen.Facilitates displayand visualization ofdata by user.	Computer basedsoftware device	Computer basedsoftware device	The proposed device and the primarypredicate are both standalonesoftware. More details have beenfound on the reference deviceART-Plan v1.10.1 which has identicalmethods of use than the proposeddevice. An improvement has beenintroduced with ART-plan v2.1.0 as itcan be also used on Edge browser.
DataVisualization/GraphicalInterface	Yes	Yes	Yes	Yes	Yes	The proposed device, the primarypredicates and all references deviceshave a data visualisation and graphicalinterface
SyntheticCT	Generation of CTdensity imageseries out ofmultiple MR-imageseries and CBCTimages	Generation of CTdensity image seriesout of CBCT images	Generation of CTdensity imageseries out ofmultiple MR-imageseries	N/A	N/A	The proposed device and primarypredicate can generate synthetic-CTfrom CBCT image.The proposed device can generatesynthetic CT from CBCT and MRimages whereas it is not possible with
						the primary predicate to do so with MR images. This does not represent an additional claim as the technological characteristics are the same and it does not raise different questions of safety and effectiveness. Also, this feature is covered by the reference device ART-Plan v1.10.1, which is the previous version cleared of the proposed device ART-Plan v2.1.0.
Dose computation	Dose computation on CT and/or synthetic-CT images for external beam irradiation with photon beams	Dose calculation with AAA dose calculation model and Acuros XB dose calculation algorithm on CT and / or synthetic CT images	N/A	The AAA dose calculation model is a 3D convolution/superposition algorithm that models primary photons, photons scattered in the medium, contamination electrons and transport electrons near tissue heterogeneities. The AAA dose calculation model is comprised of two main components, one being the configuration algorithm and the other one the actual dose calculation algorithm.	AcurosXB dose calculation algorithm	The proposed device, the primary predicate and some reference devices ECLIPSE WITH AAA and Eclipse Treatment Planning System can perform dose computation.
Off-line adaptation decision-making	Assisted CBCT-based off-line adaptation decision-making for supported anatomies	Ethos Treatment Management allows the physician to do initial planning, review and approve candidate plans, and monitor ongoing treatments. Support for adaptive radiotherapy	N/A	N/A	N/A	The proposed device and the primary predicate can assist off-line adaptation decision-making.
		treatment planningand automated plangeneration
SupportedModalities	Registration:Static and gated CT,MR, PET (via theregistration of theCT of said PET),4D-CT, CBCT andsynthetic-CTgenerated fromCBCTSegmentation:CT (injected or not),MR images, DICOMRTSTRUCT,synthetic-CT fromCBCT	Registration:CT(includingsynthetic CT fromCBCT), MR andPETSegmentation:CT and synthetic CTfrom CBCT	Registration:Static and gated CT(including 4D-CTand CBCT), MR,PET (via theregistration of theCT of said PET)Segmentation:CT (injected or not),MR images, DICOMRTSTRUCT	Segmentation:Eclipse also includestools for treatmentpreparation(diagnostic imageand analysis,contouring andsegmentation) andplan review.	Registration:CT/MR/PET ImageRegistration4D image display(registration of timeyes yes series of 3Dimages)Segmentation:Geometrical shapes,Manual editing andmanipulation tools,Automatic/semi-automatictools,Automatic/semi-automatic on-demandand post-processingtools for individualorgans/structures,Automatic on-demandand pre-processing toolsfor multipleorgans/structures, 3DAutornargin, Logicaloperators	The proposed device, the primarypredicate and most of the referencedevices propose both registration andsegmentation on medical images ofdifferent modalities.
Data Export	Distribution ofDICOM compliantImages into otherDICOM compliantsystems.	ARIA RadOncintegration, DICOMRT, other imageformats, eclipsescripting API(ESAPI) read onlyaccess, eclipsescripting API(ESAPI) writeaccess, Eclipseautomation, Exportfield coordinates tolaser system	Distribution ofDICOM compliantImages into otherDICOM compliantsystems.	DICOM including RTobjects, MDC shaperfiles, blocks andcompensator data toPar Scientific, planand dose data topicker AcQSim,integrated with Varisverification, ASCIIfileto laser system,Varian CadPlan plus6.0	VARIS/Visiondatabase integration,DICOM RT/3.0, otherimage formats,export fieldcoordinates to lasersystem	The proposed device, the primarypredicate and reference devices haveidentical data export capabilities withDICOM format.
		RT prescriptioninformation available
Compatibility	Compatible withdata from anyDICOM compliantscanners for theapplicablemodalities.	ARIA RadOncintegration, DICOMRT, other imageformats,electromagneticdigitizer, eclipsescripting API(ESAPI) read onlyaccess, eclipsescripting API(ESAPI) writeaccess, eclipseautomation, BasicRT prescriptioninformation available	Compatible withdata from anyDICOM compliantscanners for theapplicablemodalities.	DICOM including RTobjects, CARTformat, TIFF format,CMP format,Configurable purepixel data,PortalVision MArk 1& 2, Varian CToption,ElectromagneticDigitilizer, Filmscanner	VARIs/Visiondatabase integration,DICOM RT/3.0, otherimage formats,Electromagneticdigitizer, film scanner	The proposed device, the primarypredicate and reference devices haveidentical compatibility (DICOM format)

Page 9 of 31

{12}------------------------------------------------

Page 10 of 31

{13}------------------------------------------------

Page 11 of 31

{14}------------------------------------------------

Technical Information Comparison

		Technical Information
Property	Proposed DeviceART-Plan v2.1.0	Primary PredicateEthos TreatmentManagement, 2.1;Ethos TreatmentPlanning, 1.1	Reference deviceART-Planv1.10.1	ReferencedeviceECLIPSE WITHAAA	Reference deviceEclipse TreatmentPlanning System	Comment
DelineationMethod	Al	Al	Al	Not stated	Not stated	The proposed device, primary predicate andone of the reference devices (ART-Planv1.10.1) share an Al delineation method.
Imageregistration	Multi-modal andmono-modal.Rigid and deformableAutomatic andmanual initialization(landmarks, fusionbox, alignment).Registration for thepurposes ofreplanning/	Registration:CT (includingsynthetic CT fromCBCT), MR andPET	Multi-modal andmono-modal.Rigid and deformableAutomatic andmanual initialization(landmarks, fusionbox, alignment).Registration for thepurposes of	NA	CT/MR/PET ImageRegistration4D image display(registration of timeyes yesseries of 3D images)	The proposed device, the primary predicate andmost of the reference devices proposeregistration of medical images of differentmodalities.
	recontouring andAI-based automaticcontouring.	CT and synthetic CTfrom CBCT	replanning/recontouringandAI-based automatic contouring.
Segmentation Features	Automaticallydelineates OARs andhealthy lymph nodesDeep learningalgorithm.Automaticsegmentationincludes the followinglocalizations:* head and neck (onCT images)* thorax/breast (formale/female and onCT images)* abdomen (on CTimages and MRimages)* pelvis male (on CTimages and MRimages)* pelvis female (on CTimages)* brain (on CT imagesand MR images)		Automaticallydelineates OARs andhealthy lymph nodesDeep learningalgorithmAutomaticsegmentationincludes the followinglocalizations:* head and neck (onCT images)* thorax/breast (formale/female and onCT images)* abdomen (on CTimages and MRimages)* pelvis male (on CTimages and MRimages)* pelvis female (onCT images)* brain (on CT imagesand MR images)	Eclipse alsoincludes tools fortreatmentpreparation(diagnostic imageand analysis,contouring andsegmentation) andplan review.	Geometrical shapes,Manual editing andmanipulation tools,Automatic/semi-automatictools,Automatic/semi-automatic on-demandand post-processingtools for individualorgans/structures,Automaticon-demand andpre-processing toolsfor multipleorgans/structures, 3DAutornargin, Logicaloperators	The proposed device, the primary predicate andmost of the reference devices proposesegmentation on medical images of differentmodalities using Al.
ViewManipulationandVolumeRendering	Window and level,pan, zoom,cross-hairs, slicenavigation.Color rendering, fusedviews, gallery views.	Window and level,pan, zoom,cross-hairs, slicenavigation.Color rendering,fused views, galleryviews.	Window and level,pan, zoom,cross-hairs, slicenavigation.Maximum, averageand minimumintensity projection(MIP, AVG, MinIP),color rendering,multi-planarreconstruction (MPR),fused views, galleryviews	Not stated	Not stated	The proposed device has the same tools as theprimary predicate.
Regions andVolumesof Interest(ROI)	AIBasedautocontouring,Registration basedcontour projection(re-contouring),Manualmanipulation andtransformation(margins, booleansoperators,interpolation).	AI basedautocontouring,Registration basedcontour projection(re-contouring)Manualmanipulation andtransformations(margins, booleansoperators,interpolation).	AIBasedautocontouring,Registration basedcontour projection(re-contouring),Manualmanipulation andtransformation(margins, booleansoperators,interpolation).	Not stated	Not stated	Both the proposed device and the primarypredicate allow AI automatic contouring andmanual contouring.
Region/volume ofinterestmeasurements andsizemeasurements	IntensityandHounsfield units.Sizemeasurementsinclude 2Dand 3Dmeasurements(number ofslices,volume of a structure,static ruler)	Intensity, Hounsfieldunits.Size measurementsinclude 2D and 3Dmeasurements(number ofslices,volume of astructure,staticruler)	Intensity, Hounsfieldunits, and SUVSize measurementsinclude 2D and 3Dmeasurements(number of slices,volume of a structure,static ruler)	Not stated	Not stated	The proposed device offers the same kind ofregion/volume of interestmeasurements and size measurements as theprimary predicate.

{15}------------------------------------------------

{16}------------------------------------------------

{17}------------------------------------------------

Device Description:

Compared to Ethos Treatment, 2.1; Ethos Treatment Planning, 1.1 (primary predicate), the following additional feature has been added to ART-Plan v2.1.0:

generation of synthetic CT from MR images. This does not represent an additional . claim as the technological characteristics are the same and it does not raise different questions of safety and effectiveness. Also, this feature is already covered by reference and previous version of the device ART-Plan v1.10.1.

Generation ofSynthetic CT	ART-Plan V2.1.0(Proposed device)	Ethos TreatmentManagement, 2.1;Ethos TreatmentPlanning, 1.1(primarypredicate)	ART-Plan v1.10.1(reference device andprevious version of theproposed device)
from MR images	✓		✓
from CBCT images	✓	✓

The ART-Plan technical functionalities claimed by TheraPanacea are the following:

. Proposing automatic solutions to the user, such as an automatic delineation, automatic multimodal image fusion, etc. towards improving standardization of processes/ performance / reducing user tedious / time consuming involvement.
. Offering to the user a set of tools to assist semi-automatic delineation, semi-automatic registration towards modifying/editing manually automatically generated structures and addina/removing new/undesired structures or imposing user-provided correspondences constraints on the fusion of multimodal images.
. Presenting to the user a set of visualization methods of the delineated structures, and registration fusion maps.
. Saving the delineated structures / fusion results for use in the dosimetry process.
. Enabling rigid and deformable registration of patients images sets to combine information contained in different or same modalities.
Allowing the users to generate, visualize, evaluate and modify pseudo-CT from MRI and CBCT images.

{18}------------------------------------------------

. Allowing the users to generate, visualize and analyze dose on images of CT modality (only within the AdatpBox workflow)
. Presenting to the user metrics to define if there is a need for replanning or not.

ART-Plan offers deep-learning based automatic segmentation for the following localizations:

head and neck (on CT images) .
thorax/breast (for male/female and on CT images) .
abdomen (on CT images and MR images) ●
pelvis male(on CT images, on synthetic-CT from CBCT and on MR images) ●
pelvis female (on CT images) .
brain (on CT images and MR images) .

ART-Plan offers deep-learning based synthetic CT-generation from MR images for the following localizations:

pelvis male .
brain

ART-Plan offers deep-learning based synthetic CT-generation from CBCT images for the following localizations:

· pelvis male

Technological Characteristics:

A comparative review of the ART-Plan with the predicate device found that the technology. mode of operation, and general principles for treatment with this device were substantially equivalent as the predicate device.

Information about our training dataset and generalizability of the models:

A method generalizes well if the observed performance on training and validation sets remains stable. In the case of strong presence of expert's annotation variability (that is not necessarily because of erroneous annotations but because image quality/orqan visibility can be interpreted differently among experts), a method that can demonstrate similar performance with respect to a given metric on training, validation and later on testing is considered to generalize well.

In that process, both the loss function being optimized by the optimization procedure (stochastic gradient descent) and the dice metric which is the main proxy of segmentation quality, are monitored over the train and validation sets. If the loss is non-increasing on the validation set and if the dice metrics follow similar in value trends in both the validation and training sets, it is considered that the model being trained does not overfit, and hence should generalize well, at least on input domains similar to ones in those sets.

On the contrary, overfitting can be detected whenever the training loss keeps decreasing while the validation loss after a while increases. This means that the model is focusing on features that are specific to the training data and not present in the validation data. This implies that the capacity of the model to generalize is poor. In that respect, the independence of the train/validation/test sets is fundamental.

We consider that a model is a good candidate for production when the following conditions are met: 1) the loss and dices have reached a plateau on the validation set, 2) there is no overfitting, i.e. training and validation curves are similar and 3) the level of the dice for the different organs are as good or above the clinical expectations according to well defined performance criteria.

{19}------------------------------------------------

The learning curves of organs may be different depending on the sizes and shapes (difficulties) of structures (organs). Thus, the range of testing scores, Dice Similarity Coefficient (DSC), may vary. It is important to remember that smaller orqans might have smaller DSC and yet be still clinically relevant and acceptable, as the DSC is a relative metric that is heavily dependent on the volume of the organ. This is due to the fact that the DSC scores are normalized from the union of organ volume between the two sets (ground truth, automatic annotations) and therefore lower DSC could correspond to clinically acceptable values for small organs, since the proposed contours might take just a few editions to make them usable for planning, whilst still saving time from the users, i.e. that these contours would be judged "clinically acceptable after minor corrections" in a qualitative evaluation.

Learning curves can have an average DSC and loss function for each epoch (which is an iteration of training where the whole training dataset has been passed to the network) over the training set and over the validation set. Our curves show that validation and training data are very close to each other, reaching convergence after some epochs (depending on the structure), demonstrating no overfitting of the training data. Once convergence is achieved, the model is considered ready to be tested and clinically validated on a different, yet representative data set, following a well-established process of validation that has already been submitted to and cleared by the FDA.

Some limitations have been identified that correspond either to the sex or the age of patients. For instance, for the auto-segmentation model following limitations are disclosed to the user in the Instruction For Use (User Manual) based on the sex of the patient:

-The Truefisp Pelvis MRI and T2 Elekta Pelvis MRI auto-contouring models only work on male anatomy.
-The patient sex of the patient (dicom tag (0010, 0040)) is taken into account for the auto-segmentation:
- if the tag is "F" or "M", the sex specific organs (prostate, breast, etc.) are contoured according

to the tag

if the tag is emptv or "O":
- ' if batch: no contour is delineated except external contour
  - if auto segmentation on Annotate: only common contours to the 2 sexes are delineated
if the tag is incorrect, the generated contours may be inappropriate -

The automatic contouring (including external contour) function may generate inappropriate contours in the following cases:

When the volume used is an image taken of a child -
-When the patient has a particular anatomy.
When the considered volume is that of a patient not positioned on his back at the time of acquisition.
-When the value entered in the Patient Position tag (0018, 5100) is erroneous.
-When the DICOM-CT contains an unusually high number of slices.
When the quality of the images used as input is not satisfying enough or the resolution is low such as CBCT. Therefore, the contours produced may have a low quality.
-When the primary volume is an MRI whose acquisition sequence is not compatible with the selected auto-contouring model.

{20}------------------------------------------------

When the patient is unusually positioned on the image (image not centered on the patient, head rotated on the side ... )
Only some anatomies are covered by the automatic contouring:
Automatic contouring on CT images covers all anatomies (Head & Neck, thorax. breast, abdominal region and pelvis (M/F)
-Automatic contouring on MR images covers some sequences and anatomies: Brain T1, Abdo TF (TrueFisp), Pelvis (male) T2, Pelvis (male) TF.
-Automatic contouring on synthetic-CT from CBCT covers pelvis (male) anatomy.
-In order to suggest the most relevant structures to the user, a CT that does not include a chiasma but does include a liver, is not considered as Head and Neck case. In that case, no Head and Neck structures will be automatically segmented.

All information on the limitations of some models is included in the Instruction For Use (User Manual) which is made available to all users of the software.

. Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance:

Acceptance criteria for performance of ART-Plan modules were established using performance ranges extracted from benchmark devices and alternative technologies in the literature. For an auto segmentation model to be judged acceptable, every organ included in the model must pass at least one acceptance criterion with success across the different testings it has been submitted to. These criteria are as follows:

a) The Dice Similarity Coefficient (DSC) is equal to or superior to the acceptance criteria set by the AAPM: DSC (mean)≥ 0.8.

b) The Dice Similarity Coefficient (DSC) is equal to or superior to inter-expert variability: DSC (mean)≥ 0.54 or DSC (mean) ≥ mean (DSC inter-expert) + 5% . Or

c) The clinicians' s qualitative evaluation of the auto-segmentation is considered acceptable for clinical use without modifications (A) or with minor modifications / corrections (B) with a A+B % above or equal to 85% considering the following scale:

A: the contour is acceptable for a clinical use without any modification

B: the contour would be acceptable for clinical use after minor modifications/corrections

C: the contour requires major modifications (e.g. it would be faster for the expert to manually delineate the structure)"

For the SmartFuse module, the acceptance criteria are as follows:

1. ART-Plan SmartFuse produces an anatomical registration of a source image towards a target image for which:
- a) Dice Similarity Coefficient (DSC) of the segmented registered and non registered image is equal to or superior to the acceptance criteria set by the AAPM: DSC(mean)≥0.81
- b) Dice Similarity Coefficient (DSC) of the segmented registered and non registered image is equal to or superior to a benchmark device: DSC(mean)≥0.65
- c) The clinicians' qualitative evaluation of the propagated contours post-registration are considered acceptable for clinical use without

{21}------------------------------------------------

modifications (A) or with minor modifications/corrections (B) with A+B% above or equal to 85% for deformable and above or equal to 50% for rigid registration considering the following scale:

A: the contour is acceptable for a clinical use without any modification i)
B: the contour would be acceptable for a clinical use after minor ii) modifications/corrections
C: the contour requires major modifications (e.g. it would be faster for iii) the expert to manually delineate the structure)
d) The clinicians' qualitative evaluation of the overall registration output following clinical protocols to qualitatively assess registration outcomes is considered acceptable for clinical use with A+B% above or equal to 85% for deformable and 50% for rigid registration considering the following scale:
- A: the registration exceeds the expectation i)
- B: the registration meets the expectation (incl. cases for which ii) additional margin may be required or registration might be relaunched using different supporting tools)
- C: the registration is not acceptable iii)
1. ART-Plan SmartFuse module produces an anatomical registration of a source image towards a target image for which the Jacobian Determinant need to be positive
1. ART-Plan SmartFuse module produces an anatomical registration of a source image towards a target image for which the target registration error (TRE) must be bellow the acceptance criteria set by the AAPM (maximum voxel size of the pair of images involved): TRE<2mm (POPI database)

For the synthetic-CT generation tool from MR, the acceptance criteria are as follows:

A median 2%/2mm gamma passing criteria of ≥95% a.
A median 3%/3mm gamma passing criteria of ≥99.0% ﻘ
A mean dose deviation (synthetic-CT compared to standard CT) of ≤2% in ≥88% of C. patients

For the synthetic-CT generation tool from CBCT, the acceptance criteria are as follows:

A median 2%/2mm gamma passing criteria of ≥92% a.
A median 3%/3mm gamma passing criteria of ≥93.57% b.
C. A mean dose deviation (synthetic-CT compared to standard CT) of ≤2% in ≥76.7% of patients

For the dose engine function, the acceptance criteria are as follows:

a. DVH or median dose deviation ≤24.4% for Lung tissue or ≤4.4% for other organs
a median 2%/2mm gamma passing rated of ≥86.3% ﻘ
A median 3%/3mm gamma passing criteria of ≥91.75% C.

. Total number of individual patients images in the reported auto segmentation tools and independence of test data and training data

Our training, validation and test cohorts are built from real-world retrospective data which were initially used for treatment of cancer patients. For the structures of a given anatomy for a given modality (MR or CT), two non-overlapping data sets were separated: the test patients (number selected based on thorough literature review and statistical power) and the train data. We make sure that those sets are non-overlapping and further split the train cases into train and

{22}------------------------------------------------

validation sets and ensure enough train cases for the machine learning models to converge and achieve good performances of the validation set.

We choose the proportion of the training data that is kept as validation set to be between 10% and 25%, depending on the absolute amount of training data. Having more validation data is important to better assess the robustness and generalization of the models as long as enough data is kept for training. This explains that this validation proportion may vary from one task to the other.

Auto-segmentation tool

	SampleSize	%
Training	246226	78
Validation	69147	22
Total	315373	100

Synthetic-CT from MR images ●

	Sample Size	%
Training	6195	77
Validation	1839	23
Total	8034	100

Synthetic-CT from CBCT images ●

	SampleSize	%
Training	1467	88
Validation	203	12
Total	1670	100

Table 2: Distribution of samples between training and validation data sets

. Total number of cases and samples images for training in the reported auto segmentation results

The total number of patients used for training of auto-segmentation (8950) is lower than the number of samples (246226). This is linked to the fact that one patient can be associated with more images (e.g. CT. MR) and that each image (anatomy) has the delineation of several structures (OARs and lymph nodes) which increases the number of samples used for training and validation. The same rationale for the generation of synthetic-CT from CBCT or MR images.

Demographic distribution including gender, age and ethnicity ●

{23}------------------------------------------------

All data used for training of the models have been pseudo-anonymised by the centers providing data before transfer. Around 88% of the data used for training contain information on gender and age of the patients. In terms of gender, around 44% and 56% of our data (that contains this information) are from female and male patients, respectively. In comparison, in 2020 according to the Global Cancer Observatory, 48% and 52% of the cancer patients were female and male, respectively.

In terms of age, our data follows the same trend observed and reported in the US (SEER NIH). UK (Cancer Research UK) and worldwide (Global Cancer Observatory) for cancer incidence according to age, with more than 95% of the data coming from patients between 20 and 85 years old. Our data has a slight overrepresentation (8% points) for the ages between 54 and 64 years old, at the cost of a slight underrepresentation of patients in the age range between 20-34 (1.5% points) and above 85 (2.1% points) years old. In addition, following the general global (incl US) trend, our data also depicts a steep rise in the incidence rate from in the age group of 55-64 years old, with a median age of 64 years old (as compared to 66 years old in the US).

Although this information is not exhaustive, this analysis shows that the demographic distribution in terms of age and gender of the data used for training and validation of the models are well aligned with the incidence cancer statistics found for instance in US, UK and globally. This comes from the fact that real clinical data provided by medical facilities without any selection criteria (i.e. no discrimination or selection has been applied to the cases retrieved), leading to the demographic distribution including gender and age across the data is representative of the distribution in the clinic and thus of the cancer patient population in general.

In terms of anatomies, the training data overall is made of 16.4% brain. 28.1% head and neck, 24.6% thorax, 4.4% abdominal and 26.4% pelvis.

An exception is noted for following models that are gender-dependent:

100% of pelvis images for male pelvis model for automatic annotation are male patients
100% of pelvis images for female pelvis model for automatic annotation are female patients
100% of breast images for the breast automatic annotation are female patients
100 % of pelvis images for automatic synthetic-CT generation from CBCT and MR are male patients

Since we use pseudo-anonymized data for training and this data does not include any information on ethnicity, TheraPanacea is not able to assess the data distribution and representation in terms of ethnicity.

In addition, automatic delineation of the device demonstrated equivalent performances between non-US and US population.

● On the "truthing" and data collection process

Autosegmentation ●

The contouring guidelines followed to produce the contours were confirmed with the centers which provided the data. Our truthing process includes a mix of data created by different delineators (clinical experts) and assessment of intervariability, ground truth contours provided by the centers and validated by a second expert of the center, and qualitative evaluation and validation of the contours. This process ensures that the data used for training and testing can be considered representative of the delineation practice across centers and is following international guidelines.

{24}------------------------------------------------

Generation of synthetic-CT (from MR or CBCT) ●

The clinical evaluation as part of the "truthing-process" guidelines followed to produce and validate the synthetic-CTs were extracted from the literature and confirmed with the centers which provided the data and helped in the performance evaluation. Our truthing process includes imaging metrics based comparison between synthetic-CTs and real planning CTs for the same patients. The real planning CTs come from a mix of machines and centers to avoid any bias. In addition, the evaluation includes a non-inferiority assessment of the capability of the synthetic-CT to be used for dose generation purposes as compared to a planning CT. This process ensures that the data used for training and testing can be considered representative of the clinical practice across centers and following the processes outlined and reviewed through the literature review.

On clinical subgroups, confounders and equipment details .

In general, confounding factors affecting health status present in the dataset could be related to patient clinical variables such as age, gender, ethnicity, economical and educational levels. As shown in "Demographic distribution including gender, age and ethnicity", our data is representative of the demographic cancer distribution in terms of gender and age. In addition, our models when appropriate (i.e. for gender independent anatomies) are shared across gender removing any further bias and augmenting substantially training cohorts. To assess potential subgroup bias in Al models, a fairness methodology is used for each subgroup. The analysis raised no significant concerns about the introduction of unfair biases in the Al models for any of the identified subgroups (age and gender).

Variables like ethnicity, economical and educational status that could be associated with obesity are further confounding factors that could impact global patient's anatomy and introduce bias in the performance of the obtained solution. To address this aspect, we have adopted a strategy that projects a patient's specific anatomy to common, multiple, different in size, full-body female and male patient templates, allowing a direct harmonization of data resulting in potential removal of bias of anatomical diversity across ethnic, economical and educational groups. Please note that this information (ethnic group, educational/economical level, etc.) is often not available in the pseudo-anonymised data and therefore performing statistical tests and increasing the number of operations allowing to separate correlations from causality is often unattainable.

Regarding variables associated with treatment therapeutic and treatment implementation strategies; we can imaging devices and treatment devices being potential confounding factors as differences exist among CT and MR scanners manufacturers that could potentially introduce bias. We have addressed this concern through a statistical analysis of the different imaging vendors in EU & USA towards the creation of a data training, validation and testing cohort that globally appropriately represents the market share of the different vendors allowing generalization and removing hardware specific bias. In terms of treatment implementation, it should be noted that different guidelines exist and depending on the treatment device different therapeutic constraints and guidelines are applied. This is reflected in our database since different strategies and constraints are used depending on the choice of treatment (e.g external radiotherapy vs stereotactic treatment). Our solution, due to its concept of removing bias through projection to patient template anatomies as well as due to the component-based approach that is able to aggregate training data across imaging and treatment vendors, is able to address the maximum set of constraints. Therefore, we do not introduce any bias on the type of treatment that will be delivered (supporting any type of clinically conventionally adopted treatment from manufactures such as Varian, Elekta, Accuray, GE, Siemens, ViewRay & Zap

{25}------------------------------------------------

Surgical), providing direct means for customization of the constraints to be met at the clinical expert level and offering a representative coverage of all vendors in radiation oncology world-wide.

An exception is noted for following models that are vendor-, machine- or sequence-dependent:

MR annotation tool for pelvis and abdominal regions were trained on data from a -0.35T MR machine provided by ViewRay
synthetic-CT generation tool for pelvis was trained on data from a 0.35T MR machine provided by ViewRay
synthetic-CT generation tool and annotation tool for MR pelvis was trained on data from 1.5T Philips (Elekta) for T2 sequences, and might not work on T1-weighted images
synthetic-CT from CBCT generation tool for pelvis male was trained on data coming from Varian and Elekta machines

{26}------------------------------------------------

Summary of Verification and Validation Activities

In Table 3, a summary of Performance Test Results for the Annotate Module of ART-Plan (since the latest cleared version of the software in v1.10.1) is presented:

	Organ	Performance test method/Acceptance criterion	Summary of results	Any differences to protocol?
1.	Duodenum	Intervariability comparison to expertsCriterion CMin sample size for evaluation method: 20	DICE diff inter-expert=1.32%Passed	Sample size: 25which is above the minimum data sample size
2.	Large bowel	Intervariability comparison to expertsCriterion CMin sample size for evaluation method: 20	DICE diff inter-expert=1.19%Passed	Sample size: 25which is above the minimum data sample size
3.	Small bowel	Intervariability comparison to expertsCriterion CMin sample size for evaluation method: 20	DICE diff inter-expert=2.44%Passed	Sample size: 25which is above the minimum data sample size
4.	Right lacrimal gland	Qualitative evaluation by expertsCriterion DMin sample size for evaluation method: 15	A+B=100%Passed	Sample size: 20which is above the minimum data sample size
5.	Left lacrimal gland	Qualitative evaluation by expertsCriterion DMin sample size for evaluation method: 15	A+B=100%Passed	Sample size: 20which is above the minimum data sample size
6.	cervical lymph nodes VIA	Qualitative evaluation by expertsCriterion DMin sample size for evaluation method: 15	A+B=97%Passed	Sample size: 20which is above the minimum data sample size
7.	Cervical lymph	Qualitative evaluation by experts	A+B=100%	Sample size: 20
	nodes VIB	Criterion DMin sample size for evaluationmethod: 15	Passed	which is above theminimum data samplesize
8.	Pharyngealconstrictormuscle	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=100%Passed	Sample size: 20which is above theminimum data samplesize
9.	Anal canal	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=98.68%Passed	Sample size: 38which is above theminimum data samplesize
10.	Bladder	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=93.42%Passed	Sample size: 38which is above theminimum data samplesize
11.	Left femoralhead	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=100%Passed	Sample size: 38which is above theminimum data samplesize
12.	Right femoralhead	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=100%Passed	Sample size: 38which is above theminimum data samplesize
13.	Penile bulb	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=96.05%Passed	Sample size: 38which is above theminimum data samplesize
14.	Prostate	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=92.10%Passed	Sample size: 38which is above theminimum data samplesize
15.	Rectum	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=100%Passed	Sample size: 38which is above theminimum data samplesize
	Criterion DMin sample size for evaluationmethod: 15	passed	which is above theminimum data samplesize
16. Seminal vesicle	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=94.59%Passed	Sample size: 37which is above theminimum data samplesize
17. Sigmoid	Qualitative evaluation by expertsCriterion DMin sample size for evaluationmethod: 15	A+B=98.68%Passed	Sample size: 38which is above theminimum data samplesize

{27}------------------------------------------------

TheraPanacea SAS

Traditional 510(k)

{28}------------------------------------------------

In Table 4, a summary of Performance Test Results for the SmartFuse module of ART-Plan (since the latest cleared version of the software in v1.10.1) is presented:

	Clinical use	Performance testmethod/Acceptance criterion	Summary of results	Any differences toprotocol?
1.	tCBCT - sCT	Qualitative evaluation by expertsCriterion 1DMin sample size for evaluationmethod: 15	Rigid: A+B%=95.56%Deformable:A+B%=97.78%Passed	Sample size: 45which is above theminimum data samplesize
2.	tsynthetic-CT -sCT	Qualitative evaluation ofpropagated contours by expertsCriterion 1CMin sample size for evaluationmethod: 17	Deformable:Target:A+B%=94.06%Passed	Sample size: 30which is above theminimum data samplesize
3.	tCT - sSCT	Qualitative evaluation by expertsCriterion 1DMin sample size for evaluationmethod: 17	Rigid: A+B%=70.37%Passed	Sample size: 27which is above theminimum data samplesize

In Table 5, a summary of Performance Test Results for the AdaptBox module of ART-Plan (since the latest cleared version of the software in v1.10.1) is presented:

{29}------------------------------------------------

TheraPanacea SAS

Traditional 510(k)

Criteria	Performance testmethod/Acceptance criterion	Summary of results	Any differences toprotocol?
Synthetic-CT from CBCT
Gamma index2%/2mm3%/3mm	Criteria A & BMin sample size for evaluationmethod: 17	2%/2mm = 98.853%/3mm = 99.43Passed	Sample size: 20which is above theminimum data samplesize
DVH parameters(PTV)	Criterion CMin sample size for evaluationmethod: 17	DVH parameters < 0.199% in 100% of thecasesPassed	Sample size: 20which is above theminimum data samplesize
Dose engine
Gamma index2%/2mm3%/3mm	Criteria B & CMin sample size for evaluationmethod: NA in the state of the art	2%/2mm = 97.22%3%/3mm = 99.50%Passed	Sample size: 272 totalBrain: 42H&N: 70Chest: 44Breast: 26Pelvis 90
DVH parameters(PTV)	Criteria AMin sample size for evaluationmethod: NA in the state of the art	DVH parameters < 1.29%Passed	Sample size: 272 totalBrain: 42H&N: 70Chest: 44Breast: 26Pelvis 90
DVH parameters(OARs)	Criteria AMin sample size for evaluationmethod: NA in the state of the art	DVH parameters < 3.9%Passed	Sample size: 272 totalBrain: 42H&N: 70Chest: 44Breast: 26Pelvis 90

{30}------------------------------------------------

Non-Clinical Tests (Performance/Physical Data):

In Table 6, testing based on which ART-Plan v2.1.0 (since the latest cleared version of the software in v1.10.1) was evaluated for its safety and effectiveness are presented:

Test Name	Test Description/Results	Results
Usability Report(V2.1.0)	This document is intended to document the usability testresults for the ART-Plan v2.1.0 for compliance with IEC62366-1:2015+AMD1:2020MedicaldevicesApplication of usability engineering to medical devices.	Passed
Usability file - ART-USR-13(V2.1.0)	The ART-Plan was assessed with regards to usability forcompliance with each section of IEC 62366.	Passed
Usability - Testers qualification(V2.1.0)	This table shows that European medical physicists whohave participated in the evaluation have at least anequivalent expertise level compared to a junior USmedical physicist (MP), and responsibilities intheradiotherapy clinical workflow are equivalent.	N/A
Literature Review andPerformance CriteriaExtraction Report for ART-Plan(V2.1.0)	A literature review is performed to establish acceptancecriteria for performance of ART-Plan modules usingperformance ranges observed from benchmark devicesalternative technologies in the literature. Allandmeasures of performance that were established in thisdocument were supported by clinical evidence. It wasalso demonstrated, from the clinical data, that ART-Planhas a clear clinical relevance in accordance with theclinical state of the art.	N/A
ART-Plan performance testing- Overview(V1.10.1-2.1.0)	The document summarises all performance tests thathave been performed since the last FDA approvedversion (1.6.1). It also shows which criteria have beenmet in each test for all modules of ART-Plan. Itdemonstrates that all modules of ART-Plan pass at leastone performance acceptance criterion and hence areclinically acceptable for release.	Passed
Pilot study for sample sizeestimation - literature review(V2.1.0)	The literature review was performed to estimate theappropriate sample size of the testing data set towardsdemonstrating the performance of the image registration,segmentation and synthetic-CT generation solutions onthe basis of the most recent and most relevant scientificliterature.	N/A
Qualitative & Quantitativevalidation of fusionperformances (V2.1.0)	The study was developed to cover the major clinical usecases in which fusions are used in the radiotherapyworkflow and split into as many sub-studies as clinicaluse cases of fusion in radiotherapy workflow. The resultsshow that both types of fusion algorithms (Rigid &Deformable) in SmartFuse pass the performed tests, andprovide valid results for further clinicaluseinradiotherapy.	Passed
Protocol for qualitative &quantitative validation of fusionperformances fortCBCT sCT replanningmodality (V2.0.0)	This study evaluated the quality of the rigid and thedeformable fusion algorithms of the SmartFuse modulefor replanification of CT-based treatments.	Passed
Protocol for qualitative &quantitative validation of fusionperformancesfortsynthetic-CT_SCT_replanningmodality (V2.1.0)	This study evaluated the quality of the rigid and thedeformable fusion algorithms of the SmartFuse modulefor replanification of CT-based treatments.	Passed
Protocol for qualitative &quantitative validation of fusionperformancesfortCT_ssynthetic-CT_replanningmodality (V2.1.0)	This study evaluated the quality of the rigid and thedeformable fusion algorithms of the SmartFuse modulefor replanification of CT-based treatments.	Passed
	The purpose of this document is to describe all the testingprotocols and testing results for validating theperformance of the Annotate module.
Study Protocol and ReportAnnotate PerformancesSummary (V2.1.0)	To this aim, this document gathers information of all thedifferent testing conducted on Annotate for the CT, MRand synthetic-CT from CBCT autosegmentationalgorithms for v2.1.0:qualitative evaluation for autosegmentationperformance - pelvis male organs onsynthetic-CT from CBCT - see section 18.13 autosegmentation performances againstinter-expert variability - bowel loop structures onCT - see section 18.14 qualitative evaluation for autosegmentationperformance - H&N lymph nodes (CT) - seesection 18.15 Non regression testing for integration inART-Plan v1.11.0 (CT and MR models) - seesection 18.7 Non regression testing for integration inART-Plan v2.1.0 (CT and MR models) - seesection 18.16 Since all organs added in v.2.1.0 of Annotate havepassed at least one test and met at least one acceptancecriteria, all organs have been released.	Passed
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan for pelvismale organs on synthetic-CTfrom CBCT (V2.1.0)	This test demonstrates that the module Annotateprovides acceptable contours for the organs evaluated onsynthetic-CT from CBCT images of patients. All organsthat have passed the acceptance criterion of reaching apercentage of at least 85% of A or B (qualitativeevaluation) have been released in v.2.1.0.	Passed
Study Protocol and Report-Autosegmentationperformances againstinter-expert variability - bowelloop structures (V2.1.0)	This test demonstrates that the module Annotateprovides clinically acceptable (compared to inter-expertvariability) for bowel loops structure. All organs that havepassed the acceptance criterion of reaching a percentageof a DSC(mean)≥ 0.8 or DSC(mean)≥0.54) orDSC(mean)≥mean(DSC inter-expert)+5% relative error(quantitative evaluation) have been released in v.2.1.0.	Passed
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan for H&Nlymph nodes (V2.1.0)	This test demonstrates that the module Annotateprovides acceptable contours for the organs evaluated onCT images of patients. All organs that have passed theacceptance criterion of reaching a percentage of at least85% of A or B (qualitative evaluation) have been releasedin v.2.1.0.	Passed
Autosegmentation regressiontest for integration in ART-Plan(V2.1.0)	This test demonstrates equivalence between the versionv.2.1.0 and v.2.0.0 of the auto-segmentation models forall structures and shows that the updated models provideclinically acceptable contours. All organs passed thedefined criteria, and were hence accepted for release inthe v.2.1.0.	Passed
Study protocol and reportDose engine measurementsvalidation (V2.1.0)	The evaluation demonstrated the dose calculationaccuracy by carrying out measurements on a Linac andcomparing the results with the dose engine given variousmetrics and acceptance criteria.	Passed
Study protocol and reportDose engine clinical validation(V2.1.0)	The evaluation demonstrated the non-inferiority of thedose engine function of the AdaptBox module in terms ofdosimetric measures compared to other commerciallyavailable dose engines.	Passed
Study protocol and reportDose engine performanceagainst reference devices(V2.1.0)	The evaluation demonstrated the non-inferiority of thedose engine function of the AdaptBox module in terms ofdosimetric measures compared to FDA cleared devices.	Passed
Study protocol and reportClinical validation ofsynthetic-CTs from CBCT(V2.1.0)	The evaluation demonstrated the non-inferiority of usingsynthetic-CT from CBCT for treatment replanning interms of dosimetric measures as compared to CT-basedtreatment replanning. Our synthetic-CT from CBCT forpelvis has shown to produce results that meet theacceptance criteria derived from clinical practice andliterature review.	Passed
Study protocol and reportPerformance against Ethos(Varian) (V2.1.0)	The evaluation demonstrated the non-inferiority of theAdaptBox module compared to a FDA cleared device.	Passed
Study protocol and reportPerformance on US data(V2.1.0)	The evaluation demonstrated the equivalentperformances between non-US and US population.	Passed
Study Protocol and Report forCBCT-based synthetic-CTevaluation (V2.1.0)	The evaluation demonstrated the anatomical andgeometrical of the synthetic-Ct generated from CBCT	Passed
Al-powered decision makingprocess for RT re-planning(V2.1.0)	This study demonstrated that AdaptBox is an effectivetool to assist physicians and physicists in the decisionmaking process for re-planning	Passed
System Verification andValidation Testing (V2.1.0)	The system verification and validation testing wasperformed to verify the software of the ART-Plan.	Passed

{31}------------------------------------------------

TheraPanacea SAS

Traditional 510(k)
Traditional 510(k)

{32}------------------------------------------------

Software Verification and Validation Testing

Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."

The software for this device was considered as a "major" level of concern, since a failure or latent design flaw could directly result in death or serious injury to the patient or a failure or provide diagnostic information that directly drives a decision regarding treatment or therapy, such that if misapplied it could result in serious injury or death.

Animal Studies

{33}------------------------------------------------

No animal studies were conducted as part of submission to prove substantial equivalence.

Clinical Studies

No clinical studies were conducted as part of submission to prove substantial equivalence.

Safety and Effectiveness/Conclusion:

Based on the information presented in these 510(k) premarket notifications the TheraPanacea ART-Plan is considered substantially equivalent. The TheraPanacea ART-Plan is as safe and effective as the currently marketed predicate device.

Based on testing and comparison with the predicate devices, TheraPanacea ART-Plan indicated no adverse indications or results. It is our determination that the TheraPanacea ART-Plan performs within its design specifications and is substantially equivalent to the predicate device.

Regulation Number and Section

§ 892.5050 Medical charged-particle radiation therapy system.

(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.