The HealthMyne software is a Picture Archiving and Communications System (PACS) intended to be used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The HealthMyne software displays, processes, stores, and transfers medical data from original equipment manufacturers (OEMs) that support the HL7 and DICOM (including DICOM-RT) standards, with the exception of mammography. It provides the capability to store images and patient information from OEM equipment, and perform filtering, digital manipulation and quantitative measurements, and export the product automatically and semiautomatically segments normal structures and abnormal structures (for example, nodules and lesions), and provides metrics for the structures.

The client software is designed to run on standard personal and business computers. The product is intended to be used by trained medical professionals, including but not limited to radiologists, and physicians. It is intended to provide image and related information (for example, image analysis) that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.

Device Description

HealthMyne accesses the information in real-time so that current patients and images are available to a clinician. The clinician can filter and search the patient and image metadata to find the desired patient(s) and/or image(s). The clinician can view the images in various hanging protocol layouts. The layouts contain viewports of the slices within the image set, each annotated with patient information. Within the viewports the clinician can manipulate the image using standard tools: scroll, pan, zoom, window and level, and view the location of the slice in other viewports. The system can automatically segment and register data sets, and calculate metrics on clinician-identified nodules. When a clinician identifies a seed point for a nodule, the system automatically finds the extent of the nodule. Regions of interest (organs and nodules) can be viewed on the 2D data sets as contours and as 3D models. Metrics can be used to aid in analysis of a study, including the American College of Radiology RADS standards, and specifically with this release the LungRADs categories.

AI/ML Overview

The provided text describes the HealthMyne software, a Picture Archiving and Communications System (PACS), and its comparison to a predicate device (VitreaAdvanced). However, it does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a study proving the device meets those criteria.

Specifically, the document is a 510(k) summary for FDA clearance, which focuses on substantial equivalence to a predicate device rather than presenting a comprehensive clinical study with specific acceptance criteria, sample sizes, expert adjudication, or MRMC studies for AI performance improvement.

The only section that vaguely touches upon "studies" is "Summary of Studies" on page 7, which states: "The HealthMyne software has undergone verification and validation to confirm its functional performance. Non clinical testing conformance to the following FDA recognized industry standards applicable to PACS devices: DICOM standard for medical diagnostic images, HL7 standard for patient information, SMPTE display, and the JPEG2000 image standard." This refers to technical compliance and functional testing, not a clinical study to prove the device meets specific performance criteria related to diagnostic accuracy or AI assistance.

Therefore, I cannot provide a table of acceptance criteria with reported device performance or information on MRMC studies, ground truth establishment for a test set, etc., as this information is not present in the provided document.

I will, however, extract what information is available:

1. A table of acceptance criteria and the reported device performance

This information is not provided in the document. The document focuses on functional comparison with a predicate device, not on specific clinical performance metrics with pre-defined acceptance criteria.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

This information is not provided in the document. The "Summary of Studies" mentions "verification and validation to confirm its functional performance" and "Non clinical testing conformance to...industry standards," but it does not describe a test set, its sample size, or data provenance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

This information is not provided in the document. No information on ground truth establishment for a test set is present.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

This information is not provided in the document.

5. 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

There is no indication of an MRMC comparative effectiveness study in the document. The device is described as a PACS system with features like segmentation and metrics, but not a device that directly assists with diagnosis in a way that would typically be evaluated by an MRMC study for improved human reader performance. Its intended use states "It is intended to provide image and related information (for example, image analysis) that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings."

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

The document does not detail any standalone performance studies for an "algorithm." While it mentions the product "automatically and semi-automatically segments normal structures and abnormal structures (for example, nodules and lesions), and provides metrics for the structures," it does not present a standalone performance evaluation of these automatic features.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

This information is not provided in the document.

8. The sample size for the training set

This information is not provided in the document. The document describes functional software capabilities, not an AI model that undergoes a training phase.

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

This information is not provided in the document. Similar to point 8, there's no mention of a training set or its ground truth.

In summary: The provided FDA 510(k) summary for HealthMyne focuses on demonstrating substantial equivalence to a predicate PACS device primarily through a feature-by-feature comparison and adherence to industry standards (DICOM, HL7, SMPTE, JPEG2000). It does not contain the detailed clinical study data, acceptance criteria, test set specifics, or AI performance metrics requested. The document emphasizes the device's role as a tool for trained medical professionals to interpret, rather than an AI system providing direct diagnoses or requiring extensive comparative effectiveness studies of human-AI collaboration.

Summary

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

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Department of Health & Human Services. The logo consists of a circular seal with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" around the perimeter. Inside the circle is a stylized symbol of three human profiles facing to the right, arranged in a cascading manner.

Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002

January 15, 2016

HealthMyne, Inc. % Mr. Mark Job Responsible Third Party Official 1394 25th Street, NW BUFFALO MN 55313

Re: K153289 Trade/Device Name: HealthMyne Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: December 31, 2015 Received: January 4, 2016

Dear Mr. Job:

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. 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 (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638 2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/Resourcesfor You/Industry/default.htm. 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

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely yours.

Michael D'Hara

For

Robert Ochs, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K153289

Device Name HealthMyne

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

Summary of Safety and Effectiveness/510k Summary

This 510(k) summary of safety and effectiveness information is submitted in accordance with the requirements of 21 CFR Part 807.87(h).

Company	HealthMyne, Inc.918 Deming WayMadison, WI 53717
Contact	Sigrid SchoepelDirector of Regulatory AffairsTelephone: 608-833-2610Email: sigrid.schoepel@healthmyne.com
Preparation Date	October 26, 2015
Trade Name	HealthMyne
Classification	Class II per 21 CFR 892.2050Picture Archiving and Communications System
Product Code	LLZ

Marketed Devices

HealthMyne is a software-only medical device that can manage OEM medical diagnostic images that are compatible with the DICOM standard. It performs functions similar to those currently available in the VitreaAdvanced software cleared for marketing via 510(k) K121213 by Vital Images, Inc.

Device Description

Intended Use

The HealthMyne software is a Picture Archiving and Communications System (PACS) intended to be used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The HealthMyne software displays, processes, stores, and transfers medical data from original equipment manufacturers (OEMs) that support the HL7 and DICOM (including DICOM-RT) standards, with the exception of mammography. It provides the capability to store images and patient information from OEM equipment, and perform filtering, digital manipulation and quantitative measurements, and export the information. The product automatically and semi-automatically

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

segments normal structures and abnormal structures (for example, nodules and lesions), and provides metrics for the structures.

The client software is designed to run on standard personal and business computers. The product is intended to be used by trained medical professionals, including but not limited to radiologists, oncologists, and physicians. It is intended to provide image and related information (for example, image analysis) that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.

Comparison with Predicate

HealthMyne performs many diagnostic image management picture archiving and communications functions available in the predicate device as shown in the following comparison chart. Its intended uses are similar to those of the predicate.

Element	Submission - HealthMyne 2015 Rel 2	Predicate - VitreaAdvanced 6.6(K121213)
Device Name	HealthMyne	VitreaAdvanced*
510(k) owner	HealthMyne, Inc.	Vital Images, Inc.
Supportsmammography	No.	No.
OperatingSystem	Windows, Linux	Windows
Platform	Client-server	Client-server
JPG/JPG 2000	Supported using third-party Kakadutool. ISO 10918/15444	Supported. See DICOM conformancestatement at vitalimages.com.
Images arestored/compressed/uncompressed	Both. Lossy used to indicateloading/for display only and losslessloaded simultaneously, unless DICOMcontains lossy only.	Both. Users can choose to compressimages.
Local archive:Server level/archive level	No separate archive due to software-only product. Redundant data storagerecommended to the customer.	Yes. Available as a separate product.
DICOMcompliant	Yes. See conformance statement.	Yes. See conformance statement atvitalimages.com.
HL7 support	Yes. See conformance statement.	No reference to HL7.
Study lists	Yes.	Yes.
Ability to filterand searchstudy list	Yes. Can set up custom filters.Dynamic (freeform) search andmatching. Also customizable, indexedsearch parameters.	Yes. Can set up custom filters. Search andmatching.
View study-relateddocuments	Yes. Presentation states and regions ofinterest/nodules.	Yes. Presentation states and regions ofinterest/nodules.
Managepushed studies	Yes. This product supports onlypushed studies. No studies originatewithin this product.	Yes. This product can import and exportusing DICOM.
Element	Submission - HealthMyne 2015 Rel 2	Predicate - VitreaAdvanced 6.6(K121213)
View currentand priorstudies at thesame time	Yes. Called current study and priorstudy. Prior studies have a large"PRIOR" label in each viewport.	Yes. Can select series from differentstudies for the same patient.
Re-organizeseries in astudy (forviewing)	Yes. Has a thumbnail view with theability to drag and drop the thumbnailinto a viewport. Cannot save theorder.	Yes. Can drag and drop a viewport imageto another viewport.
Createseparatedisplays	Yes. Can display a viewport as a singleviewport, can select a viewport layoutand add series to it.	Yes. Can display a viewport as a singleviewport, can select a viewport layout andadd series to it.
Cycle throughseries	Yes. Can show the "next" and"previous" sets of series.	Yes. Can show the "next" and "previous"sets of series.
Image displaymodes	Yes. Static and manual cine.	Yes. Static and manual cine.
Display colorimages	Yes.	Yes.
Select images	Yes. There is an active image indicator.The active image can be chosen or isautomatically set based on tool use.	Yes. Select images to group and/orperform functions.
Delete images	Yes. Only with PACS admin privilegesand from the admin console.	Yes. Can delete images from the viewerwindow.
Sort images	Yes. Sorting and grouping are bysystem-defined rules.	Yes. Sorting and grouping are by system-defined rules.
Scrollingthrough slices	Yes. Linked series are scrolledtogether. Can "swipe" on a scroll barto move through slices quickly. Canlock/unlock scrolling through everyimage.	Yes. Grouped series are scrolled together.
Zoom in/out	Yes. Default settings and can zoominteractively.	Yes. Default settings and can zoominteractively.
Pan an image	Yes.	Yes.
Rotate animage	Yes. In 3D.	Yes. Can flip 2D images and rotate 2D and3D images.
3D images	Yes.	Yes.
3D MIP	No.	Yes.
Create obliqueplanes	No.	Yes.
Standardviewportlayouts	Yes. Viewport layouts that areindependent of any modality orcommon features of series.	Yes. Viewport layouts that areindependent of any modality or commonfeatures of series.
Customlayouts	No. Viewport layouts and hangingprotocols are factory-default.	Yes. Viewport layouts can be set by theuser.
Element	Submission - HealthMyne 2015 Rel 2	Predicate – VitreaAdvanced 6.6(K121213)
Labels	Yes. There are labels in the viewport for patient, study, and image information.	Yes. There are labels in the viewport for patient, study, and image information.
Orientation labels	Yes.	Yes.
Cross-reference indicator	Yes. There is a cutline in linked viewports to indicate intersection.	No. Use of cross-hair markers.
Location indicator	Yes. There is a cross-hair tool to show a point of interest.	Yes. There is a cross-hair tool to show a point of interest, also used to change the axis in 3D rotation.
View DICOM data	Yes. You can view the DICOM information about the patient, study, and current image.	Yes. You can view the DICOM information about the patient, study, and current image.
Create MPR images	Yes. MPRs from the external source are supported/displayed and can create multi-planar reconstructions of 2D images.	Yes. Can create multi-planar reconstructions of 2D images and set options for display.
Window/level across series	Yes. W/L settings are applied to the active image and any linked images.	Yes. Must group series to link W/L.
Window/level presets	Yes. Factory default.	Yes. Factory defaults and can save window/level settings.
Adjust window/level	Yes. Can interactively adjust the window and level.	Yes. Can interactively adjust the window and level.
Post-processing of images	Yes. Can create multi-planar reconstructions of 2D images and 3D views of contours.	Yes. Can create multi-planar reconstructions of 2D images and 3D views.
Annotation	Yes. User can display annotations and can add and edit callouts.	Yes. User can display annotations and can add and edit callouts.
Measuring tools	Yes. Pixel intensity/location and ruler.	Yes. Ruler.
Metrics	Yes. Image analysis metrics.	Yes. Image analysis metrics.
ACR RADS categories	Yes. Architecture in place to display RADS categories, initial implementation is for LungRADS.	Yes. References the Fleischner society guidelines. LungRADS's risk stratification is based on the Fleischner society guidelines.
Store presentation states	Yes. Can save certain visualization settings.	Yes. Can save certain visualization settings.
Detect image/patient issues	Yes. Can view patients and studies with errors.	Yes. Can view patients and studies with errors.
Print reports	No.	Yes. Can export and print reports.
Element	Submission – HealthMyne 2015 Rel 2	Predicate - VitreaAdvanced 6.6(K121213)
Customhangingprotocols	No. Comes with factory-defaulthanging protocols.	No. Comes with factory-default layouts.
Custom filters	Yes. Can set filters to affect the studieslisted.	Yes. Can set filters to affect the studieslisted.
Set readingstate	Yes. Can mark a study as read.	Yes. Can mark a study as read.
Custom searchgroups	Yes. Can set "codes" to indexelements for searching (for example,referring physician or sets of examtypes) for faster auto-complete duringsearch.	Yes. Can set searches using matches andranges on the column headings.
Display RTPstructures	Yes. Supports DICOM RT structures.	Yes. Supports DICOM RT structures.
Registerimages	Yes. Can automatically and/ormanually register images.	Yes. Can manually synchronize datasets inviewers. Only applies to MPRs and 3Dimages.
Segmentregions ofinterest (ROIs)	Yes. Can automatically generate ROIsand also manually identify nodules forautomatic generation of nodule ROIs.	Yes. Can automatically generate ROIs andalso manually identify nodules forautomatic generation of nodule ROIs.
Edit ROIs	Yes. Can edit the shape of nodules inthree dimensions.	Yes. Can edit ROIs in three dimensions.
Manual noduledetection	Yes. Manual click to identify nodules,automatic segmentation of thevolume.	Yes. Manual click to identify nodules,automatic segmentation of the volume.
Automaticnoduledetection	No.	Yes. Automatic detection of nodules incurrent study if nodules identified inprevious studies, and the reverse.
Nodule displaymodes	Yes. View nodules independently or inreference to other anatomy.	Yes. View nodules independently or inreference to other anatomy.
Image fusion	No.	Yes. Create a fused 3D image bycombining series.
Timelinecomparison	No.	Yes. Compare between nodules in studiesof elapse time between scans, doublingtime, percent growth

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

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

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

Summary of Studies

The HealthMyne software has undergone verification and validation to confirm its functional performance. Non clinical testing conformance to the following FDA recognized industry standards applicable to PACS devices: DICOM standard for medical diagnostic images, HL7 standard for patient information, SMPTE display, and the JPEG2000 image standard.

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

Conclusion

It is the opinion of HealthMyne, Inc. that the HealthMyne software is substantially equivalent to similar image management options available in the predicate device. HealthMyne does not include any new indications for use with regards to the management of medical diagnostic image information, nor does use of this software result in any new potential hazards.

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).