ART-PLAN by TheraPanacea | FDA 510(k) Summary

ART-Plan is indicated for cancer patients for whom radiation treatment has been planned. It is intended to be used by trained medical professionals including, but not limited to, radiation oncologists, dosimetrists, and medical physicists.

ART-Plan is a software application intended to display and visualize 3D multi-modal medical image data. The user may import, define, display, transform and store DICOM3.0 compliant datasets (including regions of interest structures). These images, contours and objects can subsequently be exported/distributed within the system, across computer networks and/or to radiation treatment planning systems. Supported modalities include CT, PET-CT, CBCT, 4D-CT and MR images.

ART-Plan supports Al-based contouring on CT and MR images and offers semi-automatic and manual tools for segmentation.

To help the user assess changes in image data and to obtain combined multi-modal image information, ART-Plan allows the registration of anatomical and functional images and display of fused and non-fused images to facilitate the comparison of patient image data by the user.

With ART-Plan, users are also able to generate, visualize, evaluate and modify pseudo-CT from MRI images.

Device Description

The ART-Plan application is comprised of two key modules: SmartFuse and Annotate, allowing the user to display and visualize 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. Supported modalities cover static and gated CT (computerized tomography including CBCT and 4D-CT), PET (positron emission tomography) and MR (magnetic resonance).

Compared to ART-Plan v1.6.1 (primary predicate), the following additional features have been added to ART-Plan v1.10.0:

· an improved version of the existing automatic segmentation tool
· automatic segmentation on more anatomies and organ-at-risk
image registration on 4D-CT and CBCT images .
automatic segmentation on MR images .
· generate synthetic CT from MR images
a cloud-based deployment

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 adding/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 images.

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 and 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

AI/ML Overview

Here's a summary of the acceptance criteria and study details for the ART-Plan device, extracting information from the provided text:

Acceptance Criteria and Device Performance

Criterion Category	Acceptance Criteria	Reported Device Performance
Auto-segmentation - Dice Similarity Coefficient (DSC)	DSC (mean) ≥ 0.8 (AAPM standard) OR DSC (mean) ≥ 0.54 or DSC (mean) ≥ mean(DSC inter-expert) + 5% (inter-expert variability)	Multiple tests passed demonstrating acceptable contours, exceeding AAPM standards in some cases (e.g., Abdo MRI auto-segmentation), and meeting or exceeding inter-expert variability for others (e.g., Brain MR, Pelvis MRI). For Brain MRI, initially some organs did not meet 0.8 but eventually passed with further improvements and re-evaluation against inter-expert variability. All organs for all anatomies met at least one acceptance criterion.
Auto-segmentation - Qualitative Evaluation	Clinicians' qualitative evaluation of auto-segmentation is considered acceptable for clinical use without modifications (A) or with minor modifications/corrections (B), with A+B % ≥ 85%.	For all tested organs and anatomies, the qualitative evaluation resulted in A+B % ≥ 85%, indicating that clinicians found the contours acceptable for clinical use with minor or no modifications. For example, Pelvis Truefisp model achieved ≥ 85% A or B, and H&N Lymph nodes also met this.
Synthetic-CT Generation	A median 2%/2mm gamma passing criteria of ≥ 95% OR A median 3%/3mm gamma passing criteria of ≥ 99.0% OR A mean dose deviation (pseudo-CT compared to standard CT) of ≤ 2% in ≥ 88% of patients.	For both pelvis and brain synthetic-CT, the performance met these acceptance criteria and demonstrated non-inferiority to previously cleared devices.
Fusion Performance	Not explicitly stated with numerical thresholds, but evaluated qualitatively.	Both rigid and deformable fusion algorithms provided clinically acceptable results for major clinical use cases in radiotherapy workflows, receiving "Passed" in all relevant studies.

Study Details

Sample Size used for the test set and the data provenance:
- Test Set Sample Size: The exact number of patients in the test set is not explicitly given as a single number but is stated that for structures of a given anatomy and modality, two non-overlapping datasets were separated: test patients and train data. The number of test patients was "selected based on thorough literature review and statistical power."
- Data Provenance: Real-world retrospective data, initially used for treatment of cancer patients. Pseudo-anonymized by the centers providing data before transfer. Data was sourced from both non-US and US populations.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Varies. For some tests (e.g., Abdo MRI auto-segmentation, Brain MRI autosegmentation, Pelvis MRI auto-segmentation), at least 3 different experts were involved for inter-expert variability calculations. For the qualitative evaluations, it implies multiple clinicians or medical physicists.
- Qualifications of Experts: Clinical experts, medical physicists (for validation of usability and performance tests) with expertise level comparable to a junior US medical physicist and responsibilities in the radiotherapy clinical workflow.
Adjudication method for the test set:
- The document describes a "truthing process [that] 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 suggests a multi-reader approach, potentially with consensus or an adjudicator for ground truth, but a specific "2+1" or "3+1" method is not detailed. The "inter-expert variability" calculation implies direct comparison between multiple experts' delineations of the same cases.
If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- A direct MRMC comparative effectiveness study with human readers improving with AI vs without AI assistance is not explicitly described in the provided text. The studies focus on the standalone performance of the AI algorithm against established criteria (AAPM, inter-expert variability, qualitative acceptance) and non-inferiority to other cleared devices.
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance evaluation of the algorithm was done. The acceptance criteria and performance data are entirely based on the algorithm's output (e.g., DSC, gamma passing criteria, dose deviation) compared to ground truth or existing standards, and qualitative assessment by experts of the algorithm's generated contours.
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth used primarily involved:
  - Expert Consensus/Delineation: Contours created by different clinical experts and assessed for inter-variability.
  - Validated Ground Truth Contours: Contours provided by the centers and validated by a second expert from the same center.
  - Qualitative Evaluation: Clinical review and validation of contours.
  - Dosimetric Measures: For synthetic-CT; comparison to standard CT dose calculations.
The sample size for the training set:
- Training Patients: 8,736 patients.
- Training Samples (Images/Anatomies/Structures): 299,142 samples. (One patient can have multiple images, and each image multiple delineated structures).
How the ground truth for the training set was established:
- "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 indicates that the ground truth for the training set was established through a combination of expert delineation, internal validation by a second expert, adherence to established guidelines, and assessment of variability among experts.

Summary

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

Image /page/0/Picture/0 description: The image contains 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" followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in a stacked format.

TheraPanacea % Edwin Lindsay QA/RA consultant Pépinière Cochin Paris Santé, 29 rue du Faubourg Saint-Jacques Paris. 75014 FRANCE

Re: K220813

Trade/Device Name: ART-Plan Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management and Processing System Regulatory Class: Class II Product Code: QKB Dated: March 16, 2022 Received: March 21, 2022

Dear Edwin Lindsay:

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 (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 located 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.

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 803) for

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

devices or postmarketing safety reporting (21 CFR 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 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 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,

Julie Sullivan, Ph.D. Director 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

Enclosure

for

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

Indications for Use

510(k) Number (if known) K220813

Device Name ART-Plan

Indications for Use (Describe)

ART-Plan is indicated for cancer patients for whom radiation treatment has been planned. It is intended to be used by tramed medical professionals including, but not limited to, radiation oncologists, dosimetrists, and medical physicists.

ART-Plan supports Al-based contouring on CT and MR images and offers semi-automatic and manual tools for segmentation.

With ART-Plan, users are also able to generate, visualize, evaluate and modify pseudo-CT from MRI images.

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.

Submitter's Name:

TheraPanacea

Submitter's Address:

Pépinière Paris Santé Cochin 29 rue du Faubourg Saint-Jacques 75014 Paris France

Telephone: +33 9 62 52 78 19

Establishment Registration Number:

3019834893

Contact Person:

Edwin Lindsay

Telephone +44 (0) 7917134922

Date Prepared:

16 Mar 2022

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

Primary Product Code:

RegulationNumber	Device	DeviceClass	ProductCode	ClassificationPanel
892.2050	Medical imagemanagement andprocessing system	Class II	QKB	Radiology

Device Trade Name:

ART-Plan

Device Common Name:

ART-Plan

Intended Use:

Page 1 of 28

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

ART-Plan is a software for multi-modal visualization, contouring and processing of 3D images of cancer patients for whom radiotherapy treatment has been prescribed.

It allows the user to view, create and modify contours for the regions of interest. It also allows to generate automatically, and based on medical practices, the contours for the organs at risk and healthy lymph nodes and to register combinations of anatomical and functional images. Contours and images require verifications, potential modifications, and subsequently the validation of a trained user with professional qualifications in anatomy and radiotherapy before their export to a Treatment Planning System.

ART-Plan offers the following visualization, contouring and manipulation tools to aid in the preparation of radiotherapy treatment:

Multi-modal visualization and rigid- and deformable registration of anatomical and O functional images such as CT, MR, PET-CT, 4D-CT and CBCT
O Display of fused and non-fused images to facilitate the comparison and delineation of image data by the user
O Manual 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 0 on medical practices, on medical images such as CT and MR images.
Generation of pseudo-CT for supported anatomies 0

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

Indications for Use:

ART-Plan is indicated for cancer patients for whom radiation treatment has been planned. It is intended to be used by trained medical professionals including, but not limited to, radiologists, radiation oncologists, dosimetrists, and medical physicists.

ART-Plan supports Al-based contouring on CT and MR images and offers semi-automatic and manual tools for seqmentation.

With ART-Plan, users are also able to generate, visualize, evaluate and modify pseudo-CT from MRI images.

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

Summary of Substantial Equivalence:

The following predicate devices have been that the ART-Plan can claim equivalence with and these are detailed below

General Comparison

	General Information
Property	Proposed DeviceART-Plan v1.10.0	PrimaryPredicateART-Planv1.6.1	ReferencedeviceContourProtégéAl	ReferencedeviceMIM 4.1	ReferencedeviceMRCAT Pelvis	ReferencedeviceMRCAT Brain	ReferencedeviceSyngo.via RTImage Suite	Comment
CommonName	Radiological imageprocessing software forradiation therapy	Radiological imageprocessing softwarefor radiation therapy	RadiologicalImageProcessingSoftware ForRadiationTherapy	System, imageprocessing,radiological	System,Planning,RadiationTherapyTreatment	System,Planning,RadiationTherapyTreatment	System,Planning,RadiationTherapyTreatment	N/A
DeviceManufacturer	TheraPanacea	TheraPanacea	MIM Software,Inc	MIMvista Corp(now MIMSoftware Inc)	Philips MedicalSystems	Philips MedicalSystems	SiemensMedicalSolutions USA,Inc.	N/A
510k	N/A	K202700	K210632	K071964	K182888	K193109	K173635	N/A
DeviceClassification	II	II	II	II	II	II	II	N/A
PrimaryProduct Code	QKB	QKB	QKB	LLZ	MUJ	MUJ	MUJ	The primary product codeis QKB "RadiologicalImage ProcessingSoftware For RadiationTherapy" as the softwareuses Al algorithms and isintended for radiationtherapy, just like theprimary predicate device
SecondaryProduct Code	LLZ, MUJ	LLZ	-	-	-	-	LLZ	As secondary productcode:LLZ (System, ImageProcessing,Radiological) wasincluded as thesoftware is used in
								image processing andsome predicates use itas primary orsecondary productcode:MUJ (System,Planning, RadiationTherapy Treatment)was includes as it is asoftware used in theplanning ofradiotherapytreatment and some ofthe reference devicesuse it as their primarycode
TargetPopulation	Any patient type forwhom relevant modalityscan image data isavailable	Any patient type forwhom relevantmodality scan data isavailable	Not stated	Not stated	Any patient withsoft tissuecancers in thepelvic region forwhomradiotherapytreatment hasbeen planned	Any patient withprimary andmetastatic braintumor for whomradiotherapytreatment hasbeen planned	Not stated	The proposed device hasidentical targetpopulations to the primaryand reference devices.
Environment	Hospital	Hospital	Hospital	Hospital	Hospital	Hospital	Hospital	The proposed deviceand predicates haveidentical targetenvironments
Intended Use/Indication forUse	Intended UseART-Plan is a softwarefor multi-modalvisualization, contouringand processing of 3Dimages of cancerpatients for whomradiotherapy treatmenthas been prescribed.It allows the user toview, create and modifycontours for the regionsof interest. It also allowsto generateautomatically, andbased on medical	Intended UseART-Plan is asoftware designed toassist the contouringprocess of the targetanatomical regionson 3D-images ofcancer patients forwhom radiotherapytreatment has beenplanned.The SmartFusemodule allows theuser to registercombinations ofanatomical and	Intended UseContourProtégéAl is anaccessory toMIM softwareused for thecontouring ofanatomicalstructures inimaging datausingmachine-learning-basedalgorithmsautomatically.Appropriate	Intended UseMIM 4.1(SEASTAR)software isintended fortrained medicalprofessionalsincluding, but notlimited to,radiologists,oncologists,physicians,medicaltechnologists,dosimetrists andphysicists.	Intended Use:MRCAT imagingisintended toprovide theoperator withinformation oftissuepropertiesfor radiationattenuationestimationpurposesin photonexternal beamradiotherapy	Intended Use:MRCAT imagingis intended toprovide theoperator withinformation oftissueproperties forradiationattenuationestimationpurposes inphoton externalbeamradiotherapy	Intended use:Not available inthe summaryIndication foruse:syngo.via RTImage Suite is a3D and 4Dimagevisualization,multimodalitymanipulationandcontouring toolthat helps the	The intended use andindications for use ofthe proposed device,ART-Plan v1.10.0 andthe primary predicateART-Plan v1.6.1 aresimilar as they areboth intended formedical imageregistration andsegmentation in thecontext of radiotherapytreatment planning:they allow multi-modaland mono-modal rigid
practices, the contours	functional images and	image	MIM 4.1(SEASTAR) is amedical imageand informationmanagementsystem that isintended toreceive, transmit,store, retrieve,display, print andprocess digitalmedical images,as well as create,display and printreports from thoseimages. Themedicalmodalities ofthese medicalimaging systemsinclude, but arenot limited to, CT,MRI, CR, DX,MG, US, SPECT,PET and XA assupported byACR/NEMADICOM 3.0.	treatmentplanning.	treatmentplanning.	preparation andresponseassessment oftreatments suchas, but notlimited to thoseperformed withradiation (forexample,Brachytherapy,ParticleTherapy,ExternalBeam RadiationTherapy).It provides toolsto efficientlyview existingcontours,create, edit,modify, copycontours ofregions ofthe body, suchas but notlimited to, skinoutline, targetsandorgans-at-risk. Italso providesfunctionalities tocreate andmodify simpletreatment plans.Contours,images andtreatment planscansubsequently beexported to aTreatmentPlanningSystem.The softwarecombinesfollowing digital	deformable registrationfor the same modalitiesof images (CT, MR, PETthey allow automaticsegmentation oforgans-at-risk and lymphnodes on injected andnon-injected CT imagesusing deep learningalgorithmsthey allow the import,manipulation,visualisation, generationand the export of DICOMimagesThe intended for theproposed device hasbeen adapted toprovide a more specificdescription of theproposed device butdoes not represent anew intended use,except for theadditional claims forthe proposed deviceas compared to theprimary predicate as:- it includes an improvedversion of the existingautomatic segmentationtool as compared to theone of ART-Plan v1.6.1.- it allows automaticsegmentation on moreanatomies andorgan-at-risk
for the organs at risk	display them with	visualizationsoftware mustbe used toreview and, ifnecessary, editresultsautomaticallygenerated byContourProtégéAI.ContourProtégéAI is notintended todetect orcontour lesions.	MIM 4.1(SEASTAR) provides the userwith the means todisplay, registerand fuse medicalimages frommultiplemodalities.Additionally, itevaluates cardiacleft ventricularfunction andperfusion,including leftventricular	Indications forUse:	Indications foruse:
and healthy lymph	fused and non-fused
nodes and to register	displays to facilitate
combinations of	the comparison and
anatomical and	delineation of image
functional images.	data by the user.			MRCAT Pelvisis indicated forradiotherapytreatmentplanning of softtissue cancersin the pelvicregion.	MRCAT isindicated forradiotherapytreatmentplanning forprimary andmetastatic braintumor patients
Contours and images	The images created
require verifications,	with rigid or elastic
potential modifications,	registration require
and subsequently the	verifications, potential
validation of a trained	modifications, and
user with professional	then the validation of
qualifications in	a trained user with
anatomy and	professional
radiotherapy before	qualifications in
their export to a	anatomy and
Treatment Planning	radiotherapy.	Indications forUse
System.	With the Annotate	Trained medical
	module, users can	professionals
ART-Plan offers the	edit manually and	use Contour
following visualization,	semi-automatically	ProtégéAI as a
contouring and	the contours for the	tool to assist in
manipulation tools to	regions of interest. It	the automated
aid in the preparation of	also allows to	processing of
radiotherapy treatment:	generate	digital medical
	automatically, and	images of
- Multi-modal	based on medical	modalities CT
visualization and rigid-	practices, the	and MR, as
and deformable	contours for the	supported by
reqistration of	organs at risk and	ACR/NEMA
anatomical and	healthy lymph nodes	DICOM 3.0. In
functional images such	on CT images.	addition.
as CT, MR, PET-CT,	The contours created	Contour
4D-CT and CBCT	automatically.	ProtégéAI
- Display of fused and	semi-automatically or	supports the
non-fused imaqes to	manually require	following
facilitate the	verifications, potential	indications: •
	modifications, and	Creation of
comparison and	then the validation of	contours using
delineation of image	a trained user with	machine-learnin
data by the user	professional	g algorithms for
- Manual modification	qualifications in	applications
and semi-automatic	anatomy and	including, but
generation of contours	radiotherapy.	not limited to,
		ventricular

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

Page 4 of 28

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

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

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 pseudo-CT for supported anatomies	The device is intended to be used in a clinical setting, by trained professionals only.Indications for UseART-Plan is intended to be used by trained medical professionals including, but not limited to, radiologists, radiation oncologists, dosimetrists and physicists.ART-Plan is a software application intended to display and visualize 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. Supported modalities include static and gated CT, PET, and MR.ART-Plan allows the user to register combinations of anatomical and functional images and display them with fused and non-fused displays to facilitate the comparison of image data by the user. PET images should not be	quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems, and archiving contours for patient follow-up and management. • Segmenting normal structures across a variety of CT anatomical locations. • And segmenting normal structures of the prostate, seminal vesicles, and urethra within T2-weighted MR images. Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAI.	end-diastolic volume, end-systolic volume, and ejection fraction. The_Region of Interest (ROI) feature reduces the time necessary for the user to define objects in medical image volumes by providing an initial definition of object contours. The objects include, but are not limited to, tumors and normal tissues.MIM 4.1 (SEASTAR) provides tools to quickly create, transform, and modify contours for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation therapy treatment planning systems and archiving contours for patient follow-up and managementMIM 4.1 (SEASTAR) also	image processing and visualization tools:x Multi-modality viewing and contouring of anatomical, functional, and multi-parametric images such as but not limited to CT, PET, PET/CT, MRI, Linac Cone Beam CT (CBCT) images and dose distributionsx Multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP), volume rendering technique (VRT)x Freehand and semi-automatic contouring of regions-of-interest on any orientation including obliquex Creation of contours on any type of images without prior assignment of a planning CTx Manual and semi-automatic	- it allows automatic segmentation on MR images which is not possible with ART-Plan v1.6.1 but covered by reference devices (MIM 4.1. and Contour ProtégéAl)- it can generate synthetic CT from MR images which is not possible with ART-Plan v1.6.1 but covered by reference devices (MRCATpelvis, MRCAT brain and Syngo.via RT Image Suite- it allows a cloud-based deployment which is not possible with ART-Plan v1.6.1 but covered by Contour ProtégéAl and Syngo.via RT Image Suite

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

interest structures).	registered directly but	aids in the	registration
These images, contoursand objects cansubsequently beexported/distributedwithin the system,across computernetworks and/or toradiation treatmentplanning systems.Supported modalitiesinclude CT, PET-CT,CBCT, 4D-CT and MRimages.	via the registration ofthe CT of the PETtoward the targetimage. The result ofthe registrationoperation can assistthe user in assessingchanges in imagedata, either within orbetweenexaminations andaims to help the userobtain a betterunderstanding of thecombined informationthat would otherwisehave to be visuallycompareddisjointedly.	assessment ofPET/SPECT brainscans. It providesautomatedquantitative andstatistical analysisby automaticallyregisteringPET/SPECT brainscans to astandard templateand comparingintensity values toa referencedatabase or toother PET/SPECTscans on a voxelby voxel basis,within stereotacticsurfaceprojections orstandardizedregions ofinterest.	using rigid anddeformableregistrationx Supports theuser incomparing,contouring, andadaptingcontours basedon datasetsacquiredwith differentimagingmodalities andat different timepointsx Supports theuser incomparingimages andcontours ofdifferentpatientsx Supportsmulti-modalityimage fusionx Visualizationand contouringof movingtumors andorgansx Managementof points ofinterestincluding but notlimited to theisocenterx Managementof simpletreatment plansx Generation ofa synthetic CTbased onmultiple
ART-Plan supportsAl-based contouring onCT and MR images andoffers semi-automaticand manual tools forsegmentation.To help the user assesschanges in image dataand to obtain combinedmulti-modal imageinformation, ART-Planallows the registrationof anatomical andfunctional images anddisplay of fused andnon-fused images tofacilitate thecomparison of patientimage data by the user.With ART-Plan, usersare also able togenerate, visualize,evaluate and modifypseudo-CT from MRIimages.	ART-Plan provides anumber of tools suchas regions ofinterests, which areintended to be usedfor the assessment ofregions of an imageto support a clinicalworkflow. Examplesof such workflowsinclude, but are notlimited to, thedelineation ofanatomical regions ofinterest on3D-images of cancerpatients for whomradiotherapytreatment has beenplanned.ART-Plan supportsthe loading andsaving of DICOM RTobjects and allowsthe user to define,import, display	Indications forUseMIM 4.1(SEASTAR)software is usedby trained medicalprofessionals as atool to aid inevaluation andinformationmanagement ofdigital medicalimages. Themedical imagemodalitiesinclude, but arenot limited to, CT,MRI, CR, DX,MG
	transform, store andexport such objectsincluding regions ofinterest structures toradiation therapyplanning systems.ART-Plan allows theuser to transformregions of interestassociated with aparticular imagingdataset to another,supporting Al-basedcontouring on CTimages along withsemi-automatic andmanual tools forsegmentation.	US, SPECT, PETand XA assupported byACR/NEMADICOM 3.0. MIM4.1(SEASTAR)assists in thefollowingindications:* Receive,transmit, store,retrieve, display,print, and processmedical imagesand DICOMobjects.* Create, displayand print reportsfrom medicalimages.* Registration,fusion display,and review ofmedical imagesfor diagnosis,treatmentevaluation, andtreatmentplanning.* Evaluation ofcardiac leftventricularfunction andperfusion,including leftventricularend-diastolicvolume,end-systolicvolume, andejection fraction.* Localization anddefinition ofobjects such as	pre-define MRacquisitions

		tumors and
		normal tissues in
		medical images.
		* Creation,

		transformation,
		and modification
		of contours for
		applications
		including, but not
		limited to,

		quantitative
		analysis, aiding
		adaptive therapy,
		transferring
		contours to
		radiation therapy

		treatment
		planning systems,
		and
		archiving contours
		for patient
		follow-up and
		management.
		* Quantitative and

		statistical analysis
		of PET/SPECT
		brain scans by
		comparing to
		other registered
		PET/SPECT brain
		scans


		Lossy
		compressed
		mammographic
		images and
		digitized film
		screen images
		must not be

		reviewed for
		primary image
		interpretations.
		lmages that are
		printed to film
		must be printed
		using a

		FDA-approvedprinter for thediagnosis ofdigitalmammographyimages.Mammographicimages must beviewed on adisplaysystem that hasbeen cleared bythe FDA for thediagnosis ofdigitalmammographyimages. Thesoftware is not tobe used formammographyCAD

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

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

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

System Information Comparison

	System Information
Property	ProposedDeviceART-Planv1.10.0	PrimaryPredicateART-Planv1.6.1	ReferencedeviceContourProtégéAl	ReferencedeviceMIM 4.1	ReferencedeviceMRCAT Pelvis	ReferencedeviceMRCAT Brain	ReferencedeviceSyngo.via RTImage Suite	Comment
Method ofUse	Standalonesoftwareapplicationaccessed viaa compliantbrowser(Chrome orMozillaFirefox) on apersonalcomputer,tablet or	Standalonesoftwareapplicationaccessed viaa compliantbrowser(Chrome orMozillaFirefox) on apersonalcomputer,tablet or	Standalonesoftwareapplication	Standalonesoftwarepackage	Provided as aplug-in clinicalapplication toIngenia MR-RT. Itis compatible withIngenia 1.5T and3.0T MR-RT,Ingenia Ambition1.5T MR-RT andIngenia Elition3.0T MR-RT. It runsparallel to image	Provided as aplug-in clinicalapplication toIngenia MR-RT. Itis compatible withIngenia 1.5T and3.0T MR-RT,Ingenia Ambition1.5T MR-RT andIngenia Elition3.0T MR-RT. Itruns parallel to	syngo.via can beused as astandalone deviceor together with avariety ofsyngo.via-basedsoftware options,which are medicaldevices in theirown right.	The proposed device andpredicates (especially theprimary predicate) haveidentical methods of use
	phone (Incase ofconnection tothe platformwith a screenof a phone ora tablet, theuser mustchoose theoption for thedesktop site ofhiscommunication device. Theplatform isoptimally usedwith 17 inchesand upscreen.Facilitatesdisplay andvisualizationof data byuser.	phone (Incase ofconnection tothe platformwith a screenof a phone ora tablet, theuser mustchoose theoption for thedesktop siteof hiscommunication device. Theplatform isoptimally usedwith 17 inchesand upscreen.Facilitatesdisplay andvisualization ofdata by user.			acquisition on theMR console,embeddedpost-processinggenerates MRCATimages using: •Automatedsegmentation andtissueclassification •Automatedassignment ofCT-based densityvalues	image acquisitionon the MRconsole,embeddedpost-processinggenerates MRCATimages using: •Automatedsegmentation andtissueclassification •Automatedassignment ofCT-based densityvalues
ComputerPlatform andOperatingSystem	Full webplatformLaunch fromGoogleChrome orMozilla FirefoxAvailable onserver-basedapplication orCloud-baseddeployment	Full webplatformLaunch fromGoogleChrome orMozilla Firefox	Server-basedapplicationsupportingLinux-based OS- and -Localdeployment onWindows or MacCloud-baseddeployment	Windows2000/XP	As the densityinformation isgenerated directlyon the MRconsole, theresulting data isavailable at theconsole forimmediate review.	As the densityinformation isgenerated directlyon the MRconsole, theresulting data isavailable at theconsole forimmediate review.	This solution isalso availablecloud-based,providingscalability withflexible usemodels and clouddeployment1	The proposed device andpredicates are compatible withidentical operating systems.
DataVisualization/ GraphicalInterface	Yes	Yes	Yes	Yes	Yes	Yes	Yes	The proposed device and allthe predicates have a datavisualisation and graphicalinterface
Synthetic CT	Generation ofCT density	N/A	N/A	N/A	Generation of CTdensity image	Generation of CTdensity image	Generation of CT-	The proposed device andreference devices such as
SupportedModalities	image seriesout of multipleMR-imageseries	Registration:Static andgated CT, MR,PET (via theregistration ofthe CT of saidPET), 4D-CTand CBCT.Segmentation:CT (injectedor not),MR images,DICOMRTSTRUCT	Registration:Static andgated CT, MR,PET (via theregistration ofthe CT of saidPET)Segmentation:CT (injected ornot), DICOMRTSTRUCT	CT and MR	Medical imagemodalitiesinclude, but arenot limited to,CT, MRI, CR,DX, MG, US,SPECT, PET andXA as supportedby ACR/NEMADICOM 3.0.	series out ofmultiple MR-imageseries	series out ofmultiple MR-imageseries	density imageseries out ofmultiple MR-imageseries	MRCAT pelvis, MRCAT brainand Syngo.via RT Image Suitehave the same feature
						MR images	MR images	3D: CT, PET1,PET/CT1, MRI1,4D-CT and LinacCone Beam CT(CBCT) imagesupportSupport for timeresolved CT andMR1 images (e.g.MR DCE,Perfusion CT)	The proposed device iscompatible with the samemodalities as the primarypredicate on the registrationfeature, which are CT, MR andPET images in a DICOMformat. However, the proposeddevice supports 2 additionalmodalities:- CBCT (covered bythe reference deviceSyngo.via RT ImageSuite)- 4D-CT (covered bythe reference deviceSyngo.via RT ImageSuiteFor both devices, supportedimages can be fixed (static) ormoving (gated).The proposed device and theprimary predicate are bothcompatible with CT images(injected or not), DICOM andRTSTRUCT on thesegmentation feature.For MR images, the proposeddevice and some referencedevices (such as MRCATpelvis and MRCAT brain) areboth compatible with MRimages on the segmentationfeature.

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

1 Information obtained from their brochure.https://cont.com/39b415b7b6de2d907/a4c5e63e0880cd1/2053f68eadshs-syngo-via-timage-suite-brochure-2021.ptf

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

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

								Compared to referencedevices, the proposed deviceclaims less supportedmodalities
Data Export	Distribution ofDICOMcompliantImages intoother DICOMcompliantsystems.	Distribution ofDICOMcompliantImages intoother DICOMcompliantsystems.	As supported byACR/NEMADICOM 3.0.	The system hasthe ability tosend data toDICOM-readydevices forimage storage,retrieval andtransmission.	MRCAT imagescan be exported inDICOM formatenabling the useas primary imagesin the treatmentplanning systems	MRCAT imagescan be exported inDICOM formatenabling the useas primary imagesin the treatmentplanning systems	DICOM, HL7 andIHE-RO standardcompliance	The proposed device andpredicates (especially theprimary one) have identicaldata export capabilities withDICOM format.
Compatibility	Compatiblewith data fromany DICOMcompliantscanners forthe applicablemodalities.	Compatiblewith data fromany DICOMcompliantscanners forthe applicablemodalities.	supported byACR/NEMADICOM 3.0	The software canreceive, transmit,store, retrieve,display, print,and processDICOM objectsand medicalimage modalitiesincluding, but notlimited to, CT,MRI, CR, DX,MG, US, SPECT,PET and XA assupported byACR/NEMADICOM 3.0.	MR console:Compatible withIngenia 1.5T and3.0T MR-RT,Ingenia Ambition1.5T MR-RT andIngenia Elition3.0T MR-RTAfter export,compatible withany DICOMcompliantscanners.	MR console:Compatible withIngenia 1.5T and3.0T MR-RT,Ingenia Ambition1.5T MR-RT andIngenia Elition3.0T MR-RTAfter export,compatible withany DICOMcompliantscanners.	Compatible withDICOMAutomatic send toTPS configuration	The proposed device andpredicates (especially theprimary one) have identicalcompatibility (DICOM format)

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

Technical Information Comparison

		Technical Information
Property	ProposedDeviceART-Planv1.10.0	PrimaryPredicateART-Planv1.6.1	ReferencedeviceContourProtégéAl	ReferencedeviceMIM 4.1	ReferencedeviceMRCAT Pelvis	ReferencedeviceMRCAT Brain	ReferencedeviceSyngo.via RTImage Suite	Comment
DelineationMethod	Al	Al	Al	Atlas	N/A	N/A	Deep learningautocontouringfor organs at risk(incl. lymphnodes)2	The proposed device,primary predicate andmost of the referencedevices share an Aldelineation method.
Imageregistration	Multi-modalandmono-modal.Rigid anddeformableAutomatic andmanualinitialization(landmarks,fusion box,alignment).Registration forthe purposesof replanning/recontouringand Al-basedautomaticcontouring.	Multi-modal andmono-modal.Rigid anddeformableAutomatic andmanualinitialization(landmarks,fusion box,alignment).Registration forthe purposes ofreplanning/recontouringand Al-basedautomaticcontouring.	N/A	Registration, fusiondisplay, and reviewof medical imagesfor diagnosis,treatmentevaluation, andtreatment planning.	N/A	N/A	Image FusionRigid andDeformableRegistration withregion-of interestbasedregistration andmultipleregistrations perimage pairManual editingof registrationsSaveregistrations andsave deformedimages asreformatteddataset2Contour warpingand display ofprior and newstructure setRegistrationQuality Checkwith spyglass,deformationvector map	Both the predicate deviceand ART-Plan offermono-modal (CT-CT) andmulti-modal (CT/MR,CT/PET) rigid anddeformable registration.However, the proposeddevice supports 2additional modalities:- CBCT (coveredby the referencedeviceSyngo.viaRT Image Suite)- 4D-CT (coveredby the referencedeviceSyngo.viaRT Image SuiteBoth devices offer anautomatic solution forregistration andsemi-automatic registrationby including manualinitialization tools inaddition to automaticinitialization.
SegmentationFeatures	AutomaticallydelineatesOARs andhealthy lymphnodesDeep learningalgorithm.Automaticsegmentationincludes thefollowinglocalizations:* head andneck (on CTimages)* thorax/breast(formale/femaleand on CTimages)* abdomen (onCT images andMR images)* pelvismale(on CTimages andMR images)* pelvis female(on CTimages)* brain (on CTimages andMR images)	AutomaticallydelineatesOARs andhealthy lymphnodes (on anyCT images)Deep learningalgorithm.Automaticsegmentationincludes thefollowinglocalizations:* head andneck* thorax/breast(formale/female)* abdomen* pelvis (formale only)* brain.	Creation ofcontours usingmachine-learningalgorithms forapplicationsincluding, but notlimited to,quantitativeanalysis, aidingadaptive therapy,transferringcontours toradiation therapytreatment planningsystems, andarchiving contoursfor patient follow-upand management.Segmentinganatomicalstructures across avariety of CTanatomicallocations.And segmentingnormal structuresof the prostate,seminal vesicles,and urethra withinT2-weighted MRimages.	The softwareautomaticallygenerates contoursusing a deformableregistrationtechnique whichregisterspre-contouredpatients to targetpatients.Registrations areeitherbetween a serialpair of intra-patientvolumes orbetween apre-existing atlas ofcontoured patientsand a patientvolume. Thisprocess facilitatescontour creation orre-contouring foradaptive therapy.	N/A	N/A	magnitude colormap	Reference device such asSyngo.via RT Image Suiteoffers the same options asthe proposed device: rigidand deformableregistration.
							MultimodalitycontouringFreehand 2D,3D image-basedSmart Freehandsegmentation, sContour on anyarbitrary planeincluding obliqueplanesdeep learningautocontouringfor organs at risk(inclusive LNs)One-clickadaptivecontouringUserconfigurableOrganTemplatesMultiplestructure setsupport (1 perimage series)Molecularimaging datasuch as PET,threshold-basedand skin, grayvalue-basedsegmentation1"CT-free"contouring:native PET orMR contouring	The proposed device andprimary predicate arecapable of automaticallycontouring theorgan-at-risk (OAR) andhealthy lymph nodes usingAl (deep learning)algorithm.There is a difference inintended anatomies for CTimages as the proposeddevice also includes pelvisfemale.For MR images, allanatomies included in theproposed device are alsoincluded in the primarypredicate.

² https://www.siemens-healthineers.com/radiotherapy/software-solutions/syngovia-rt-image-suite (last checked on Feb, 15th 2022)

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

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

							Parallelcontouring:contouringperformed onany image isreflected on allother imagesVisualization ofpreviously drawnstructures on thecurrent imageseriesContour copyand warpingbetween imageseries2
ViewManipulationandVolumeRendering	Window andlevel, pan,zoom,cross-hairs,slicenavigation.Maximum,average andminimumintensityprojection(MIP, AVG,MinIP),colorrendering,multi-planarreconstruction(MPR), fusedviews,gallery views.	Window andlevel, pan,zoom,cross-hairs,slicenavigation.Maximum,average andminimumintensityprojection (MIP,AVG, MinIP),color rendering,multi-planarreconstruction(MPR), fusedviews,gallery views.	Not stated	Not stated	N/A	N/A	Organ algebra(union,intersection,exclusion)Symmetric andasymmetricstructure growthor contractionSmart 2D/3DNudge, brushPan, scale,rotate contourGeometrical andsmartimage-basedcontourinterpolationMulti-modalityImageManipulationMultiplanarreconstruction(MPR) thin/thick,minimumintensityprojection (MIP),volume	The proposed device hasthe same tools as theprimary predicate.
							renderingtechnique(VRT)2
Regions andVolumesof Interest(ROI)	AI Basedautocontouring,Registrationbased contourprojection(re-contouring),Manual ROImanipulationandtransformation(margins,booleansoperators,interpolation).	AI Basedautocontouring,Registrationbased contourprojection(re-contouring),Manual ROImanipulationandtransformation(margins,booleansoperators,interpolation).	AI Basedcontouring, tools toquickly create,transform, andmodify contours.	Atlas basedcontouring, tools toquickly create,transform, andmodify contours.	N/A	N/A	syngo.via RTImage Suiteprovidesdedicated tools,which help themedicalprofessional incontouringand evaluatingvolumes ofinterest.Freehand andsemi-automaticcontouring ofregions-of-interest on anyorientationincludingoblique2	Both the proposed deviceand the primary predicateallow AI automaticcontouring and manualcontouring
Region/volume ofinterestmeasurements andsizemeasurements	Intensity,Hounsfieldunits and SUVmeasurementsSizemeasurementsinclude 2D and3Dmeasurements(number ofslices, volumeof a structure,static ruler)	Intensity,Hounsfield unitsand SUVmeasurementsSizemeasurementsinclude 2D and3Dmeasurements(number ofslices, volumeof a structure,static ruler)	N/A	Quantitativeanalysis tools.	N/A	N/A	N/A	The proposed deviceoffers the same kind ofregion/volume of interestmeasurements and sizemeasurements as theprimary predicate

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

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

Device Description:

Compared to ART-Plan v1.6.1 (primary predicate), the following additional features have been added to ART-Plan v1.10.0:

· an improved version of the existing automatic segmentation tool
· automatic segmentation on more anatomies and organ-at-risk
image registration on 4D-CT and CBCT images .
automatic segmentation on MR images .
· generate synthetic CT from MR images
a cloud-based deployment

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 adding/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 images.

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 and 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

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

Information about your training dataset:

Summary test statistics or other test results including acceptance criteria or ● other information supporting the appropriateness of the characterised 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. Or
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 synthetic-CT generation tool, the acceptance criteria are as follows:

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

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

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

	Sample Size	%
Training	299142	0.8
Validation	75018	0.2
Total	374160	1

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

The total number of patients used for training (8736) is lower than the number of samples (374160). 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.

Demographic distribution including gender, age and ethnicity ●

All data used for training of the models have been pseudo-anonymised by the centers providing data before transfer. Around 80% 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 vears old. Our data has a slight overrepresentation (8% points) for the ages between 54 and 60 years old, at the cost of a slight underrepresentation of patients in the age range between 20-34 (1.5% points) and above 85 (6.5% 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 63 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.

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 are male patients

No pseudo-anonymized data included any information on the ethnicity.

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

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

On the "truthing" and data collection process .

The contouring quidelines 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 following international guidelines.

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.

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.

Reqarding 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 quidelines 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

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

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

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.

Non-Clinical Tests (Performance/Physical Data):

The ART-Plan was evaluated for its safety and effectiveness based on the following testing:

Test Name	Test Description/Results	Results
Usability Report(V1.10.0)	This document is intended to document theusability test results for the ART-Plan v1.10.0 forcompliance with IEC 62366-1:2015+AMD1:2020 -Medical devices - Application of usabilityengineering to medical devices.	Passed
Usability file - ART-USR-09(V1.10.0)	The ART-Plan was assessed with regards tousability for compliance with each section of IEC62366	Passed
Usability - Testers qualification(V1.10.0)	This table shows that European medical physicistswho have participated in the evaluation have atleast an equivalent expertise level compared to ajunior US medical physicist (MP), andresponsibilities in the radiotherapy clinical workfloware equivalent	N/A
Literature Review andPerformance CriteriaExtraction Report for ART-Plan(V1.9.0 and V1.10.0)	A literature review is performed to establishacceptance criteria for performance of ART-Planmodules using performance ranges observed frombenchmark devices and alternative technologies inthe literature. All measures of performance thatwere established in this document were supportedby clinical evidence. It was also demonstrated,from the clinical data, that ART-Plan has a clear	N/A
	clinical relevance in accordance with the clinicalstate of the art.
ART-Plan performance testing- Overview(V1.6.1-V1.10.0)	The document summarises all performance teststhat have been performed since the last FDAcleared version (1.6.1). It also shows which criteriahave been met in each test for all modules ofART-Plan. It demonstrates that all modules ofART-Plan pass at least one performanceacceptance criterion and hence are clinicallyacceptable for release.	Passed
Study Protocol and ReportAnnotate PerformancesSummary (V1.9.0)	The testing demonstrated that Annotate providesacceptable contours for the concerned structureson an image of a patient.	Passed
Abdo MRI auto-segmentationperformances according toAAPM requirements (V1.8.0)	Mean DSC of each organ was compared with thetolerance threshold of 0.8. After comparing thecontours of 3 different experts on the same patientthe mean DSC was calculated, compared with theauto-segmentation and was observed to be inevery case superior. It is concluded that theauto-segmentation algorithm provides clinicalacceptable contours.	Passed
Testing protocol/report - BrainMRI autosegmentationperformances according toAAPM requirements	In this test, some organs did not meet theacceptance criteria. However, the value of 0.80 isindicated by the AAPM as the "uncertainty ofcontouring of the structure" which in fact can besignificantly below 0.80 depending on the organ.Thus, we also decided to evaluate in parallel themodels with a qualitative evaluation of ourpredictions (see additional qualitative test below).	Passed
Qualitative validation ofautoseqmentationperformances - Brain (V1.8.0)	All organs except left and right cochlea passed atleast one of the acceptance criteria demonstratingthat the Annotate module provides acceptablecontours on MR brain structures. The MR brainmodel has been further improved, subjected tofurther testing, and, after providing acceptablecontours for all structures (incl. the cochlea),released in v1.10.0. (see Study Protocol andReport- Autosegmentation performances againstinter-expert variability - Brain MR (V1.10.0)).	Passed
Qualitative validation ofauto-segmentationperformances - Gyneco(V1.8.0)	The testing demonstrates that Annotate providesacceptable contours for a specific list ofgynecological structures on a Female pelvis CTimage. Three testing methods are used: DICEcalculation Inter-expert DICE calculationcalculation,and	Passed
	qualitative Indicator. All structures passed at least one of the acceptance criteria and were released.
Pelvis MRI auto-segmentation tool performances according to AAPM requirements (V1.8.0)	The testing demonstrates that the auto-segmentation algorithm for Pelvis MRIs provides acceptable contours for the concerned structures on an image of a patient. All organs met at least one of the acceptance criteria and therefore were considered acceptable.	Passed
Qualitative & Quantitative validation of fusion performances (V1.9.0)	The study was developed to cover the major clinical use cases in which fusions are used in the radiotherapy workflow and split into as many sub-studies as clinical use cases of fusion in radiotherapy workflow. 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.	Passed
Study Protocol and Report for qualitative validation of fusion performances for tCT_SCT_injected/PET modality (V1.9.0)	The study evaluated the quality of the rigid and the deformable fusion algorithms of the SmartFuse module for the following cases:- CT injected image fuse towards CT image- CT-PET image fuse towards CT image.Both types of fusion algorithms, rigid and deformable, provided clinically acceptable results for the desired clinical uses.	Passed
Study Protocol & Report for qualitative validation of ITV calculation performances for 4D_CT modality (V1.9.0)	The testing evaluated the quality of ITV calculation algorithm of the Annotate module in the case of 4D-CT examinations. Acceptable results were reached for the evaluation of contours propagation.	Passed
Study Protocol and Report for validation of fusion performances for tCT_SMR modality (V1.9.0)	This testing evaluated the performances of the SmartFuse module for the clinical case of fusion of an MRI towards a planning CT to aid in the delineation. Acceptable results were reached for this evaluation.	Passed
Study Protocol and Report for qualitative validation of fusion performances for tMR_SCT modality (V1.9.0)	This study evaluated the performances of the SmartFuse module for fusion of CTs towards planning MRIs for the purpose of electron density transfer. Acceptable results were reached for this evaluation.	Passed
Study Protocol and Report for qualitative & quantitative validation of fusion performances for tMR_SMR modality (V1.9.0)	This study evaluated the performances of the SmartFuse module on the clinical case of using fusion for MRI replannification. Favorable results to the established performance criteria for rigid and deformable registrations, and for all organs, were obtained.	Passed
Protocol for qualitative & quantitative validation of fusion performances for tCT_SCT_replanning modality (V1.9.0)	This study evaluated the quality of the rigid and the deformable fusion algorithms of the SmartFuse module for replanification of CT-based treatments. Acceptable results were reached for this evaluation.	Passed
Pilot study for sample sizeestimation - literature review(V1.9.0)	The literature review was performed to estimate theappropriate sample size of the testing data settowards demonstrating the performance of theimage registration, segmentation and pseudo-CTgeneration solutions on the basis of the mostrecent and most relevant scientific literature.	N/A
Autoseg 2D regression test forintegration in ART-Plan V1.9.0	The objective of the test was to demonstrateequivalence between the version (V1.9.0) andprevious versions of Annotate (V.1.8 and v1.6.1).All organs passed at least one of the definedcriteria, and hence were accepted for release inv1.9. Given that equivalence TheraPanaceaconsiders all tests (especially the qualitative ones)performed on previous versions of the software tobe still relevant.	Passed
Study Protocol & Report(SPR): External contournon-regression protocol forintegration in ART-PlanV1.10.0	This test demonstrates equivalence between theversion V.1.10 and V.1.9 of the external contoursand show that the new added anatomies in themodule Annotate provides clinically acceptablecontours. The external contour for all anatomiespassed the defined criteria, and hence wereaccepted for release in the v1.10.	Passed
Testing Protocol/Report -Autoseg CT, MRnon-regression test forintegration in ART-PlanV1.10.0	This test demonstrates equivalence between theversion v.1.10 and v.1.9 of the auto-segmentationmodels for all structures and shows that theupdated models provide clinically acceptablecontours. All organs passed the defined criteria,and were hence accepted for release in the v1.10.	Passed
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan V1.10.0for Thorax	This test demonstrates that Annotate providesacceptable contours for structures of the thoraxregion: thoracic aorta and bronchial trees. Thisqualitative test was performed as an addition toSection 18.21 to ensure the contours are clinicallyacceptable.	Passed
Study Protocol and Report-Autosegmentationperformances againstinter-expert variability - BrainMR (V1.10.0)	This test demonstrates that the Annotate providesclinically acceptable (compared to inter-expertvariability) for all MR-T1 Brain structures. Existingstructures present in the previous version (v.1.8 -see Section 18.8) were also re-evaluated since acomplete retraining of the model was done.	Passed
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan V1.10.0for Pelvis Truefisp model	This test demonstrates that the module Annotateacceptable contours for 9 organsprovidesevaluated on MR Truefisp images of patients. Allorgans have passed the acceptance criterion ofreaching a percentage of at least 85% of A or B(qualitative evaluation) and hence can be releasedin v.1.10.0.	Passed
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan V1.10.0for H&N Lymph nodes	This test demonstrates that Annotate providesacceptable contours for following cervical lymphnodes levels: la, lb right, VIIa left, VIIb right, II left,III right, V left, IVb right, IVb left. All cervical lymphnodes having reached a percentage of at least	Passed
	85% of A or B, the performance of auto segmentation is demonstrated, and hence all structures were included in V1.10.
Study Protocol and ReportQualitative Validation ofAnnotate in ART-Plan V1.10.0	This test demonstrates that Annotate provides clinically acceptable contours, following qualitative measures, for the new version v.1.10. It serves as an additional evaluation to Section 18.21, and was done on a set of organs of all anatomies for both the CT and MR models. The benchmarking was done not only against the qualitative evaluation but also against the manual contours and a previously validated version of the models. All contours can be considered as acceptable as at least one criterion was met for each of the included structures.	Passed
Study Protocol and ReportAnnotate PerformancesSummary (V1.10.0)	The purpose of this document is to describe all the testing protocols and testing results for validating the performance of the Annotate module.Since all organs added in v.1.10.0 of Annotate have passed at least one test and met at least one acceptance criteria, all organs have been released.	Passed
Testing: pseudo-CT clinicalperformance and comparisonto predicates (pelvis)(V1.10.0)	The evaluation demonstrated the non-inferiority of using Annotate's pseudo-CT for treatment planning in terms of dosimetric measures as compared to CT-based treatment planning. Our pseudo-CT for pelvis has shown to produce results that meet the acceptance criteria derived from clinical practice and literature review as well as to perform at least as good as two FDA cleared devices for pseudo-CT generation.	Passed
Testing: pseudo-CT clinicalperformance and comparisonto predicates (brain)(V1.10.0)	The evaluation demonstrated the non-inferiority of using Annotate's pseudo-CT for treatment planning in terms of dosimetric measures as compared to CT-based treatment planning. Our pseudo-CT for pelvis has shown to produce results that meet the acceptance criteria derived from clinical practice and literature review as well as to perform at least as good as two FDA cleared devices for pseudo-CT generation.	Passed
Study Protocol & Report(SPR): Testing:Autosegmentationperformances againstpredicates(V1.10.0)	This evaluation demonstrated the non-inferiority of using ART-Plan v1.10.0 for annotation of organs as compared to other devices which have been cleared for use in the US. In addition, ART-Plan v1.10.0 offers almost 3 times (2.72) more organs than MIM/ContourProtege AI, which represents an additional benefit to the users as compared to other devices.	Passed
Study Protocol & Report(SPR): Autosegmentation	In this test, Annotate demonstrated equivalent performances between non-US and US population	Passed
performances on Thorax USdata(V1.10.0)	for the Thorax localisation. Considering that this isa worst case scenario of morphologicaldeformation due to factors such as age, gender orweight in abdominal region, we claim thatconsidering any localisation included in theintended use of ART-Plan, any autosegmentationresult demonstrated on a non-US population canbe generalized to a US population. Nonetheless,TheraPanacea has performed an additionalevaluation on pediatric US-data covering all otherlocalisations included in the intended use of thedevice.
Clinical evaluation of automaticsegmentation on Pediatricimages(V1.10.0)	Considering the fact that all the structures havereached a percentage of 90% (>=85%) of A or Bfor the MR brain model, and that 11/15 structurespassed with success for the CT model,Therapanacea claims that the performance of autosegmentation on said organs has beendemonstrated for the studied population.These results highlight the high generalizability ofthe commercial tool, initially made for adults, topediatric cases and its clinical implementationfeasibility. Note that this study served todemonstrate that ART-Plan's Annotate, trained onEuropean data, can be generalised to the USpopulation given that it would be clinicallyacceptable even for pediatric cases where a moreprominent change in size is expected than the onebetween two adults from different countries. Thisdoes not mean that TheraPanacea is claiming thatART-Plan should be used for pediatric patients.	Passed
System Verification andValidation Testing	The system verification and validation testing wasperformed to verify the software of the ART-Plan.	Passed

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

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

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

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

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

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

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

Clinical Studies

Page 27 of 28

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

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 devices.

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

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).