(111 days)
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, transfering 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.
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.
Here's a breakdown of the acceptance criteria and study details for Contour ProtégéAI, based on the provided document:
Acceptance Criteria and Device Performance Study for Contour ProtégéAI
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria for Contour ProtégéAI were based on a non-inferiority study comparing its segmentation performance (measured by Dice coefficient) to a predicate device, MIM Maestro (K071964), specifically using atlases built from the same training data. The key acceptance criterion was:
Equivalence is defined such that the lower 95th percentile confidence bound of the Contour ProtégéAI segmentation is greater than 0.1 Dice lower than the mean MIM atlas segmentation reference device performance.
This translates to being either equivalent to or having better performance than the MIM Maestro atlas segmentation reference device. The acceptance was demonstrated at a p=0.05 significance level.
The table below summarizes the reported mean ± standard deviation Dice coefficients for both the MIM Atlas (predicate) and Contour ProtégéAI, along with the lower 95th percentile confidence bound for Contour ProtégéAI, for various anatomical structures across different CT models (4.0.0 CT Model). The asterisk (*) next to Contour ProtégéAI performance indicates that equivalence was demonstrated at p=0.05.
Note: The document presents a single large table for all structures and models. For clarity, a few representative examples from each CT Model are extracted below to illustrate the reported performance against the acceptance criteria. The full table from the document should be consulted for comprehensive results.
| 4.0.0 CT Model: | Structure: | MIM Atlas (Mean ± Std Dice) | Contour ProtégéAI (Mean ± Std Dice, Lower 95th Percentile Bound) | Acceptance Met? |
|---|---|---|---|---|
| Head and Neck | Bone_Mandible | 0.81 ± 0.07 | 0.85 ± 0.07 (0.82) * | Yes |
| Head and Neck | Brain | 0.97 ± 0.01 | 0.98 ± 0.01 (0.97) * | Yes |
| Head and Neck | SpinalCord | 0.66 ± 0.14 | 0.63 ± 0.16 (0.57) * | Yes |
| Thorax | Esophagus | 0.49 ± 0.16 | 0.70 ± 0.15 (0.65) * | Yes |
| Thorax | Heart | 0.88 ± 0.08 | 0.90 ± 0.07 (0.88) * | Yes |
| Thorax | Lung_L | 0.95 ± 0.02 | 0.96 ± 0.02 (0.96) * | Yes |
| Abdomen | Bladder | 0.72 ± 0.23 | 0.91 ± 0.12 (0.81) * | Yes |
| Abdomen | Liver | 0.84 ± 0.12 | 0.92 ± 0.08 (0.86) * | Yes |
| Pelvis | Prostate | 0.74 ± 0.12 | 0.85 ± 0.06 (0.82) * | Yes |
| Pelvis | Rectum | 0.63 ± 0.18 | 0.83 ± 0.11 (0.79) * | Yes |
| SurePlan MRT | Bone | 0.76 ± 0.08 | 0.87 ± 0.05 (0.74) * | Yes |
| SurePlan MRT | Spleen | 0.72 ± 0.10 | 0.95 ± 0.03 (0.87) * | Yes |
2. Sample Size and Data Provenance for the Test Set
- Sample Size for Test Set: 819 independent images.
- Data Provenance: The images were gathered from 10 institutions. The document explicitly states that the test set institutions are "totally disjoint from the training datasets used to train each model." The countries of origin for the test set are not explicitly detailed, but since the training data included multiple countries (USA, Hong Kong, Australia), it's implied the test set could also be diverse. The data was retrospective clinical data, re-segmented for this specific purpose.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: The ground truth for the test set was established by "consultants (physicians and dosimetrists)." The exact number is not specified, but it implies a team. These initial segmentations were then "reviewed and corrected by a radiation oncologist." Finally, "Qualified staff at MIM Software (M.D. or licensed dosimetrists) then performed a final review and correction."
- Qualifications of Experts:
- Consultants: Physicians and dosimetrists.
- Review and Correction: Radiation oncologist.
- Final Review and Correction: Qualified staff at MIM Software (M.D. or licensed dosimetrists).
- All segmenters and reviewers were given "detailed instructions derived from relevant published clinical contouring guidelines" and instructed to ensure the "highest quality training data."
4. Adjudication Method for the Test Set
The adjudication method involved a multi-stage process:
- Initial Segmentation: Done by consultants (physicians and dosimetrists).
- First Review & Correction: By a radiation oncologist.
- Final Review & Correction: By qualified staff (M.D. or licensed dosimetrists) at MIM Software.
This indicates a sequential review process, rather than a specific (e.g., 2+1, 3+1) consensus model among peers at the same stage.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study was explicitly described comparing human readers with AI assistance versus without AI assistance. The study focused on the algorithm's standalone performance compared to an atlas-based predicate device, and a preliminary user evaluation for time-saving was mentioned, but not in the context of an MRMC study.
6. Standalone (Algorithm Only) Performance
Yes, a standalone (algorithm only) performance study was conducted. The Dice coefficient results presented in the table demonstrate the performance of the Contour ProtégéAI algorithm compared to the MIM Maestro atlas-based segmentation, without human intervention in the segmentation process being evaluated. The document explicitly states the "performance of both segmentation devices was measured by calculating the Dice score of the novel segmentations with the original ground-truth contours."
7. Type of Ground Truth Used
The ground truth used was expert consensus. It was established by a multi-stage review and correction process involving physicians, dosimetrists, a radiation oncologist, and qualified MIM Software staff who re-segmented images "specifically for this purpose, outside of clinical practice" and were instructed to adhere to "relevant published clinical contouring guidelines."
8. Sample Size for the Training Set
The training set consisted of 326 CT images gathered from 37 clinical sites across multiple countries (USA, Hong Kong, Australia).
9. How the Ground Truth for the Training Set was Established
The ground truth for the training set was established through a rigorous, multi-step expert review process:
- CT images (from clinical treatment plans) were re-segmented by consultants (physicians and dosimetrists).
- These initial segmentations were then reviewed and corrected by a radiation oncologist against the same standards and guidelines.
- A final review and correction was performed by qualified staff at MIM Software (M.D. or licensed dosimetrists).
All involved in ground truth establishment were given "detailed instructions derived from relevant published clinical contouring guidelines" and were explicitly asked "to spend additional time to ensure the highest quality training data" and to contour all specified structures "according to referenced standards."
{0}------------------------------------------------
April 6, 2023
Image /page/0/Picture/1 description: The image contains the logo of 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 is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
MIM Software Inc. % Lynn Hanigan Quality Assurance Director 25800 Science Park Drive Suite 180 CLEVELAND OH 44122
Re: K223774
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: March 9, 2023 Received: March 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 (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part
{1}------------------------------------------------
801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Digitally signed by Lora D. Lora D. Weidner -S Weidner -S Date: 2023.04.06
19:24:44 -04'00'
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
Enclosure
{2}------------------------------------------------
Indications for Use
510(k) Number (if known) K223774
Device Name
Contour ProtégéAI
Indications for Use (Describe)
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, transfering 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.
| 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) | Prescription Use (Part 21 CFR 801 Subpart D) | Over-The-Counter Use (21 CFR 801 Subpart C) |
| 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}------------------------------------------------
Image /page/3/Picture/1 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 bold, 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.
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
Dec 14, 2022
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 - | K213976 | Contour ProtégéAl | 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 ProtégéAI 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:
{4}------------------------------------------------
Image /page/4/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 cut out of it. 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.
- 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.
- . Seqmenting 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.
A total of 326 CT images from 37 clinical sites across multiple continents was gathered for the training of the final neural network models. The following table lists the data used for the training of the final production models.
| Institution | Country | # of images |
|---|---|---|
| Institution 1 | USA | 2 |
| Institution 2 | USA | 5 |
| Institution 3 | USA | 11 |
| Institution 4 | USA | 4 |
| Institution 5 | USA | 3 |
| Institution 6 | USA | 1 |
| Institution 7 | USA | 31 |
| Institution 8 | USA | 12 |
| Institution 9 | USA | 6 |
| Institution 10 | Hong Kong | 25 |
| Institution 11 | USA | 10 |
| Institution 12 | USA | 6 |
| Institution 13 | USA | 10 |
| Institution 14 | USA | 6 |
| Institution 15 | USA | 21 |
| Institution 16 | USA | 2 |
| CT data used to train the final production of the 4.0.0 CT models | |||||
|---|---|---|---|---|---|
{5}------------------------------------------------
Image /page/5/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.
| Institution | Country | # of images |
|---|---|---|
| Institution 17 | USA | 10 |
| Institution 18 | USA | 7 |
| Institution 19 | USA | 11 |
| Institution 20 | USA | 22 |
| Institution 21 | USA | 6 |
| Institution 22 | USA | 21 |
| Institution 23 | Australia | 15 |
| Institution 24 | USA | 10 |
| Institution 25 | USA | 11 |
| Institution 26 | USA | 10 |
| Institution 27 | USA | 2 |
| Institution 28 | USA | 1 |
| Institution 29 | USA | 7 |
| Institution 30 | USA | 6 |
| Institution 31 | USA | 4 |
| Institution 32 | USA | 1 |
| Institution 33 | USA | 2 |
| Institution 34 | USA | 2 |
| Institution 35 | USA | 6 |
| Institution 36 | USA | 14 |
| Institution 37 | USA | 3 |
Substantial Equivalence
| ITEM | Contour ProtégéAI(K# - TBD) | Contour ProtégéAI(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
|---|---|---|---|
| Clearance Dates | TBD | 02/03/2022 | 9/26/2007 |
| ITEM | Contour ProtégéAl(K# - TBD) | Contour ProtégéAl(K213976) | 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 imagevisualization software must beused to review and, ifnecessary, edit resultsautomatically generated byContour ProtégéAI.Contour ProtégéAl is notintended to detect or contourlesions. | Contour ProtégéAI is anaccessory to MIM softwareused for the contouring ofanatomical structures inimaging data using machine-learning-based algorithmsautomatically.Appropriate imagevisualization software must beused to review and, ifnecessary, edit resultsautomatically generated byContour ProtégéAI.Contour ProtégéAl is notintended to detect or contourlesions. | MIM 4.1 (SEASTAR)software is intendedfor trained medicalprofessionalsincluding, but notlimited to, radiologists,oncologists,physicians, medicaltechnologists,dosimetrists, andphysicists.MIM 4.1 (SEASTAR)is a medical imageand informationmanagement systemthat is intended toreceive, transmit,store, retrieve, display,print and processdigital medicalimages, as well ascreate, display andprint reports fromthose images. Themedical modalities ofthese medical imagingsystems include, butare not limited to, CT,MRI, CR, DX, MG,US, SPECT, PET andXA as supported byACR/NEMA DICOM3.0.MIM 4.1 (SEASTAR)provides tools toquickly create,transform, and modifycontours forapplications including,but not limited to,quantitative analysis,aiding adaptive |
| ITEM | Contour ProtégéAl(K# - TBD) | Contour ProtégéAl(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
| therapy, transferringcontours to radiationtherapy treatmentplanning systems andarchiving contours forpatient follow-up andmanagement. | |||
| Indications forUse | 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:• Creation of contours usingmachine-learningalgorithms for applicationsincluding, but not limitedto, quantitative analysis,aiding adaptive therapy,transferring contours toradiation therapy treatmentplanning systems, andarchiving contours forpatient follow-up andmanagement.• Segmenting normalstructures across a varietyof CT anatomicallocations.• And segmenting theprostate, the seminalvesicles, and the urethrawithin T2-weighted MRimages. | 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:• Creation of contours usingmachine-learningalgorithms for applicationsincluding, but not limitedto, quantitative analysis,aiding adaptive therapy,transferring contours toradiation therapytreatment planningsystems, and archivingcontours for patient follow-up and management.• Segmenting normalstructures across a varietyof CT anatomicallocations.• And segmenting normalstructures of the prostate,seminal vesicles, andurethra within T2-weightedMR images. | MIM 4.1 (SEASTAR)software is used bytrained medicalprofessionals as a toolto aid in evaluationand informationmanagement of digitalmedical images. Themedical imagemodalities include, butare not limited to, CT,MRI, CR, DX, MG,US, SPECT, PET and |
| ITEM | Contour ProtégéAl(K# - TBD) | Contour ProtégéAl(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
| Appropriate imagevisualization software must beused to review and, ifnecessary, edit resultsautomatically generated byContour ProtégéAI. | Appropriate imagevisualization software must beused to review and, ifnecessary, edit resultsautomatically generated byContour ProtégéAI. | evaluation, andtreatment planning.• Localization anddefinition of objectssuch as tumors andnormal tissues inmedical images.• Creation,transformation, andmodification ofcontours forapplications including,but not limited to,quantitative analysis,aiding adaptivetherapy, transferringcontours to radiationtherapy treatmentplanning systems, andarchiving contours forpatient follow-up andmanagement. | |
| Modalities | CT and MR | CT and MR | CT, MR, CR, DX, MG,US, SPECT, PET andXA |
| Atlas-BasedSegmentation | No | No | Yes |
| ITEM | Contour ProtégéAl(K# - TBD) | Contour ProtégéAl(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
| 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 | Yes |
| ITEM | Contour ProtégéAl(K# - TBD) | Contour ProtégéAl(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
| Previous NeuralNetwork Modelsincluded | (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 StructuresCT | (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 | None |
| ITEM | Contour Protégé Al(K# - TBD) | Contour Protégé Al(K213976) | MIM 4.1 SEASTAR[i.e., MIM Maestro](K071964) |
| New NeuralNetwork Modelsincluded | (4.0.0 models)Head and Neck CTThorax CTAbdomen CTPelvis CTSurePlan MRT 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 bold, sans-serif font. Below the text "mim" is the text "SOFTWARE" in a smaller, sans-serif font.
25800 Science Park Drive - Suite 180 Cleveland, OH 44122 866-421-2536 www.mimsoftware.com
{7}------------------------------------------------
Image /page/7/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 cut out of the intersection. To the right of the squares is the text "mim SOFTWARE" in black, with "SOFTWARE" in a smaller font size below "mim".
{8}------------------------------------------------
Image /page/8/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 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.
T
25800 Science Park Drive - Suite 180 Cleveland, OH 44122 866-421-2536 www.mimsoftware.com
{9}------------------------------------------------
Image /page/9/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 SOFTWARE" in a sans-serif font. The word "mim" is in a larger font size than the word "SOFTWARE".
{10}------------------------------------------------
Image /page/10/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 clean and modern, with a focus on simplicity and clarity.
25800 Science Park Drive - Suite 180 Cleveland, OH 44122 866-421-2536 www.mimsoftware.com
{11}------------------------------------------------
Image /page/11/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 word "mim" in a bold, sans-serif font, with the word "SOFTWARE" in a smaller font below it.
Discussion
Changes within this submission include new 4.0.0 CT neural network models with additional contours. These changes differ when comparing to Contour ProtégéAl 510(K)213976. 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
For the proposed Contour ProtégéAl device, the new 4.0.0 CT neural network models were trained on a pool of training data that did not include any patients from the same institution as the test subjects. This training data included 326 CT images gathered from 37 clinical sites across multiple countries. Models were trained using images of adults at various ages. No ethnicities or genders were excluded from training. The models were then evaluated on the test subjects from a pool of 819 independent images gathered from 10 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 guidelines were prepared for the dosimetrists. The initial seqmentations 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 and reviewers were instructed to spend
{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 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.
additional time to ensure the highest quality training data. In particular, the consultants were asked to contour all specified OAR structures on all images to 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 disjoint from the training datasets used to train each model in the Contour ProtégéAl device. The predicate MIM device was confiqured with Atlases built from the same training data used to train the models. We tested Contour ProtégéAl against the predicate device, and the goal of this testing is to show that it is equivalent or superior to the predicate. The performance of both segmentation devices was measured by calculating the Dice score of the novel segmentations with the original ground-truth contours. Any structure that ends up being statistically significantly worse than MIM atlas segmentation predicate device will be removed from the final model.
The mean and standard deviation Dice coefficients, along with the lower 95th percentile confidence bound, were calculated for both the proposed Contour ProtégéAl device and the MIM Maestro atlas segmentation 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.
| 4.0.0 CT Model: | Structure: | MIM Atlas | Contour ProtégéAI |
|---|---|---|---|
| Head and Neck | Bone_Mandible | 0.81 ± 0.07 | 0.85 ± 0.07 (0.82) * |
| Head and Neck | BrachialPlex_L | 0.17 ± 0.08 | 0.26 ± 0.10 (0.19) * |
| Head and Neck | BrachialPlex_R | 0.15 ± 0.07 | 0.25 ± 0.11 (0.16) * |
| Head and Neck | Brain | 0.97 ± 0.01 | 0.98 ± 0.01 (0.97) * |
| Head and Neck | Brainstem | 0.78 ± 0.09 | 0.82 ± 0.09 (0.78) * |
| Head and Neck | Cavity_Oral | 0.75 ± 0.14 | 0.77 ± 0.12 (0.69) * |
| Head and Neck | Cochlea_L | 0.19 ± 0.15 | 0.27 ± 0.17 (0.20) * |
| Head and Neck | Cochlea_R | 0.17 ± 0.15 | 0.29 ± 0.18 (0.21) * |
| Head and Neck | Eye_L | 0.80 ± 0.08 | 0.87 ± 0.06 (0.84) * |
| Head and Neck | Eye_R | 0.80 ± 0.10 | 0.87 ± 0.06 (0.83) * |
| Head and Neck | Glnd_Lacrimal_L | 0.22 ± 0.17 | 0.39 ± 0.17 (0.27) * |
| Head and Neck | Glnd_Lacrimal_R | 0.23 ± 0.16 | 0.43 ± 0.15 (0.32) * |
| Head and Neck | Glnd_Submand_L | 0.57 ± 0.13 | 0.77 ± 0.10 (0.69) * |
| Head and Neck | Glnd_Submand_R | 0.56 ± 0.16 | 0.77 ± 0.09 (0.68) * |
| 4.0.0 CT Model: | Structure: | MIM Atlas | Contour ProtégéAI |
| Glnd_Thyroid | 0.47 ± 0.18 | 0.71 ± 0.16 (0.59) * | |
| Lens_L | 0.22 ± 0.23 | 0.61 ± 0.17 (0.52) * | |
| Lens_R | 0.22 ± 0.22 | 0.63 ± 0.15 (0.54) * | |
| Lips | 0.38 ± 0.14 | 0.38 ± 0.14 (0.28) * | |
| OpticChiasm | 0.04 ± 0.07 | 0.12 ± 0.11 (0.08) * | |
| OpticNrv_L | 0.45 ± 0.15 | 0.53 ± 0.13 (0.46) * | |
| OpticNrv_R | 0.44 ± 0.14 | 0.52 ± 0.12 (0.45) * | |
| Parotid_L | 0.71 ± 0.10 | 0.80 ± 0.10 (0.75) * | |
| Parotid_R | 0.71 ± 0.09 | 0.80 ± 0.06 (0.77) * | |
| Pituitary | 0.38 ± 0.18 | 0.49 ± 0.15 (0.37) * | |
| SpinalCord | 0.66 ± 0.14 | 0.63 ± 0.16 (0.57) * | |
| Thorax | BrachialPlex_L | 0.28 ± 0.14 | 0.37 ± 0.13 (0.25) * |
| BrachialPlex_R | 0.28 ± 0.11 | 0.36 ± 0.16 (0.23) * | |
| Breast_L | 0.75 ± 0.10 | 0.74 ± 0.17 (0.65) * | |
| Breast_R | 0.76 ± 0.11 | 0.77 ± 0.10 (0.71) * | |
| Bronchus | 0.60 ± 0.17 | 0.66 ± 0.13 (0.56) * | |
| Carina | 0.39 ± 0.18 | 0.51 ± 0.13 (0.43) * | |
| Cricoid | 0.03 ± 0.05 | 0.03 ± 0.04 (-0.01) * | |
| Esophagus | 0.49 ± 0.16 | 0.70 ± 0.15 (0.65) * | |
| Glnd_Thyroid | 0.46 ± 0.18 | 0.67 ± 0.16 (0.57) * | |
| GreatVes | 0.70 ± 0.08 | 0.74 ± 0.10 (0.65) * | |
| Heart | 0.88 ± 0.08 | 0.90 ± 0.07 (0.88) * | |
| Humerus_Head_L | 0.95 ± 0.02 | 0.95 ± 0.02 (0.94) * † | |
| Humerus_Head_R | 0.93 ± 0.09 | 0.96 ± 0.02 (0.90) * † | |
| Kidney_L | 0.74 ± 0.18 | 0.92 ± 0.05 (0.85) * | |
| Kidney_R | 0.74 ± 0.19 | 0.91 ± 0.06 (0.84) * | |
| Larynx | 0.45 ± 0.21 | 0.50 ± 0.16 (0.42) * | |
| Liver | 0.85 ± 0.11 | 0.93 ± 0.06 (0.89) * | |
| 4.0.0 CT Model: | Structure: | MIM Atlas | Contour ProtégéAI |
| Lung_L | 0.95 ± 0.02 | 0.96 ± 0.02 (0.96) * | |
| Lung_R | 0.95 ± 0.03 | 0.96 ± 0.02 (0.96) * | |
| Musc_Constrict | 0.41 ± 0.16 | 0.47 ± 0.15 (0.37) * | |
| Pancreas | 0.17 ± 0.19 | 0.45 ± 0.22 (0.32) * | |
| SpinalCord | 0.67 ± 0.16 | 0.66 ± 0.16 (0.62) * | |
| Stomach | 0.46 ± 0.21 | 0.80 ± 0.16 (0.72) * | |
| Trachea | 0.67 ± 0.17 | 0.73 ± 0.17 (0.65) * | |
| Abdomen | Bladder | 0.72 ± 0.23 | 0.91 ± 0.12 (0.81) * |
| Bowel | 0.46 ± 0.14 | 0.73 ± 0.11 (0.61) * † | |
| BowelBag | 0.63 ± 0.08 | 0.68 ± 0.08 (0.62) * + | |
| CaudaEquina | 0.62 ± 0.15 | 0.66 ± 0.13 (0.55) * | |
| Kidney_L | 0.74 ± 0.17 | 0.93 ± 0.03 (0.84) * | |
| Kidney_R | 0.75 ± 0.18 | 0.92 ± 0.05 (0.82) * | |
| Liver | 0.84 ± 0.12 | 0.92 ± 0.08 (0.86) * | |
| SpinalCord | 0.60 ± 0.16 | 0.63 ± 0.13 (0.55) * | |
| Stomach | 0.49 ± 0.21 | 0.81 ± 0.11 (0.70) * | |
| Pelvis | Bladder | 0.73 ± 0.22 | 0.93 ± 0.11 (0.89) * |
| Bowel | 0.37 ± 0.15 | 0.52 ± 0.19 (0.41) * | |
| Colon_Sigmoid | 0.20 ± 0.17 | 0.60 ± 0.26 (0.48) * | |
| Femur_Head_L | 0.90 ± 0.08 | 0.93 ± 0.05 (0.91) * | |
| Femur_Head_R | 0.90 ± 0.08 | 0.93 ± 0.04 (0.91) * | |
| LN_Iliac | 0.63 ± 0.04 | 0.72 ± 0.03 (0.68) * | |
| PenileBulb | 0.59 ± 0.16 | 0.63 ± 0.16 (0.58) * | |
| Prostate | 0.74 ± 0.12 | 0.85 ± 0.06 (0.82) * | |
| Rectum | 0.63 ± 0.18 | 0.83 ± 0.11 (0.79) * | |
| Sacrum | 0.87 ± 0.01 | 0.92 ± 0.00 (0.87) * | |
| SeminalVes | 0.38 ± 0.27 | 0.68 ± 0.15 (0.61) * | |
| SurePlan MRT | Bone | 0.76 ± 0.08 | 0.87 ± 0.05 (0.74) * |
| 4.0.0 CT Model: | Structure: | MIM Atlas | Contour ProtégéAI |
| Glnd_Lacrimal_L | 0.23 ± 0.16 | 0.30 ± 0.22 (0.14) * | |
| Glnd_Lacrimal_R | 0.24 ± 0.16 | 0.33 ± 0.23 (0.17) * | |
| Glnd_Submand_L | 0.58 ± 0.11 | 0.77 ± 0.13 (0.68) * | |
| Glnd_Submand_R | 0.55 ± 0.16 | 0.77 ± 0.14 (0.65) * | |
| Glnd_Thyroid | 0.48 ± 0.18 | 0.61 ± 0.18 (0.48) * | |
| Kidney_L | 0.72 ± 0.18 | 0.89 ± 0.04 (0.79) * | |
| Kidney_R | 0.76 ± 0.17 | 0.89 ± 0.04 (0.80) * | |
| Liver | 0.85 ± 0.12 | 0.93 ± 0.07 (0.88) * | |
| Lung_L | 0.94 ± 0.03 | 0.95 ± 0.03 (0.92) * | |
| Lung_R | 0.94 ± 0.05 | 0.95 ± 0.04 (0.91) * | |
| Parotid_L | 0.70 ± 0.09 | 0.80 ± 0.05 (0.76) * | |
| Parotid_R | 0.71 ± 0.09 | 0.82 ± 0.05 (0.77) * | |
| Spleen | 0.72 ± 0.10 | 0.95 ± 0.03 (0.87) * |
Results over the validation set compared to the reference device are presented here:
{13}------------------------------------------------
Image /page/13/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 in the intersection. To the right of the squares is the text "mim" in a stylized font, with the word "SOFTWARE" underneath in a smaller font.
T
{14}------------------------------------------------
Image /page/14/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 bold, 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.
T
{15}------------------------------------------------
Image /page/15/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 smaller letters below it. The logo is simple and modern, with a focus on the company's name.
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 ProtégéA1 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.
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 K213976. In addition, the proposed device performs as well as the reference device, MIM 4.1 SEASTAR (tradename MIM Maestro) K071964.
§ 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).