Autofuse by Pymedix | FDA 510(k) Summary

Autofuse is a software package that provides physicians a means for comparison of medical data including imaging data that is DICOM compliant. It allows the display, annotation, volume operation, volume rendering, registration and fusion of medical images as an aid during use by diagnostic radiology, oncology, radiation therapy planning, and other medical specialties. Autofuse is not intended for mammography.

Device Description

Autofuse is a software application providing relevant tools for Radiotherapy professionals to use while creating treatment plans.

The Autofuse device is a Picture Archiving and Communication System (medical imaging software). Autofuse provides medical image processing designed to facilitate the oncology or other clinical specialty workflow by allowing the comparison of medical imaging data from different modalities, points in time, and / or scanning protocols. The product provides users with the means to display, co-register and analyze medical images from multiple modalities including PET, CT, RT Dose and MR; draw Regions of Interest (ROI); and import / export results to/from commercially available radiation treatment planning systems and PACS devices. Co-registration includes deformable registration technology that can be applied to DICOM data including diagnostic and planning image volumes, structures, and dose.

Autofuse is used as a stand-alone application on recommended Off-The-Shelf (OTS) computers supplied by the company or by the end-user.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the "Autofuse" device, based on the provided FDA 510(k) submission:

Acceptance Criteria and Device Performance

The submission primarily focuses on demonstrating substantial equivalence to a predicate device ("Velocity AIS") by comparing technological characteristics and asserting similar or better performance based on non-clinical testing. There isn't a table explicitly listing "acceptance criteria" with numerical targets and then "reported device performance" against those targets in a quantitative sense for Autofuse itself. Instead, the "acceptance criteria" are implied by the features and performance of the predicate, and the "reported device performance" is a general statement of conformance based on software verification and validation.

Implied Acceptance Criteria and Reported Device Performance (Derived from Comparison to Predicate):

Feature/Characteristic (Implied Acceptance Criteria from Predicate)	Autofuse Performance (Reported)
General Functionality
Display, annotation, volume operation, volume rendering, registration, fusion of medical images as an aid during diagnostic radiology, oncology, radiation therapy planning, and other medical specialties. (Not for mammography)	Performs all these functions.
DICOM compliant data handling	DICOM compliant.
Image Study Importation (CT/MR/PET/Dose/SPECT)	Imports CT/MR/PET. Imports DICOM-RT Dose. (Note: Autofuse sees Dose as an object associated with a scan, not an imaging modality itself, but this is deemed not to raise new safety/efficacy questions). The predicate supports SPECT, while Autofuse does not explicitly mention it for import, but the overall import capability is "Similar" and the difference is deemed not to raise new safety/efficacy questions.
Image Structure Import, Save & Export to Treatment Planning Systems	Yes
Volume Rendering	Yes
Advanced Visualization and Navigation Features	Yes
Volume Operations	No (Same as predicate)
Diagnostic Image Registration	Yes
Image Fusion (Anatomical and Functional)	Yes
ROI & Contouring	Yes
Manual Contouring Tools	Yes
Image Analysis	Yes
Plan Review of Imported Plans or Created Dose Composites	No (Same as predicate)
Oncology Workflow Automation	No (Same as predicate)
Image/ROI Export to DICOM RT	Yes
User Scaling of Image Volumes	No (Same as predicate)
Biological Effective Dose (BED) Scaling	No (Same as predicate)
Y-90 Microsphere Dosimetry	No (Same as predicate)
Navigator Semi-Automated Workflows	No (Image registration is fully automated with no user-facing workflow; same as predicate).
Adaptive Navigators to Assist in Offline Dose Review	No (Same as predicate)
Automated Image-Based Registration
Manual Registration Editing	No (Predicate has it). Autofuse differs by not allowing manual registration editing, citing AAPM TG-132. This difference is deemed not to bring up new questions of safety or efficacy.
Auto Rigid Registration	Yes
Deformable Registration	Yes
Inverse Deformable Registration	No (Same as predicate)
Structure Guided Deformable	No (Same as predicate)
Segmentation
Atlas Auto-Segmentation	No (Predicate has it). Autofuse does not contain or use atlases for auto-segmentation. This difference is deemed not to bring up new questions of safety or efficacy.
Image Analysis with Volumetric Graphs
Histograms and Voxel Assessment Graphs	Yes
DVH Statistics Display	Yes
Security/Platform
Secure Login and Data Storage	No (Predicate has application-level login). Autofuse runs on a secure workstation, logging OS-level info, with storage and authentication handled by the OS. This difference is deemed not to bring up new questions of safety or efficacy.
Logging of Database Activity	No (Predicate logs database activity). Autofuse's database activity is timestamped, tagged by user, and logged for all transactions. This difference is deemed not to bring up new questions of safety or efficacy. (Note: The table entry for Autofuse says "No" for logging, but the remark describes logging functionality. This appears to be a discrepancy in the table's "Yes/No" column vs. the descriptive remark.)
Operating System Platform	Ubuntu 22.04 (Predicate: Microsoft Windows, MAC OSX). Different platform (Linux-based) but deemed not to raise new questions of safety or efficacy.

Study Information:

Sample sizes used for the test set and the data provenance:
- The submission does not specify a distinct "test set" sample size in terms of number of cases or patients.
- The non-clinical validation testing was performed in a "Staging Environment (SE), which consists of a network of virtual machines (VMs) within a Kernel Virtual Machine (KVM) hypervisor." This environment was "designed to mimic a typical clinical set up" and included a departmental CT scanner and a radiology PACS.
- No information is provided regarding the country of origin of the data used for testing, nor whether it was retrospective or prospective. It's implied to be simulated or example data suitable for verification and validation.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The submission does not mention the use of experts to establish ground truth for a test set. The validation is focused on software verification against specifications and intended use in a simulated environment, rather than clinical performance against expert-defined ground truth.
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- No information on adjudication methods is provided, as the study described is software verification and validation, not a reader-based clinical study.
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:
- No MRMC comparative effectiveness study was done or reported in this submission.
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, the primary performance data presented is "Non-clinical performance Data" based on "Software Verification and Validation Testing." This represents the standalone performance of the algorithm against its documented specifications and user needs in a simulated environment. The device is described as "a stand-alone application."
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the non-clinical performance data, the "ground truth" is effectively the device specifications, user needs, and applicable requirements and standards against which the software was tested. It is not clinical ground truth like pathology or expert consensus on patient data.
The sample size for the training set:
- The submission does not explicitly describe a "training set" or "training process" for the Autofuse software in the context of machine learning, as it is characterized as medical image management and processing software with deformable registration technology, rather than a deep learning-based diagnostic algorithm requiring extensive training data. Therefore, no sample size for a training set is provided.
How the ground truth for the training set was established:
- As no training set is described in the context of machine learning, no information is provided on how ground truth for a training set was established.

Summary

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

March 6, 2024

Image /page/0/Picture/1 description: The image contains the logo for the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, with the word "ADMINISTRATION" underneath.

Pymedix % Trey Thorsen RA Consultant Lean RAQA 131 E Loch Lomond Pl ORO VALLEY, AZ 85737

Re: K233572

Trade/Device Name: Autofuse Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: January 30, 2024 Received: February 2, 2024

Dear Trey Thorsen:

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).

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

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

Loran Weiner

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

Submission Number (if known)

K233572

Device Name

Autofuse

Indications for Use (Describe)

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}------------------------------------------------

1. APPLICANT INFORMATION

Pymedix Company Contact
Name:	Kris Huang
Title:	Co-CEO, CTO
Phone Number:	513-693-5845
Email:	kris.huang@pymedix.com
Official Correspondent
Name:	Trey Thorsen
Title:	RA consultant
Phone Number:	850-450-3932
Email:	treyt@leanraqa.com

2. DEVICE INFORMATION

Device Name:	Picture Archiving and Communication System
Common Name:	Medical Imaging Software
Classification Name:	Medical image management and processing system
Model(s):	Autofuse
Regulation Number:	21 CFR § 892.2050
Product Code:	LLZ
Class:	II

3. PREDICATE DEVICES

Predicate Type	510(k)Number	Name of Device	Name of Manufacturer
Primary Device	K081076	Velocity AIS	Velocity Medical Solutions, LLC
Reference Device	K201607	Eclipse TreatmentPlanning System, v16.1	Varian Medical Systems, Inc

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

4. DEVICE DESCRIPTION

Autofuse is a software application providing relevant tools for Radiotherapy professionals to use while creating treatment plans.

Autofuse is used as a stand-alone application on recommended Off-The-Shelf (OTS) computers supplied by the company or by the end-user.

5. INDICATIONS FOR USE

Autofuse is not intended for mammography.

Characteristic	Proposed Device	Predicate Device	Remark
Device	Autofuse	Velocity AIS	N/A
Manufacturer	Pymedix, Inc.	Velocity MedicalSolutions, LLC	N/A
510(k) Number	TBD	K081076	N/A
Product CommonName	Picture Archiving andCommunication System(Medical ImagingSoftware)	Picture Archiving andCommunication System(Medical ImagingSoftware)	Same
Product Code	LLZ	LLZ	Same
Classification	II	II	Same
Device description	Autofuse is a softwareapplication providingrelevant tools forRadiotherapyprofessionals to use	Velocity is a softwareapplication providingrelevant tools forRadiotherapyprofessionals to use	Similar

6. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS

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

while creating treatment plans.

The Autofuse device is a Picture Archiving and Communication System (medical imaging software). Autofuse provides medical image processing designed to facilitate the oncology or other clinical specialty workflow by allowing the comparison of medical imaging data from different modalities, points in time, and / or scanning protocols. The product provides users with the means to display, co-register and analyze medical images from multiple modalities including PET. CT. RT Dose and MR; draw Regions of Interest (ROI): and import / export results to/from commercially available radiation treatment planning systems and PACS devices. Coregistration includes deformable registration technology that can be applied to DICOM data including diagnostic and planning image volumes, structures, and dose.

Autofuse is used as a stand-alone application on recommended Off-The-Shelf (OTS) computers supplied by the company or by the end-user.

while creating treatment plans.

The Velocity device is a Picture Archiving and Communication System (medical imaging software). Velocity provides medical image processing designed to facilitate the oncology or other clinical specialty workflow by allowing the comparison of medical imaging data from different modalities, points in time, and / or scanning protocols. The product provides users with the means to display, co-register and analyze medical images from multiple modalities including PET. SPECT. CT, RT Dose and MR; draw Regions of Interest (ROI), calculate and report relative differences in pixel intensities, Standardized Uptake Value (SUV) or other values within those regions; and import / export results to/from commercially available radiation treatment planning systems and PACS devices. Co-registration includes deformable registration technology that can be applied to DICOM data including diagnostic and planning image volumes, structures, dose, and automatic anatomical

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

			atlas-basedsegmentation tools.
			Velocity is used as astand-alone applicationon recommended Off-The-Shelf(OTS)computerssupplied by thecompany or by the end-user.
	Indications for Use	Autofuse is a softwareproduct that providesphysicians a means forcomparison of medicaldata including imagingdata that is DICOMcompliant. It allows thedisplay, annotation,volume operation,volume rendering,registration and fusion ofmedical images as an aidduring use by diagnosticradiology, oncology,radiation therapyplanning, and othermedical specialties.Autofuse is not intendedfor mammography.	VelocityAIS (VelocityAI)is a standalone softwareproduct that providesthe physician a meansfor comparison ofmedical imaging datafrom multiple DICOMconformant imagingmodality sources. Itallows the display,annotating, volumerendering, registrationand fusing of medicalimages as an aid duringuse by diagnosticradiology, oncology,radiation therapyplanning and othermedical specialties.VelocityAIS (VelocityAI)is not intended formammographydiagnosis.	Similar
General Usage/Performance Features
	Image StudyImportation	CT/MR/PET	DICOM,PET/SPECT/CT/MRI;Dose	Similar. Themost commonlyused imagingmodalities usedin radiationtreatmentplanning areDICOM-formatCT, MR, andPET images.

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

			Autofuse doesallow import ofDICOM-RTDose, but it isconsidered aDICOM-RTobjectassociated witha scan, not animagingmodality itself.This differencedoes not bringup any newquestions ofsafety orefficacy.
Image StructureImport, Save &Export to TreatmentPlanning Systems	Yes	Yes	Same
Volume Rendering	Yes	Yes	Same
AdvancedVisualization andNavigation Features	Yes	Yes	Same
Volume Operations	No	No	Same
Diagnostic ImageRegistration	Yes	Yes	Same
Image Fusion	Yes; Anatomical andFunctional Images	Yes; Anatomical andFunctional Images	Same
ROI & Contouring	Yes	Yes	Same
Manual ContouringTools	Yes	Yes	Same
Image Analysis	Yes	Yes	Same
Plan Review ofImported Plans orCreated DoseComposites	No	No	Same
Oncology WorkflowAutomation	No	No	Same
Image/ROI Exportto DICOM RT	Yes	Yes	Same
Secure Login andData Storage	No	Yes	Velocity usesan application-level login.Autofuse isintended to runon a secure
			workstation andlogs OS-levelinformation ofthe user loggedin and runningthe application.Data storageand userauthenticationis handled bythe underlyingworkstation OS,not theAutofuseapplication.This differencedoes not bringup any newquestions of
			safety orefficacy.
Operating SystemPlatform	Ubuntu 22.04	Microsoft Windows XP32 bit only/ Windows 7,Vista, MAC OSX 10.6	Autofuse isintended foruse in a secureLinux-basedcomputingenvironment.This differencedoes not bringup any newquestions ofsafety orefficacy.
Multimodality DICOM Import
Import and DisplayDICOM CT, MR,DS, PET, RTS, RTP	Yes	Yes	Same
Advanced Visualization and Navigation
General ImageViewer with ViewLayout Selectionand Toolbars	Yes	Yes	Same
User Scaling ofImage Volumes	No	No	Same
Biological EffectiveDose (BED) Scaling	No	No	Same
Y-90 MicrosphereDosimetry	No	No	Same
conversion ofSPECT to DS
	Automated Image-Based Registration
Manual RegistrationEditing	No	Yes	Autofuse doesnot allowmanualregistration.AAPM TG-132states "direct,unguidedmanualadjustment of adeformationvector field isnotrecommended".This differencedoes not bringup any newquestions ofsafety orefficacy.
Auto RigidRegistration	Yes	Yes	Same
DeformableRegistration	Yes	Yes	Same
Inverse DeformableRegistration	No	No	Same
Structure GuidedDeformable	No	No	Same
	Segmentation (Manual Contouring Tools and Atlas Segmentation)
Manual ContouringTools	Yes	Yes	Same
Atlas Auto-Segmentation	No	Yes	Autofuse doesnot contain oruse atlases forauto-segmentation.This differencedoes not bringup any newquestions ofsafety orefficacy.
Image Analysis with Volumetric Graphs
Histograms andVoxel AssessmentGraphs	Yes	Yes	Same
	DVH StatisticsDisplay	Yes	Yes	Same
	Plan Review
	Storage and Displayof DICOM RT Plans	No	No	Same
	Lesion VolumeTracking byAssociatingStructure withName Tag	No	No	Same
	Navigator Semi-Automated Workflows
	Semi-automaticWorkflows to Assistwith CommonClinical ImageRegistration &Analysis Tasks	No. Image registration isfully automated with nouser-facing workflow.	No	Same
	Adaptive Navigatorsto Assist in OfflineDose Review:Includes workflowsto create adaptiveCT based on CBCTRegistration, copyplan to adaptive CT,and compare dose	No	No	Same
	Security
	Logging ofDatabase Activity	No	Yes	Databaseactivity istimestamped,tagged by userand logged forall transactions.This differencedoes not bringup any newquestions ofsafety orefficacy.

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

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

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

7. PERFORMANCE DATA

7.1 Non-clinical performance Data

Software Verification and Validation Testing Software verification and validation was 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 primary objective of the design validation testing process was to ensure

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

documented confirmation that the device specifications meet user needs and the intended use through thorough testing in a simulated environment as part of the Design Control Process. Test results demonstrate conformance to applicable requirements and specifications.

The following references provide external standards and quidelines that are used, in part, for the definition of the quidelines provided in this document:

21 CFR Part 820, Quality System (QS) Regulation/Medical Device Good Manufacturing . Practices, US Food and Drug Administration
. ISO 13485:2016. Medical devices - Quality management systems - Requirements for regulatory purposes, International Organization for Standardization
ISO/DIS 10013 Quality management systems - Guidance for documented information, International Organization for Standardization
Glossary of Computerized System and Software Development Terminology. Division of . Field Investigations, Office of Regional Operations, Office of Regulatory Affairs, Food and Drug Administration, August 1995.
. AAPM Report No. 062 - American Association of Physicists in Medicine Radiation Therapy Committee Task Group 53: Quality assurance for clinical radiotherapy treatment planning (1998) ICRU Report 83 - Prescribing, Recording, and Reporting Intensity-Modulated Photon-Beam Therapy (IMRT)
AAPM Report No. 132 Use of image registration and fusion algorithms and techniques in ● radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132 (2017)

Non-clinical validation testing was performed in the Staging Environment (SE), which consists of a network of virtual machines (VMs) within a Kernel Virtual Machine (KVM) hypervisor. The network of VMs is designed to mimic a typical clinical set up including a departmental CT scanner and a radiology PACS communicating with unencrypted DIMSE communications or TLS-encrypted DIMSE communications.

7.2 Biocompatibility

Not applicable. Autofuse is software.

7.3 Clinical performance data

No clinical study is included in this submission.

8. CONCLUSION

The conclusions drawn from the nonclinical tests demonstrate that the proposed device is substantially equivalent, and performs as well as or better than 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).