Trained medical professionals use Contour ProtégéAI as a tool to assist in the automated processing of digital medical images of modalities CT and MR, as supported by ACR/NEMA DICOM 3.0. In addition, Contour ProtégéAI supports the following indications:

· Creation of contours using machine-learning algorithms 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.

· Segmenting anatomical structures across a variety of CT anatomic locations.

· And segmenting the prostate, the seminal vesicles, and the 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.

Device Description

Contour ProtégéAI is an accessory to MIM software that automatically creates contours on medical images through the use of machine-learning algorithms. It is designed for use in the processing of medical images and operates on Windows, Mac, and Linux computer systems. Contour ProtégéAl is deployed on a remote server using the MIMcloud service for data management and transfer; or locally on the workstation or server running MIM software.

AI/ML Overview

Here's a detailed breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary:

Acceptance Criteria and Reported Device Performance for Contour ProtégéAI

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria Category	Acceptance Criteria	Reported Device Performance (Contour ProtégéAI)
Individual Structure Performance	1. Statistical non-inferiority of the Dice score compared with the reference predicate (MIM Maestro atlas segmentation). 2. Statistical non-inferiority of the MDA score compared with the reference predicate (MIM Maestro atlas segmentation). 3. Average user evaluation score of 2 or higher (on a 3-point scale). A structure is deemed acceptable if it passes two or more of these three tests.	Dice Score: For all reported structures in the Head and Neck, Thorax, and Whole Body - Physiological Uptake Organs CT models, Contour ProtégéAI generally showed higher mean Dice scores (indicating better overlap with ground truth) and often superior lower 95th percentile confidence bounds compared to MIM Atlas. Equivalence (defined as lower 95th percentile confidence bound of ProtégéAI Dice > 0.1 Dice lower than MIM Atlas mean) was demonstrated for most structures, often with direct improvement. MDA Score: For most reported structures, Contour ProtégéAI showed lower mean MDA scores (indicating better boundary accuracy/distance to ground truth) and often superior upper 95th percentile confidence bounds compared to MIM Atlas. Equivalence was demonstrated for most structures, again often with direct improvement. External Evaluation Score: All reported structures achieved an average user evaluation score of 2 or higher (ranging from 2.0 to 3.0), indicating moderate to significant time savings. Overall: The summary states: "Contour ProtégéAl results were equivalent or had better performance than the MIM Maestro atlas segmentation reference device." And "only structures that pass two or more of the following three tests could be included in the final models". This indicates successful performance against the criteria for all included structures.
Model-as-a-Whole Performance	Statistically non-inferior cumulative Added Path Length (APL) compared to the reference predicate.	Cumulative APL (mm): - Head and Neck CT: MIM Atlas: 38.69 ± 33.36; Contour ProtégéAI: 28.61 ± 29.59. Equivalence demonstrated. - Thorax CT: MIM Atlas: 89.24 ± 82.73; Contour ProtégéAI: 65.44 ± 68.85. Equivalence demonstrated. - Whole Body - Physiological Uptake Organs CT: MIM Atlas: 138.06 ± 142.42; Contour ProtégéAI: 98.20 ± 127.11. Equivalence demonstrated. This indicates that Contour ProtégéAI performs with lower or equivalent APL, suggesting less editing time for the entire model.
Localization Accuracy (Informational)	No passing criterion, but results included for user understanding.	Percentage of images successfully localized by Contour ProtégéAI is provided for each structure and model. Most structures show 100% localization accuracy within their relevant FOV for Head and Neck and Thorax models. Some structures (e.g., Cochlea_L/R, OpticChiasm, Pancreas) show slightly lower percentages, indicating instances where the structure was not localized. For Whole Body CT, many structures also show 100%, with a few exceptions (e.g., Bladder: 95%, LN_Iliac: 64%).

2. Sample Size Used for the Test Set and Data Provenance

Test Set Sample Size: 754 independent images.
Data Provenance: Gathered from 27 institutions. The document does not explicitly state the countries of origin for the test set, but for the training set, it mentions "across multiple continents" and lists "USA" and "Hong Kong" and "Australia." It is reasonable to infer the test set would also be from diverse institutions/countries. The data is retrospective as it was gathered from existing clinical treatment plans.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

The ground truth for the test set was established by a multi-stage process involving:

Initial Segmentation: Consultants (physicians and dosimetrists).
Review and Correction: A radiation oncologist.
Final Review and Correction: Qualified staff at MIM Software (M.D. or licensed dosimetrists).

While the exact number of experts is not specified, it involved multiple individuals with specialized qualifications (physicians, dosimetrists, radiation oncologists, M.D.s, licensed dosimetrists).

4. Adjudication Method for the Test Set

The ground truth generation involved a multi-stage review and correction process:

Initial segmentations by consultants (physicians and dosimetrists).
Review and correction by a radiation oncologist against established standards and guidelines.
Final review and correction by qualified staff at MIM Software (M.D. or licensed dosimetrists).

This indicates a sequential refinement process, potentially similar to a "cascading consensus" or "expert review and correction" rather than a specific numeric adjudication method like 2+1 or 3+1 for resolving disagreements among multiple initial segmenters. The explicit mentioning of "correction" at multiple stages suggests an iterative process where initial segmentations were refined based on expert review.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a traditional MRMC comparative effectiveness study was not explicitly stated in the provided text in the context of comparing human readers with and without AI assistance to measure an effect size on human performance.

Instead, the study primarily focused on the standalone performance of the AI model (Contour ProtégéAI) compared to an existing atlas-based segmentation system (MIM Maestro) using quantitative metrics (Dice, MDA, APL) and a user evaluation for "time savings functionality." The user evaluation (average score of 2 or higher on a three-point scale for time savings) provides an indirect measure of the AI's utility, but not a direct MRMC study on human reader improvement with AI.

6. If a Standalone Study Was Done

Yes, a standalone study was done.

Contour ProtégéAI (the algorithm under review) was evaluated in comparison to a reference predicate device, MIM Maestro (K071964), which uses an atlas-based segmentation approach.
The comparison involved quantitative metrics like Dice score, MDA, and cumulative APL, as well as a qualitative user evaluation. The goal was to show that Contour ProtégéAI was equivalent or superior in performance to the reference predicate in a standalone capacity.

7. The Type of Ground Truth Used

The ground truth used for the test set was expert consensus / expert-derived segmentation.

It was derived from clinical treatment plans, but the original segmentations were not used.
The images were re-segmented by consultants (physicians and dosimetrists) specifically for this purpose, following detailed clinical contouring guidelines.
These initial segmentations were then reviewed and corrected by a radiation oncologist.
A final review and correction was performed by qualified staff at MIM Software (M.D. or licensed dosimetrists).
All segmenters were instructed to ensure the "highest quality training data" and contour according to referenced standards.

8. The Sample Size for the Training Set

CT Models: A total of 550 CT images from 41 clinical sites.
The document implies that these 550 images are specifically for the training of the final 4.1.0 neural network models for CT. It does not explicitly state the training set size for MR models if they were separate.

9. How the Ground Truth for the Training Set Was Established

The ground truth for the training set was established through a rigorous, multi-stage expert-driven process, identical to the description for the test set ground truth:

Initial Segmentation: Performed by consultants (physicians and dosimetrists) following detailed instructions derived from published clinical contouring guidelines.
Review and Correction: By a radiation oncologist against the same standards and guidelines.
Final Review and Correction: By qualified staff at MIM Software (M.D. or licensed dosimetrists).
- The goal was "to ensure the highest quality training data."
- Segmenters were asked to contour all specified OAR structures on all images according to referenced standards, regardless of proximity to the treatment field.

Summary

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

November 8, 2023

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

MIM Software Inc. % Lynn Hanigan Principal Regulatory and Quality Specialist 25800 Science Park Drive, Suite 180 CLEVELAND. OH 44122

Re: K231765

Trade/Device Name: Contour ProtégéAI Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QKB Dated: October 9, 2023 Received: October 10, 2023

Dear Lynn Hanigan:

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

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

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

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

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

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

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

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

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

Sincerely,

Loca Weidner

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

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

Indications for Use

510(k) Number (if known) K231765

Device Name Contour ProtégéAI

Indications for Use (Describe)

· Segmenting anatomical structures across a variety of CT anatomic locations.

· And segmenting the prostate, the seminal vesicles, and the 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.

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

K231765

Image /page/3/Picture/1 description: The image shows the logo for MIM Software. The logo consists of a red square with rounded corners, partially covered by a gray square with rounded corners and a white circle in the middle. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it.

25800 Science Park Drive - Suite 180 Cleveland, OH 44122 866-421-2536 www.mimsoftware.com

510(k) Summary of Safety and Effectiveness (The following information is in conformance with 21 CFR 807.92)

Submitter:

MIM Software Inc. 25800 Science Park Drive - Suite 180 Cleveland, OH 44122

216-455-0600 Phone: 216-455-0601 Fax:

Contact Person:

Lynn Hanigan

October 5, 2023

Date Summary Prepared:

Device Name

Trade Name: Common Name: Regulation Number / Product Code: Classification Name:

Contour ProtégéAl Medical Imaqing Software 21 CFR 892.2050 Product Code QKB Radiological Image Processing Software For Radiation Therapy

Predicate Devices

Primary -	K223774	Contour ProtégéAI	MIM Software Inc.
Reference -	K071964	MIM 4.1 SEASTAR (tradename MIM Maestro)	MIMvista Corp.

Intended Use

Contour ProtégéAI is an accessory to MIM software. It includes processing components to automatically contour imaging data using machine-learning based algorithms.

Contour ProtégéAl must be used in conjunction with MIM software to review and, if necessary, edit results automatically generated by Contour ProtégéAI.

Contour ProtégéAl is not intended to automatically detect lesions.

Indications for Use

Trained medical professionals use Contour ProtégéAl as a tool to assist in the automated processing of digital medical images of modalities CT and MR, as supported by ACR/NEMA DICOM 3.0. In addition, Contour ProtégéAl supports the following indications:

Creation of contours using machine-learning algorithms for applications including, but not limited to, quantitative analysis, aiding adaptive therapy, transferring contours to radiation

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

Image /page/4/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a sans-serif font, with the word "SOFTWARE" in a smaller font below it. The logo is simple and modern, with a focus on the company's name.

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

Segmenting anatomical structures across a variety of CT anatomical locations.
And segmenting the prostate, the seminal vesicles, and the urethra within T2-weighted MR images.

Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAl.

Device Description

A total of 550 CT images from 41 clinical sites across multiple continents was gathered for the training of the final 4.1.0 neural network models. The following table lists the data used for the training of the 4.1.0 final production models. Across the training data, 56.4% were male, 25.8% were female, and 17.8% were not labeled. Training data patient age ranges were 1-20: 0.2%, 20-40: 1.8%, 40-60: 8.9%, 60+: 24.2%, and not labeled 64.9%. Images were acquired by scanners made by: Phillips, 38.5%, GE, 17.6%; Siemens, 16.2%; Toshiba, 2.7% and not labeled 25.0%. Over the dataset, 38.7% of the images were acquired with IV or oral contrast, and 61.3% were acquired with no contrast.

Institution	Country	# of images
Institution 1	USA	2
Institution 2	USA	5
Institution 3	USA	26
Institution 4	USA	8
Institution 5	USA	3
Institution 6	USA	1
Institution 7	USA	34
Institution 8	USA	17
Institution 9	USA	6
Institution 10	Hong Kong	30
Institution 11	USA	13
Institution 12	USA	6
Institution 13	USA	10
Institution 14	USA	6
Institution 15	USA	24
Institution 16	USA	2
Institution 17	USA	14

Table 1: CT data used to train the final production of the 4.1.0 CT models.

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

Image /page/5/Picture/0 description: The image shows the MIM Software logo. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it. The logo is simple and modern, with a focus on geometric shapes and clean lines.

Institution	Country	# of images
Institution 18	USA	7
Institution 19	USA	27
Institution 20	USA	27
Institution 21	USA	6
Institution 22	USA	41
Institution 23	Australia	19
Institution 24	USA	10
Institution 25	USA	11
Institution 26	USA	10
Institution 27	USA	2
Institution 28	USA	1
Institution 29	USA	6
Institution 30	USA	9
Institution 31	USA	4
Institution 32	USA	2
Institution 33	USA	6
Institution 34	USA	2
Institution 35	USA	6
Institution 36	USA	14
Institution 37	USA	4
Institution 38	USA	5
Institution 39	USA	75
Institution 40	Australia	48
Institution 41	USA	1

Substantial Equivalence

ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
Clearance Dates	TBD	04/06/2023	9/26/2007
ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
Intended Use	Contour ProtégéAI is anaccessory to MIM softwareused for the contouring ofanatomical structures inimaging data using machine-learning-based algorithmsautomatically.Appropriate image visualizationsoftware must be used toreview and, if necessary, editresults automatically generatedby Contour ProtégéAI.Contour ProtégéAl is notintended to detect or contourlesions.	Contour ProtégéAI is anaccessory to MIM software usedfor the contouring of anatomicalstructures in imaging data usingmachine-learning-basedalgorithms automatically.Appropriate image visualizationsoftware must be used to reviewand, if necessary, edit resultsautomatically generated byContour ProtégéAI.Contour ProtégéAl is notintended to detect or contourlesions.	MIM 4.1(SEASTAR)software isintended for trainedmedicalprofessionalsincluding, but notlimited to,radiologists,oncologists.physicians, medicaltechnologists,dosimetrists, andphysicists.MIM 4.1(SEASTAR) is amedical image andinformationmanagementsystem that isintended to receive,transmit, store,retrieve, display,print and processdigital medicalimages, as well ascreate, display andprint reports fromthose images. Themedical modalitiesof these medicalimaging systemsinclude, but are notlimited to, CT, MRI,CR, DX, MG, US,SPECT, PET andXA as supported byACR/NEMADICOM 3.0.MIM 4.1(SEASTAR)provides tools toquickly create,transform, andmodify contours for
ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
Indications for Use	Trained medical professionalsuse Contour ProtégéAl as atool to assist in the automatedprocessing of digital medicalimages of modalities CT andMR, as supported byACR/NEMA DICOM 3.0. Inaddition, Contour ProtégéAlsupports the followingindications:	Trained medical professionalsuse Contour ProtégéAl as a toolto assist in the automatedprocessing of digital medicalimages of modalities CT andMR, as supported byACR/NEMA DICOM 3.0. Inaddition, Contour ProtégéAlsupports the followingindications:	MIM 4.1(SEASTAR)software is used bytrained medicalprofessionals as atool to aid inevaluation andinformationmanagement ofdigital medical
	Creation of contours usingmachine-learningalgorithms for applicationsincluding, but not limited to,quantitative analysis, aidingadaptive therapy,transferring contours toradiation therapy treatmentplanning systems, andarchiving contours forpatient follow-up andmanagement.	Creation of contours usingmachine-learning algorithmsfor applications including,but not limited to,quantitative analysis, aidingadaptive therapy,transferring contours toradiation therapy treatmentplanning systems, andarchiving contours forpatient follow-up andmanagement.	images. Themedical imagemodalities include,but are not limitedto, CT, MRI, CR,DX, MG, US,SPECT, PET andXA as supported byACR/NEMADICOM 3.0. MIM4.1 (SEASTAR)assists in thefollowing
	Segmenting anatomicalstructures across a varietyof CT anatomical locations. And segmenting theprostate, the seminalvesicles, and the urethra	Segmenting anatomicalstructures across a variety ofCT anatomical locations. And segmenting theprostate, the seminalvesicles, and the urethra	indications:Receive,transmit, store, retrieve, display,print, and processmedical images
ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
	within T2-weighted MRimages.Appropriate image visualizationsoftware must be used toreview and, if necessary, editresults automatically generatedby Contour ProtégéAI.	within T2-weighted MRimages.Appropriate image visualizationsoftware must be used to reviewand, if necessary, edit resultsautomatically generated byContour ProtégéAI.	and DICOMobjects.· Create, displayand print reportsfrom medicalimages.· Registration,fusion display, andreview of medicalimages fordiagnosis,treatmentevaluation, andtreatment planning.• Localization anddefinition of objectssuch as tumors andnormal tissues inmedical images.· Creation,transformation, andmodification ofcontours forapplicationsincluding, but notlimited to,quantitativeanalysis, aidingadaptive therapy,transferringcontours toradiation therapytreatment planningsystems, andarchiving contoursfor patient follow-upand management.
ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
Modalities	CT and MR	CT and MR	CT, MR, CR, DX,MG, US, SPECT,PET and XA
Atlas-BasedSegmentation	No	No	Yes
AutomaticallyContour ImagingData UsingMachine-Learning	Yes	Yes	No
OperatingPlatform	Server-based applicationsupportingLinux-based OS- and -Local deployment on Windowsor Mac	Server-based applicationsupportingLinux-based OS- and -Local deployment on Windowsor Mac	Windows, Mac
Cloud-baseddeployment	Yes	Yes	No
Locally deployed(or installed)	Yes	Yes	No
ITEM	Subject Device:Contour Protégé Al(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
Neural NetworkModels included	(1.0.0 models)Head and Neck CTProstate CTThorax CTLiver CTProstate MR(1.1.0 model)Prostate MR(2.0.0 models)Head and Neck CTProstate CTThorax CTAbdomen CTLungs and Liver CT(3.1.0 models)*Head and Neck CTProstate CTThorax CTAbdomen CTLungs and Liver CTMRT Additional Structures CT(4.0.0 models)Head and Neck CTThorax CTAbdomen CTPelvis CT	(1.0.0 models)Head and Neck CTProstate CTThorax CTLiver CTProstate MR(1.1.0 model)Prostate MR(2.0.0 models)Head and Neck CTProstate CTThorax CTAbdomen CTLungs and Liver CT(3.0.0 models)Head and Neck CTProstate CTThorax CTAbdomen CTLungs and Liver CTMRT Additional Structures CT(4.0.0 models)Head and Neck CTThorax CTAbdomen CTPelvis CT	None
ITEM	Subject Device:Contour ProtégéAl(K231765)	Predicate Device:Contour ProtégéAl(K223774)	ReferencePredicate:MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964)
	SurePlan MRT CT	SurePlan MRT CT
	(4.1.0 models)
	Head and Neck CT
	Thorax CT
	Whole Body - PhysiologicalUptake Organs CT

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

Image /page/6/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle cut out of the red square. To the right of the squares is the text "mim" in a sans-serif font, with the word "SOFTWARE" in a smaller font below it. The logo is simple and modern, and the colors are eye-catching.

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

Image /page/7/Picture/0 description: The image shows the MIM Software logo. The logo consists of a red square with a white circle cut out of the top left corner, and a gray square overlapping the top left corner of the red square. To the right of the squares is the word "mim" in black, with the word "SOFTWARE" in smaller black letters below it.

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

Image /page/8/Picture/0 description: The image is a logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it.

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

Image /page/9/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a stylized font, with the word "SOFTWARE" in smaller letters below it.

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

Image /page/10/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle cut out of the red square. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it.

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

Image /page/11/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle cut out where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below.

Discussion

Changes within this submission include new 4.1.0 neural network models with additional contours. These changes differ when comparing to Contour ProtégéAl 510(K)223774. Noninferiority testing was used to compare the proposed Contour ProtégéAl device to Atlases created from the MIM Maestro (K071964) reference device.

Testing and Performance Data

The proposed Contour ProtégéAl device were then evaluated on the test subjects from a pool of 754 independent images gathered from 27 institutions.

The CT images for this training set were obtained from clinical treatment plans for patients prescribed external beam or molecular radiotherapy, but the original segmentations were not used. Instead, the images were re-segmented by consultants (physicians and dosimetrists) specifically for this purpose, outside of clinical practice. Detailed instructions derived from relevant published clinical contouring quidelines were prepared for the dosimetrists. The initial segmentations were then reviewed and corrected by a radiation oncologist against the same standards and quidelines. Qualified staff at MIM Software (M.D. or licensed dosimetrists) then performed a final review and correction. All segmenters were instructed to spend additional time to ensure the highest quality training data. In particular, the consultants were asked to contour all specified OAR structures on all images according to referenced standards, whether or not they were proximal to the treatment field. All patients were imaged on an indexed couch in treatment position ("simulation CT"). Series that were non-axial, had slices thinner than 0.5mm, or had non-Fan Beam or MV acquisitions were excluded.

The verification data used for testing is from a set of institutions that are totally disioint from the training datasets used to train each model in the Contour ProtégéAl device. The reference predicate MIM device was configured with Atlases built from the same training data used to train

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

Image /page/12/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they intersect. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it.

the models. We tested Contour ProtégéAl against the reference predicate device, and the goal of this testing is to show that it is equivalent or superior to the reference predicate. The performance of both segmentation devices was measured by calculating both the Dice score and MDA of the novel segmentations with the original ground-truth contours. User beta testing was also used to evaluate the performance of Contour ProtégéAl in the context of time savings compared to contouring from scratch. This user evaluation was made on a three-point scale for each contour, with one indicating negligible time savings, two indicating moderate, and three indicating significant time savings. Our acceptance criteria combine the statistical tests and the user evaluation - only structures that pass two or more of the following three tests could be included in the final models:

Statistical non-inferiority of the Dice score compared with the reference predicate. ●
. Statistical non-inferiority of the MDA score compared with the reference predicate.
Average user evaluation of 2 or higher, when measured on a three-point scale. .

Further clinical validation was also conducted in-house to evaluate contours compared to detailed criteria based on established clinical quidelines.

In addition, each model as a whole was also evaluated. In order to be included in the released product, the cumulative Added Path Length of the contours in the model was evaluated relative to the ground-truth. Cumulative APL has been found to correlate well with the spent in editing and correcting auto-segmented contours (Vaassen et al, 2020)'. Each model was required to have statistically non-inferior cumulative APL compared to the reference predicate.

Finally, the localization accuracy of each structure in all models was measured. We did not impose a passing criterion on localization accuracy; the results however are included in this summary document and in our User Guide and Whitepaper to allow the user to better understand the performance of the device.

Across the testing data the images 48.4% were female, 35.2% were male, and 16.4% were unknown for sex. The manufacturer was GE for 37.9% of images, 25.1% was Siemens, 15.0% were Philips, 0.4% were from Toshiba, and the other 21.6% were unknown. 4.38% were between the ages of 20-40, 21.5% were between 40-60, and 47.9% were over the age of 60. 26.0% were unknown, and 0.3% were under the age 20.

The mean and standard deviation Dice coefficients and MDA scores, along with the lower 95th percentile confidence bound, were calculated for both the proposed Contour ProtégéAl device and the MIM Maestro atlas seamentation reference device for each structure of each neural network model. Contour ProtégéAl results were equivalent or had better performance than the MIM Maestro atlas segmentation reference device. Equivalence is defined such that the lower 95th percentile confidence bound of the Contour ProtégéAl segmentation is greater than 0.1 Dice lower than the mean MIM atlas segmentation reference device performance.

Results over the validation set compared to the reference device are presented here:

4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
Head andNeck	Bone_Mandible	0.81 ± 0.07	0.86 ± 0.07(0.83) *	1.00 ± 0.87	0.64 ± 0.31(0.93) *	2.86
	BrachialPlex_L	0.17 ± 0.08	0.22 ± 0.10(0.14) *	3.24 ± 2.62	2.82 ± 2.61(5.12) *	2.6
4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
	BrachialPlex_R	0.15 ± 0.07	0.19 ± 0.09(0.11) *	3.62 ± 2.79	2.73 ± 2.38(5.20) *	2.6
	Brain	0.97 ± 0.01	0.98 ± 0.01(0.97) *	0.64 ± 0.37	0.52 ± 0.36(0.66) *	2.71
	Brainstem	0.78 ± 0.09	0.82 ± 0.08(0.78) *	1.72 ± 0.81	1.20 ± 0.65(1.47) *	2.71
	Cavity_Oral	0.75 ± 0.14	0.76 ± 0.13(0.68) *	3.34 ± 2.13	3.20 ± 1.93(4.35) *	2.71
	Cochlea_L	0.19 ± 0.15	0.30 ± 0.18(0.22) *	1.26 ± 0.85	1.17 ± 0.87(1.58) *	2.29
	Cochlea_R	0.17 ±0.15	0.32 ± 0.20(0.23) *	1.12 ± 0.61	1.05 ± 0.68(1.37) *	2.29
	Eye_L	0.80 ± 0.08	0.87 ± 0.06(0.83) *	1.07 ± 0.60	0.65 ± 0.51(0.91) *	2.57
	Eye_R	0.80 ± 0.10	0.86 ± 0.07(0.82) *	1.11 ±0.64	0.66 ± 0.48(0.92) *	2.57
	Glnd_Lacrimal_L	0.22 ± 0.17	0.40 ± 0.16(0.27) *	0.86 ± 0.54	0.68 ± 0.35(1.05) *	2.71
	Glnd_Lacrimal_R	0.23 ± 0.16	0.45 ± 0.14(0.34) *	0.73 ± 0.38	0.71 ± 0.52(1.09) *	2.71
	Glnd_Submand_L	0.57 ± 0.13	0.77 ± 0.11(0.69) *	1.74 ± 0.72	0.76 ± 0.32(1.12) *	3
	Glnd_Submand_R	0.56 ± 0.16	0.75 ± 0.11(0.65) *	1.82 ± 0.87	0.81 ± 0.34(1.28) *	3
	Glnd_Thyroid	0.47 ±0.18	0.71 ±0.19(0.57) *	2.55 ± 2.14	1.38 ± 3.18(3.38) *	2.71
	Lens_L	0.22 ± 0.23	0.61 ± 0.17(0.52) *	0.77 ± 0.54	0.56 ± 0.47(0.84) *	2.29
	Lens_R	0.22 ± 0.22	0.63 ± 0.16(0.54) *	0.81 ± 0.47	0.55 ± 0.33(0.78) *	2.29
	Lips	0.38 ± 0.14	0.37 ± 0.15(0.28) *	4.14 ± 2.86	5.26 ± 3.41(7.27)	2.83
	OpticChiasm	0.04 ± 0.07	0.13 ±0.13(0.08) *	2.69 ± 1.87	2.46 ± 1.99(3.55) *	2
	OpticNrv_L	0.45 ± 0.15	0.53 ± 0.14(0.45) *	0.97 ± 0.81	0.77 ± 0.85(1.19) *	2.57
	OpticNrv_R	0.44 ±0.14	0.52 ± 0.13(0.44) *	1.11 ± 1.24	0.80 ± 0.83(1.34) *	2.57
	Parotid_L	0.71 ±0.10	0.79 ± 0.09(0.75) *	2.02 ± 0.95	1.30 ± 0.62(1.68) *	3
	Parotid_R	0.71 ± 0.09	0.80 ± 0.06(0.76) *	2.11 ±0.76	1.26 ± 0.43(1.56) *	3
	Pituitary	0.38 ± 0.18	0.54 ± 0.15	1.07 ± 0.59	0.87 ± 0.54	3
4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
			(0.41) *		(1.29) *
	SpinalCord	0.66 ± 0.14	0.65 ± 0.16(0.59) *	0.81 ±0.33	0.73 ± 0.41(0.88) *	2.86
	LN_Neck_IA	0.48 ± 0.13	0.60 ± 0.14(0.44) *	1.05 ± 1.51	0.47 ± 0.45(1.81) *	2.75
	LN_Neck_IB_L	0.70 ±0.05	0.79 ± 0.04(0.73) *	1.30 ± 0.47	0.73 ± 0.24(1.16) *	2.75
	LN_Neck_IB_R	0.68 ±0.06	0.79 ±0.05(0.72) *	1.41 ± 0.51	0.73 ± 0.20(1.19) *	2.75
	LN_Neck_IIA_L	0.64 ± 0.04	0.75 ± 0.05(0.70) *	2.02 ± 0.54	1.54 ± 0.44(2.09) *	2.25
	LN_Neck_IIA_R	0.60 ± 0.08	0.76 ± 0.04(0.69) *	2.24 ± 0.76	1.41 ±0.49(2.15) *	2.25
	LN_Neck_IIB_L	0.68 ± 0.11	0.80 ± 0.06(0.68) *	0.95 ± 0.49	0.63 ± 0.31(1.12) *	3
	LN_Neck_IIB_R	0.68 ± 0.09	0.80 ± 0.06(0.70) *	1.19 ± 0.64	0.58 ± 0.15(1.14) *	3
	LN_Neck_III_L	0.54 ± 0.12	0.75 ± 0.07(0.63) *	1.53 ± 0.60	0.92 ± 0.44(1.51) *	3
	LN_Neck_III_R	0.57 ± 0.12	0.75 ± 0.07(0.63) *	1.57 ± 0.61	0.99 ± 0.37(1.57) *	3
	LN_Neck_IV_L	0.58 ± 0.08	0.69 ± 0.08(0.59) *	1.62 ± 0.47	1.13 ± 0.37(1.63) *	2.75
	LN_Neck_IV_R	0.55 ± 0.11	0.71 ± 0.09(0.58) *	1.87 ± 0.75	1.06 ± 0.33(1.77) *	2.75
	LN_Neck_V_L	0.53 ± 0.11	0.58 ± 0.09(0.45) *	1.43 ± 0.82	1.13 ± 0.59(2.02) *	3
	LN_Neck_V_R	0.50 ± 0.10	0.58 ± 0.11(0.44) *	2.03 ± 1.66	1.43 ± 0.98(3.18) *	3
	LN_Neck_VIA	0.34 ± 0.09	0.36 ± 0.11(0.24) *	1.20 ± 0.55	0.80 ± 0.35(1.33) *	2.75
	LN_Retropharynx_L	0.22 ± 0.07	0.28 ±0.10(0.19) *	1.44 ± 0.87	1.54 ± 1.47(2.93) *	2.75
	LN_Retropharynx_R	0.21 ± 0.07	0.28 ± 0.09(0.18) *	1.64 ± 0.93	1.49 ± 1.36(2.82) *	2.75
	LN_Retrostyloid_L	0.57 ± 0.10	0.64 ± 0.09(0.53) *	1.58 ± 0.75	1.23 ± 0.48(1.96) *	2.75
	LN_Retrostyloid_R	0.56 ± 0.11	0.66 ±0.11(0.53) *	1.59 ± 0.74	1.13 ± 0.66(1.95) *	2.75
Thorax	BrachialPlex_L	0.28 ± 0.14	0.38 ± 0.14(0.26) *	2.96 ± 1.79	2.94 ± 1.84(4.49) *	3
	BrachialPlex_R	0.28 ± 0.11	0.37 ± 0.16(0.24) *	3.37 ± 2.27	3.28 ± 2.60(5.51)	3
4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
	Breast_L	0.74 ±0.11	0.76 ± 0.15(0.66) *	4.86 ± 3.45	3.64 ± 1.85(5.65) *	2.8
	Breast_R	0.76 ± 0.12	0.78 ± 0.15(0.67) *	4.02 ± 1.70	3.45 ± 1.51(4.66) *	2.6
	Bronchus	0.60 ± 0.17	0.66 ± 0.13(0.55) *	2.18 ± 1.45	1.90 ± 1.22(2.78) *	2.6
	Carina	0.36 ± 0.18	0.49 ± 0.12(0.40) *	1.27 ± 0.55	1.03 ± 0.47(1.33) *	2.4
	Cricoid	0.02 ± 0.04	0.04 ± 0.05 (-0.01) *	4.64 ± 1.54	5.71 ± 1.24(7.05)	2.4
	Esophagus	0.48 ± 0.16	0.70 ± 0.15(0.64) *	2.49 ± 2.48	0.97 ± 0.54(1.56) *	2.8
	Glnd_Thyroid	0.46 ± 0.18	0.65 ± 0.17(0.54) *	2.92 ± 2.60	1.75 ± 1.78(3.19) *	2.75
	GreatVes	0.70 ± 0.08	0.74 ±0.10(0.65) *	3.37 ± 1.42	2.67 ± 1.73(4.14) *	3
	Heart	0.88 ± 0.08	0.90 ± 0.09(0.87) *	3.39 ± 1.91	2.55 ± 1.40(3.06) *	3
	Humerus_Head_L	0.95 ± 0.02	0.95 ± 0.02(0.94) *†	0.40 ± 0.23	0.40 ± 0.31(0.63) *	2.8
	Humerus_Head_R	0.93 ± 0.09	0.96 ± 0.02(0.90) *†	0.82 ± 2.37	0.31 ± 0.26(1.81) *	2.8
	Kidney_L	0.74 ±0.18	0.92 ± 0.05(0.85) *	4.25 ± 3.38	0.94 ± 0.80(2.27) *	3
	Kidney_R	0.74 ± 0.18	0.91 ± 0.07(0.84) *	3.77 ± 2.28	0.98 ± 0.66(1.91) *	3
	Larynx	0.45 ± 0.21	0.52 ± 0.14(0.44) *	3.13 ± 1.18	3.06 ± 1.08(3.59) *	2.4
	Liver	0.85 ± 0.11	0.93 ± 0.06(0.89) *	5.30 ± 4.79	2.00 ± 1.79(3.54) *	3
	Lung_L	0.95 ± 0.02	0.96 ± 0.02(0.95) *	0.90 ± 0.39	0.77 ± 0.37(0.90) *	3
	Lung_R	0.95 ± 0.03	0.96 ± 0.02(0.95) *	1.11 ±0.58	0.89 ± 0.43(1.07) *	3
	Musc_Constrict	0.41 ±0.16	0.45 ± 0.16(0.33) *	2.22 ± 1.86	2.07 ± 1.52(3.11) *	2
	Pancreas	0.17 ±0.19	0.41 ±0.24(0.24) *	15.18 ±18.92	8.68 ± 11.12(22.23)	2.25
	SpinalCord	0.66 ± 0.16	0.66 ± 0.16(0.62) *	1.47 ± 0.88	1.41 ±0.63(1.62) *	2.75
	Stomach	0.46 ±0.21	0.79 ± 0.19(0.70) *	10.47 ± 6.72	2.33 ± 2.12(4.62)	3
	Trachea	0.67 ± 0.17	0.74 ±0.16	1.22 ± 0.61	0.88 ± 0.54	3
4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
			(0.65) *		(1.17) *
	LN_Ax_L1_L	0.59 ± 0.09	0.65 ± 0.11(0.53) *	2.73 ± 0.81	2.58 ± 1.17(3.90) *	3
	LN_Ax_L1_R	0.52 ± 0.12	0.58 ± 0.14(0.46) *	3.57 ± 1.31	3.19 ± 1.61(4.80) *	3
	LN_Ax_L2_L	0.58 ± 0.16	0.63 ± 0.16(0.50) *	2.56 ± 1.37	2.10 ± 0.96(3.12) *	2.67
	LN_Ax_L2_R	0.55 ± 0.20	0.60 ± 0.20(0.46) *	2.88 ± 1.45	2.70 ± 1.77(3.87) *	2.67
	LN_Ax_L3_L	0.55 ± 0.17	0.61 ± 0.19(0.46) *	2.33 ± 1.38	2.15 ± 1.52(3.36) *	3
	LN_Ax_L3_R	0.46 ± 0.16	0.50 ± 0.18(0.36) *	2.82 ± 1.49	2.53 ± 1.41(3.90) *	3
	LN_IMN_L	0.17 ± 0.11	0.37 ± 0.16(0.20) *	2.66 ± 1.05	1.63 ± 0.96(2.93) *	2.67
	LN_IMN_R	0.24 ± 0.16	0.48 ± 0.19(0.33) *	2.55 ± 1.84	1.55 ± 1.60(2.99) *	2.67
	LN_Sclav_L	0.60 ± 0.15	0.67 ± 0.15(0.53) *	2.18 ± 0.72	1.87 ± 0.89(2.64) *	2.67
	LN_Sclav_R	0.48 ± 0.09	0.55 ± 0.10(0.44) *	2.89 ± 0.88	2.60 ± 0.85(3.54) *	2.67
Whole BodyPhysiological UptakeOrgans	Bone	0.76 ± 0.08	0.87 ± 0.05(0.75) *	3.80 ± 2.88	0.91 ± 1.02(1.87) *	3
	Bowel	0.46 ± 0.14	0.74 ± 0.10(0.62) *	1.32 ± 1.01	0.48 ± 0.13(3.32)	3
	BowelBag	0.59 ± 0.14	0.75 ± 0.15(0.68) *	10.57 ± 5.08	7.69 ± 5.07(12.61)	3
	Brain	0.97 ± 0.01	0.97 ± 0.03(0.96) *	18.17 ± 5.89	17.18 ± 5.24(20.30)	3
	Cavity_Oral	0.77 ± 0.13	0.78 ± 0.12(0.68) *	0.69 ± 0.37	0.91 ± 1.17(1.32) *	3
	Glnd_Lacrimal_L	0.23 ± 0.17	0.37 ± 0.16(0.24) *	3.18 ± 1.96	3.19 ± 1.66(4.56) *	3
	Glnd_Lacrimal_R	0.24 ± 0.16	0.46 ± 0.14(0.34) *	0.88 ± 0.51	0.72 ± 0.43(1.13) *	3
	Glnd_Submand_L	0.58 ± 0.11	0.79 ± 0.06(0.72) *	0.74 ± 0.39	0.81 ± 0.79(1.36) *	3
	Glnd_Submand_R	0.55 ± 0.16	0.77 ± 0.06(0.68) *	1.65 ± 0.53	0.81 ± 0.35(1.14) *	3
	Heart	0.89 ± 0.04	0.91 ± 0.04	1.83 ± 0.90	0.81 ± 0.38	3
4.1.0 CTModel:	Structure:	DiceMIM Atlas	DiceContourProtégéAl	MDAMIM Atlas	MDAContourProtégéAl	ExternalEvaluationScore
			(0.87) *		(1.38) *
	Kidney_L	0.72 ± 0.17	0.93 ± 0.04(0.84) *	3.10 ± 0.84	2.65 ± 0.93(3.42) *	3
	Kidney_R	0.73 ± 0.19	0.92 ± 0.07(0.82) *	3.76 ± 2.43	0.90 ± 0.51(2.14) *	3
	Liver	0.84 ± 0.12	0.93 ± 0.07(0.87) *	3.74 ± 2.91	0.85 ± 0.44(2.34) *	3
	LN_Iliac	0.63 ± 0.04	0.71 ± 0.03(0.68) *	5.28 ± 3.59	2.26 ± 3.82(4.41) *	3
	Parotid_L	0.71 ± 0.09	0.81 ± 0.05(0.77) *	2.59 ± 0.56	1.59 ± 0.33(1.97) *	3
	Parotid_R	0.71 ± 0.09	0.82 ± 0.05(0.78) *	1.97 ± 0.65	1.30 ± 0.47(1.62) *	3
	Prostate	0.71 ± 0.14	0.85 ± 0.05(0.76) *	2.08 ± 0.71	1.34 ± 0.56(1.70) *	3
	Spleen	0.72 ± 0.10	0.95 ± 0.01(0.87) *	3.21 ± 1.54	1.55 ± 0.61(2.53) *	3

Table 2: DICE, MDA and External Evaluation Score Comparison Per Structure

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

Image /page/13/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim SOFTWARE" in black, with "mim" in a larger font than "SOFTWARE".

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

Image /page/14/Picture/0 description: The image is a logo for MIM Software. The logo consists of a gray square overlapping a red square with a white circle in the middle. To the right of the squares is the text "mim SOFTWARE" in black font. The word "mim" is in a larger font than the word "SOFTWARE".

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

Image /page/15/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a stylized black font, with the word "SOFTWARE" in smaller black letters below it. The logo is clean and modern, with a focus on simplicity and visual appeal.

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

Image /page/16/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a sans-serif font, with the word "SOFTWARE" below it in a smaller font.

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

Image /page/17/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle cut out of the red square. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it. The logo is simple and modern, and the colors are eye-catching.

Mean ± Std Dice coefficient (lower 95th percentile confidence bound based on normal distribution in parentheses) * Equivalence demonstrated at p=0.05 significance level between Contour ProtégéAl and MIM Atlas † Comparisons for both atlas and Contour ProtégéAI calculated only on axial slices that contained the ground truth.

Additionally, preliminary user evaluation conducted as part of testing demonstrated that Contour ProtégéAl yields comparable time-saving functionality when creating contours as other commercially available automatic segmentation products.

4.1.0 CT Models:	MIM Atlas	Contour ProtégéAl
Head and Neck	38.69 ± 33.36	28.61 ± 29.59 (31.61) *
Thorax	89.24 ± 82.73	65.44 ± 68.85 (72.54) *
Whole Body -Physiological UptakeOrgans	138.06 ± 142.42	98.20 ± 127.11 (118.75) *

Table 3: 4.1.0 CT models cumulative APL in mm

Mean ± Std APL mm (upper 95th percentile confidence bound based on normal distribution in parentheses) * Equivalence demonstrated at p=0.05 significance level between Contour ProtégéAl and MIM Atlas

4.1.0 CT Models:	Structure:	Relevant FOV	Whole Body CT
Head and Neck	Bone_Mandible	100	100
	BrachialPlex_L	100	91
	BrachialPlex_R	100	95
4.1.0 CT Models:	Structure:	Relevant FOV	Whole Body CT
	Brain	100	100
	Brainstem	100	100
	Cavity_Oral	100	100
	Cochlea_L	95	95
	Cochlea_R	96	95
	Eye_L	100	100
	Eye_R	100	100
	Glnd_Lacrimal_L	98	100
	Glnd_Lacrimal_R	100	100
	Glnd_Submand_L	100	100
	Glnd_Submand_R	100	100
	Glnd_Thyroid	98	95
	Lens_L	97	100
	Lens_R	97	95
	Lips	100	95
	OpticChiasm	80	91
	OpticNrv_L	99	100
	OpticNrv_R	99	100
	Parotid_L	99	100
	Parotid_R	100	100
	Pituitary	100	86
	SpinalCord	99	100
	LN_Neck_IA	100	100
	LN_Neck_IB_L	100	100
	LN_Neck_IB_R	100	100
	LN_Neck_IIA_L	100	100
	LN_Neck_IIA_R	100	95
	LN_Neck_IIB_L	100	100
	LN_Neck_IIB_R	100	95
	LN_Neck_III_L	100	100
4.1.0 CT Models:	Structure:	Relevant FOV	Whole Body CT
	LN_Neck_III_R	100	100
	LN_Neck_IV_L	100	100
	LN_Neck_IV_R	100	95
	LN_Neck_V_L	100	100
	LN_Neck_V_R	100	91
	LN_Neck_VIA	100	100
	LN_Retropharynx_L	100	100
	LN_Retropharynx_R	95	100
	LN_Retrostyloid_L	100	100
	LN_Retrostyloid_R	100	100
Thorax	BrachialPlex_L	100	100
	BrachialPlex_R	100	100
	Breast_L	100	100
	Breast_R	96	91
	Bronchus	100	100
	Carina	98	100
	Cricoid	67	100
	Esophagus	100	100
	Glnd_Thyroid	100	100
	GreatVes	100	100
	Heart	100	100
	Humerus_Head_L	100	95
	Humerus_Head_R	100	100
	Kidney_L	97	91
	Kidney_R	97	95
	Larynx	99	95
	Liver	100	100
	Lung_L	100	100
	Lung_R	100	100
	Musc_Constrict	100	91
4.1.0 CT Models:	Structure:	Relevant FOV	Whole Body CT
	Pancreas	54	91
	SpinalCord	100	100
	Stomach	100	100
	Trachea	99	100
	LN_Ax_L1_L	100	100
	LN_Ax_L1_R	100	100
	LN_Ax_L2_L	100	100
	LN_Ax_L2_R	100	100
	LN_Ax_L3_L	100	100
	LN_Ax_L3_R	100	100
	LN_IMN_L	100	100
	LN_IMN_R	100	100
	LN_Sclav_L	100	100
	LN_Sclav_R	100	100
Whole Body -Physiological UptakeOrgans	Bladder	N/A	95
	Bone	N/A	100
	Bowel	N/A	100
	BowelBag	N/A	100
	Brain	N/A	100
	Cavity_Oral	N/A	100
	Glnd_Lacrimal_L	N/A	100
	Glnd_Lacrimal_R	N/A	100
	Glnd_Submand_L	N/A	100
	Glnd_Submand_R	N/A	100
	Heart	N/A	100
	Kidney_L	N/A	95
	Kidney_R	N/A	100
	Liver	N/A	100
	LN_Iliac	N/A	64
4.1.0 CT Models:	Structure:	Relevant FOV	Whole Body CT
	Parotid_L	N/A	100
	Parotid_R	N/A	100
	Prostate	N/A	100
	Spleen	N/A	100

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

Image /page/18/Picture/0 description: The image shows the logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font. Below the text "mim" is the text "SOFTWARE" in a smaller, sans-serif font.

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

Image /page/19/Picture/0 description: The image is a logo for MIM Software. The logo consists of two overlapping rounded squares, one gray and one red, with a white circle where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it. The logo is clean and modern, with a simple color palette.

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

Image /page/20/Picture/0 description: The image is a logo for MIM Software. The logo consists of two overlapping squares, one gray and one red, with a white circle in the center where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font. Below the text "mim" is the word "SOFTWARE" in a smaller, sans-serif font.

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

Image /page/21/Picture/0 description: The image shows the logo for MIM Software. The logo consists of a red square with rounded corners, partially covered by a gray square with rounded corners. A white circle is visible where the two squares overlap. To the right of the squares, the text "mim" is written in a bold, sans-serif font, with the word "SOFTWARE" written in a smaller font below it.

Percentage of images that were successfully localized by Contour ProtégéAl. N/A (not applicable) refers to models which the relevant FOV is a Whole Body CT.

Known Limitations and Biases:

Contour ProtégéAl can produce incorrect or implausible segmentations when the underlying anatomy is in the field of view of the scan but not clearly discernable due to image quality, noise, or the generally low contrast of some structures. This can occur in any situation where the organ at risk is not clearly discernable in the image, but has been observed for submandibular glands, optic nerves, and optic chiasm, in particular.

While both images with and without IV contrast are represented in the training set for Contour ProtégéAl, the effect of iodinated contrast can vary due to patient weight, contrast dosage, and time since injection. In cases where there is unusually intense brain enhancement, the posterior boundary of the brain can be incorrectly segmented.

The age breakdown of the training data, where patient age was available, was predominantly in the 40-60 and 60+ age ranges. While this is appropriate to the intended patient population, only a small proportion of testing and training data was for patients under 40, so more intensive review may be warranted for younger patients.

Where patient sex was available, the ratio of male to female patients in the training set was roughly 2:1. The testing data was chosen with a more even ratio (about 0.82:1) to establish applicability of the model to both.

Conclusion

Based on the Discussion and Testing and Performance Data above, the proposed device is determined to be as safe and effective as its predicate device. Contour ProtégéAl 510 K223774. In addition, the proposed device performs as well as the reference predicate device. MIM 4.1 SEASTAR (tradename MIM Maestro) K071964.

References

1 Vaassen, F. et al. Evaluation of measures for assessing of automatic organ-at-risk segmentation in radiotherapy. Physics and Imaging in Radiation Oncology 13, 1-6 (2020).

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).