(45 days)
Yes
The intended use and device description explicitly state the use of "machine-learning algorithms" for creating contours and segmenting structures. The document also mentions training and testing neural network models.
No.
The device creates contours and segments normal structures, aiding therapy and treatment planning, but it does not directly treat or diagnose a disease state. It is a tool for medical professionals to process images.
No
The device is described as a tool to "assist in the automated processing of digital medical images" and specifically states its use for "creation of contours," "segmenting normal structures," and "transferring contours." It's an accessory to MIM software, requiring human review and editing of its results. This indicates it is for image processing and analysis, providing input for diagnostic or treatment planning, but not directly generating a diagnosis itself.
Yes
The device is described as an accessory to MIM software that operates on standard computer systems (Windows, Mac, Linux) and is deployed either remotely or locally. It performs image processing and contour creation using machine learning, which are software functions. There is no mention of dedicated hardware components included with the device itself.
Based on the provided information, this device is NOT an In Vitro Diagnostic (IVD).
Here's why:
- IVDs are used to examine specimens derived from the human body. The intended use and device description clearly state that Contour ProtégéAI processes digital medical images (CT and MR). It does not analyze blood, tissue, urine, or any other biological sample.
- The purpose of IVDs is to provide information for diagnosis, monitoring, or screening. While Contour ProtégéAI assists in image processing for applications like quantitative analysis and aiding adaptive therapy, its primary function is image segmentation and contour creation, not the direct analysis of biological specimens for diagnostic purposes.
The device is an image processing tool that uses AI to assist trained medical professionals in analyzing medical images. This falls under the category of medical imaging software or a medical image analysis device, not an IVD.
No
The letter does not explicitly state that the FDA has reviewed, approved, or cleared a PCCP for this specific device.
Intended Use / Indications for Use
For Intended Use: Contour ProtégéAl is an accessory to MIM software. It includes processing components to allow the contouring of anatomical structures using machine-learning-based algorithms automatically.
Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAl.
Contour ProtégéAl is not intended to detect or contour lesions.
For Indications for Use: 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 ProtégéAl 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 normal structures across a variety of CT anatomical locations.
· And segmenting normal structures of the prostate, seminal vesicles, and urethra within T2-weighted MR images.
Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAI.
Product codes (comma separated list FDA assigned to the subject device)
QKB
Device Description
Contour ProtégéAl 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.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
CT and MR
Anatomical Site
Across a variety of CT anatomical locations, prostate, seminal vesicles, urethra. Specific structures include: A_Aorta_Desc, Bladder, Bone, Bone_Mandible, Bowel, Bowel_Large, Bowel_Small, BrachialPlex_L, BrachialPlex_R, Brain, Brainstem, Breast_L, Breast_R, Bronchus, Carina, CaudaEquina, Cavity_Oral, Cochlea_L, Cochlea_R, Colon_Sigmoid, Esophagus, Eye_L, Eye_R, Femur_Head_L, Femur_Head_R, Femur_L, Femur_R, Genitals, GInd_Lacrimal_L, GInd_Lacrimal_R, GInd_Submand_L, Glnd_Submand_R, Glnd_Thyroid, GreatVes, Heart, Humerus_Head_L, Humerus_Head_R, Kidney_L, Kidney_R, Larynx, Lens_L, Lens_R, Lips, Liver, LN_Pelvic, Lung_L, Lung_R, Musc_Constrict, OpticChiasm, OpticNrv_L, OpticNrv_R, Parotid_L, Parotid_R, PenileBulb, Pituitary, Prostate, Rectum, SeminalVes, Spinal_Cord, Spleen, Stomach, Trachea.
Indicated Patient Age Range
Adults at various ages.
Intended User / Care Setting
Trained medical professionals.
Description of the training set, sample size, data source, and annotation protocol
A total of 4061 CT images from 31 clinical sites across multiple continents (Australia, France, Hong Kong, and the USA) was gathered for the training of the final neural network models. Models were trained using images of adults at various ages. No ethnicities or genders were excluded from training, with the exception of the training pool for the prostate model, for which only subjects with male anatomy were used. The ground-truth segmentations used for both training and validation were generated by a trained user (typically, a dosimetrist or radiologist) that are then reviewed and approved by a supervising physician (typically, a radiation oncologist or a radiologist) and sent back for re-segmentation and re-review as necessary. Series that were non-axial, had slices thinner than 0.5mm, or had non-Fan Beam or mV acquisitions were excluded.
Description of the test set, sample size, data source, and annotation protocol
The models were evaluated on the test subjects from a pool of 739 independent images gathered from 12 institutions. The ground-truth segmentations used for validation were generated by a trained user (typically, a dosimetrist or radiologist) that are then reviewed and approved by a supervising physician (typically, a radiation oncologist or a radiologist) and sent back for re-segmentation and re-review as necessary. 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.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Non-inferiority testing was used to compare the proposed Contour ProtégéAl device to Atlases created from the MIM Maestro reference device. The new 3.0.0 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. The models were evaluated on 739 independent images from 12 institutions. The Dice coefficient was calculated for each structure and aggregated over all patients. 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 MM 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. Key results showed improved or equivalent Dice coefficients for Contour ProtégéAI across a wide range of anatomical structures compared to MIM Atlas.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Dice coefficient (mean ± Std) and lower 95th percentile confidence bound.
Predicate Device(s): If the device was cleared using the 510(k) pathway, identify the Predicate Device(s) K/DEN number used to claim substantial equivalence and list them here in a comma separated list exactly as they appear in the text. List the primary predicate first in the list.
Reference Device(s): Identify the Reference Device(s) K/DEN number and list them here in a comma separated list exactly as they appear in the text.
Predetermined Change Control Plan (PCCP) - All Relevant Information for the subject device only (e.g. presence / absence, what scope was granted / cleared under the PCCP, any restrictions, etc).
Not Found
§ 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).
0
Image /page/0/Picture/0 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: K213976
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: December 30, 2021 Received: January 5, 2022
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 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
1
https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
Julie M. Sullivan, Ph.D. Assistant Director Nuclear Medicine and Radiation Therapy Branch Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known) K213976
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 normal structures across a variety of CT anatomical locations.
· And segmenting normal structures of the prostate, seminal vesicles, and urethra within T2-weighted MR images.
Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAI.
| 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
Image /page/3/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 letters "TM" are in superscript to the right of the word "SOFTWARE".
510(k) Summary
(The following information is in conformance with 21 CFR 807.92)
Submitter:
MIM Software Inc. 25800 Science Park Drive - Suite 180 Cleveland, OH 44122
Phone: 216-455-0600 216-455-0601 Fax:
Contact Person:
Lynn Hanigan
Date Summary Prepared: Feb 1, 2022
Device Name
Trade Name: Common Name: Regulation Number / Product Code: Classification Name:
Contour ProtégéAl Medical Imaging Software 21 CFR 892.2050 / Product Code QKB Medical Image management and processing system
Predicate Device
Contour ProtégéAl
MIM Software Inc.
Reference Device
K071964 MIM 4.1 SEASTAR (tradename MIM Maestro) MIMvista Corp.
Intended Use
Contour ProtégéAl is an accessory to MIM software. It includes processing components to allow the contouring of anatomical structures using machine-learning-based algorithms automatically.
Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAl.
Contour ProtégéAl is not intended to detect or contour lesions.
Indications for Use
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 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 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".
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 normal structures of the prostate, seminal vesicles, and urethra within T2weighted MR images.
Appropriate image visualization software must be used to review and, if necessary, edit results automatically generated by Contour ProtégéAl.
Device Description
Contour ProtégéAl 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 4061 CT images from 31 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 3.0.0 production models.
| Institution | Country | # of images |
|---|---|---|
| Institution 1 | USA | 22 |
| Institution 2 | USA | 157 |
| Institution 3 | USA | 105 |
| Institution 4 | Australia | 420 |
| Institution 5 | USA | 67 |
| Institution 6 | USA | 46 |
| Institution 7 | USA | 83 |
| Institution 8 | USA | 82 |
| Institution 9 | USA | 89 |
| Institution 10 | USA | 63 |
| Institution 11 | France | 40 |
| Institution 12 | USA | 116 |
| Institution 13 | Hong Kong | 394 |
| Institution 14 | USA | 73 |
| Institution 15 | USA | 230 |
CT data used to train the final production of the 3.0.0 CT models
5
Image /page/5/Picture/0 description: The image is a logo for MIM Software. The logo consists of a red square with rounded corners and a gray square with rounded corners overlapping each other. The word "mim" is written in black, bold letters to the right of the squares. Below the word "mim" is the word "SOFTWARE" in smaller, black letters.
| Institution | Country | # of images |
|---|---|---|
| Institution 16 | USA | 139 |
| Institution 17 | USA | 15 |
| Institution 18 | USA | 96 |
| Institution 19 | USA | 103 |
| Institution 20 | USA | 29 |
| Institution 21 | USA | 325 |
| Institution 22 | USA | 13 |
| Institution 23 | USA | 54 |
| Institution 24 | USA | 10 |
| Institution 25 | USA | 284 |
| Institution 26 | USA | 622 |
| Institution 27 | USA | 152 |
| Institution 28 | USA | 58 |
| Institution 29 | USA | 66 |
| Institution 30 | USA | 101 |
| Institution 31 | USA | 7 |
Substantial Equivalence
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
|--------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Clearance Dates | TBD | 10/20/2021 | 9/26/2007 |
| Intended Use | Contour ProtégéAl is an
accessory to MIM software
used for the contouring of
anatomical structures in
imaging data using machine-
learning-based algorithms
automatically. | Contour ProtégéAl is an
accessory to MIM software
used for the contouring of
anatomical structures in
imaging data using machine-
learning-based algorithms
automatically. | MIM 4.1 (SEASTAR)
software is intended
for trained medical
professionals
including, but not
limited to, radiologists,
oncologists,
physicians, medical |
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
| | Appropriate image
visualization software must be
used to review and, if
necessary, edit results
automatically generated by
Contour ProtégéAl.
Contour ProtégéAl is not
intended to detect or contour
lesions. | Appropriate image
visualization software must be
used to review and, if
necessary, edit results
automatically generated by
Contour ProtégéAl.
Contour ProtégéAl is not
intended to detect or contour
lesions. | technologists,
dosimetrists, and
physicists.
MIM 4.1 (SEASTAR)
is a medical image
and information
management system
that is intended to
receive, transmit,
store, retrieve, display,
print and process
digital medical
images, as well as
create, display and
print reports from
those images. The
medical modalities of
these medical imaging
systems include, but
are not limited to, CT,
MRI, CR, DX, MG,
US, SPECT, PET and
XA as supported by
ACR/NEMA DICOM
3.0.
MIM 4.1 (SEASTAR)
provides tools to
quickly create,
transform, and modify
contours for
applications including,
but not limited to,
quantitative analysis,
aiding adaptive
therapy, transferring
contours to radiation
therapy treatment
planning systems and
archiving contours for |
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
| | | | patient follow-up and
management. |
| 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 therapy
treatment planning
systems, and archiving
contours for patient follow-
up and management.
• Segmenting normal
structures across a variety
of CT anatomical
locations.
• And segmenting normal
structures of the prostate,
seminal vesicles, and | 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 therapy
treatment planning
systems, and archiving
contours for patient follow-
up and management.
• Segmenting normal
structures across a variety
of CT anatomical
locations.
• And segmenting normal
structures of the prostate,
seminal vesicles, and | MIM 4.1 (SEASTAR)
software is used by
trained medical
professionals as a tool
to aid in evaluation
and information
management of digital
medical images. The
medical image
modalities include, but
are not limited to, CT,
MRI, CR, DX, MG,
US, SPECT, PET and
XA as supported by
ACR/NEMA DICOM
3.0. MIM 4.1
(SEASTAR) assists in
the following
indications:
• Receive, transmit,
store, retrieve, display,
print, and process
medical images and
DICOM objects.
• Create, display and
print reports from
medical images.
• Registration, fusion
display, and review of
medical images for |
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
| | 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. | 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. | diagnosis, treatment
evaluation, and
treatment planning.
• Localization and
definition of objects
such as tumors and
normal tissues in
medical images.
• Creation,
transformation, and
modification of
contours for
applications including,
but not limited to,
quantitative analysis,
aiding adaptive
therapy, transferring
contours to radiation
therapy treatment
planning systems, and
archiving contours for
patient follow-up and
management. |
| Modalities | CT and MR | CT and MR | CT, MR, CR, DX, MG,
US, SPECT, PET and
XA |
| Atlas-Based
Segmentation | No | No | Yes |
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
| Automatically
Contour Imaging
Data Using
Machine-Learning | Yes | Yes | No |
| Operating
Platform | Server-based application
supporting
Linux-based OS
- and -
Local deployment on Windows
or Mac | Server-based application
supporting
Linux-based OS - and -
Local deployment on Windows
or Mac | Windows, Mac |
| Cloud-based
deployment | Yes | Yes | No |
| Locally deployed
(or installed) | Yes | Yes | No |
| ITEM | Contour ProtégéAl
(K213976) | Contour ProtégéAl
(K210632) | MIM 4.1 SEASTAR
[i.e., MIM Maestro]
(K071964) |
| Neural Network
Models included | (1.0.0 models)
Head and Neck CT
Prostate CT
Thorax CT
Liver CT
Prostate MR
(1.1.0 model)
Prostate MR
(2.0.0 models)
Head and Neck CT
Prostate CT
Thorax CT
Abdomen CT
Lungs and Liver CT
(3.0.0 models)
Head and Neck CT
Prostate CT
Thorax CT
Abdomen CT
Lungs and Liver CT
MRT Additional Structures CT
(which include:
Spleen
Pelvic Lymph Nodes
Descending Aorta
Bone) | (1.0.0 models)
Head and Neck CT
Prostate CT
Thorax CT
Liver CT
Prostate MR
(1.1.0 model)
Prostate MR
(2.0.0 models)
Head and Neck CT
Prostate CT
Thorax CT
Abdomen CT
Lungs and Liver CT | None |
6
Image /page/6/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 letters "TM" are in superscript to the right of the word "SOFTWARE".
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 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.
8
Image /page/8/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 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.
9
Image /page/9/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 bold, sans-serif font, with the word "SOFTWARE" in a smaller font 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 where they overlap. To the right of the squares is the text "mim" in a bold, sans-serif font, with the word "SOFTWARE" underneath in a smaller font. The letters in "mim" are all lowercase.
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 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.
Discussion
Changes within this submission include new CT 3.0.0 neural network models with additional contours. These changes differ when comparing to Contour ProtégéAl 510(k)210632. Non-inferiority testing was used to compare the proposed Contour ProtégéAl device to Atlases created from the MIM Maestro reference device.
Testing and Performance Data
For the proposed Contour ProtégéAl device, the new 3.0.0 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 4.061 images gathered from 31 clinical sites, from Australia, France, Hong Kong, and the USA. Models were trained using images of adults at various ages. No ethnicities or genders were excluded from training, with the exception of the training pool for the prostate model, for which only subjects with male anatomy were used. The models were then evaluated on the test subjects from a pool of 739 independent images gathered from 12 institutions.
The ground-truth segmentations used for both training and validation were generated by a trained user (typically, a dosimetrist or radiologist) that are then reviewed and approved by a supervising physician (typically, a radiation oncologist or a radiologist) and sent back for re-segmentation and re-review as necessary. The Dice coefficient was then calculated for each structure, and aggregated over all patients. 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.
With the MM Maestro atlas segmentation reference device, multiple Atlases were created over the test subjects. Each Atlas contained images of the same anatomical field of view from the same institution. Each structure appeared in one Atlas. For each patient in an Atlas, the Atlas was used to segment the structures in that patient. The test patient itself was excluded from this Atlas (leave-one-out analysis).
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 seqmentation reference device for each structure of each neural network model. Contour ProtégéAl results were equivalent or had better performance than the MM 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.
| Structure: | MIM Atlas | Contour ProtégéAl |
|---|---|---|
| A_Aorta_Desc | 0.73 ± 0.15 | 0.78 ± 0.07 (0.68) * |
| Bladder | 0.80 ± 0.12 | 0.94 ± 0.02 (0.86) * |
| Bone | 0.80 ± 0.03 | 0.83 ± 0.05 (0.76) * |
| Bone_Mandible | 0.79 ± 0.16 | 0.83 ± 0.04 (0.74) * |
| Structure: | MIM Atlas | Contour ProtégéAl |
| Bowel † | 0.60 ± 0.13 | 0.75 ± 0.07 (0.68) * |
| Bowel_Large | 0.15 ± 0.12 | 0.28 ± 0.20 (0.15) * |
| Bowel_Small | 0.29 ± 0.17 | 0.42 ± 0.19 (0.29) * |
| BrachialPlex_L | 0.32 ± 0.11 | 0.37 ± 0.13 (0.27) * |
| BrachialPlex_R | 0.38 ± 0.13 | 0.41 ± 0.10 (0.31) * |
| Brain | 0.97 ± 0.01 | 0.96 ± 0.01 (0.95) * |
| Brainstem | 0.77 ± 0.12 | 0.76 ± 0.12 (0.68) * |
| Breast_L | 0.81 ± 0.06 | 0.81 ± 0.06 (0.76) * |
| Breast_R | 0.83 ± 0.06 | 0.83 ± 0.06 (0.77) * |
| Bronchus | 0.57 ± 0.12 | 0.62 ± 0.11 (0.54) * |
| Carina | 0.54 ± 0.18 | 0.64 ± 0.17 (0.52) * |
| CaudaEquina | 0.74 ± 0.09 | 0.72 ± 0.06 (0.64) * |
| Cavity_Oral | 0.79 ± 0.10 | 0.81 ± 0.11 (0.73) * |
| Cochlea_L | 0.39 ± 0.15 | 0.41 ± 0.17 (0.30) * |
| Cochlea_R | 0.43 ± 0.15 | 0.46 ± 0.17 (0.34) * |
| Colon_Sigmoid | 0.08 ± 0.09 | 0.50 ± 0.19 (0.33) * |
| Esophagus | 0.43 ± 0.17 | 0.56 ± 0.19 (0.47) * |
| Eye_L | 0.83 ± 0.10 | 0.82 ± 0.06 (0.77) * |
| Eye_R | 0.81 ± 0.13 | 0.78 ± 0.06 (0.71) * |
| Femur_Head_L | 0.93 ± 0.04 | 0.90 ± 0.06 (0.86) * |
| Femur_Head_R | 0.93 ± 0.03 | 0.93 ± 0.03 (0.91) * |
| Femur_L | 0.96 ± 0.01 | 0.95 ± 0.01 (0.93) * |
| Femur_R | 0.96 ± 0.02 | 0.94 ± 0.01 (0.91) * |
| Genitals | 0.64 ± 0.11 | 0.68 ± 0.13 (0.53) * |
| GInd_Lacrimal_L | 0.29 ± 0.15 | 0.39 ± 0.20 (0.24) * |
| GInd_Lacrimal_R | 0.31 ± 0.15 | 0.38 ± 0.22 (0.23) * |
| GInd_Submand_L | 0.68 ± 0.10 | 0.78 ± 0.07 (0.71) * |
| Structure: | MIM Atlas | Contour ProtégéAl |
| Glnd_Submand_R | 0.67 ± 0.11 | 0.76 ± 0.06 (0.69) * |
| Glnd_Thyroid | 0.51 ± 0.14 | 0.57 ± 0.18 (0.44) * |
| GreatVes | 0.75 ± 0.06 | 0.71 ± 0.08 (0.65) * |
| Heart | 0.85 ± 0.08 | 0.89 ± 0.04 (0.86) * |
| Humerus_Head_L † | 0.88 ± 0.07 | 0.91 ± 0.04 (0.87) * |
| Humerus_Head_R † | 0.88 ± 0.09 | 0.91 ± 0.03 (0.85) * |
| Kidney_L | 0.76 ± 0.14 | 0.91 ± 0.03 (0.83) * |
| Kidney_R | 0.74 ± 0.18 | 0.89 ± 0.04 (0.80) * |
| Larynx | 0.52 ± 0.15 | 0.57 ± 0.18 (0.44) * |
| Lens_L | 0.30 ± 0.17 | 0.52 ± 0.10 (0.41) * |
| Lens_R | 0.36 ± 0.14 | 0.65 ± 0.09 (0.56) * |
| Lips | 0.39 ± 0.14 | 0.57 ± 0.18 (0.43) * |
| Liver | 0.84 ± 0.12 | 0.93 ± 0.04 (0.87) * |
| LN_Pelvic | 0.76 ± 0.03 | 0.80 ± 0.04 (0.77) * |
| Lung_L | 0.94 ± 0.03 | 0.95 ± 0.02 (0.93) * |
| Lung_R | 0.95 ± 0.02 | 0.95 ± 0.02 (0.94) * |
| Musc_Constrict | 0.44 ± 0.12 | 0.50 ± 0.17 (0.38) * |
| OpticChiasm | 0.34 ± 0.16 | 0.37 ± 0.17 (0.25) * |
| OpticNrv_L | 0.46 ± 0.12 | 0.52 ± 0.10 (0.44) * |
| OpticNrv_R | 0.50 ± 0.10 | 0.54 ± 0.09 (0.47) * |
| Parotid_L | 0.68 ± 0.13 | 0.81 ± 0.04 (0.74) * |
| Parotid_R | 0.71 ± 0.10 | 0.78 ± 0.05 (0.72) * |
| PenileBulb | 0.62 ± 0.12 | 0.65 ± 0.11 (0.56) * |
| Pituitary | 0.53 ± 0.15 | 0.56 ± 0.18 (0.43) * |
| Prostate | 0.71 ± 0.12 | 0.82 ± 0.06 (0.74) * |
| Rectum | 0.67 ± 0.14 | 0.76 ± 0.08 (0.67) * |
| SeminalVes | 0.58 ± 0.15 | 0.70 ± 0.08 (0.60) * |
| Structure: | MIM Atlas | Contour ProtégéAI |
| Spinal_Cord | 0.76 ± 0.10 | 0.82 ± 0.07 (0.78) * |
| Spleen | 0.78 ± 0.14 | 0.91 ± 0.07 (0.80) * |
| Stomach | 0.45 ± 0.20 | 0.79 ± 0.09 (0.69) * |
| Trachea | 0.77 ± 0.09 | 0.73 ± 0.07 (0.67) * |
Results over the validation set compared to the reference device are presented here:
12
Image /page/12/Picture/0 description: The image is a logo for MIM Software. The logo consists of a red square with rounded corners and a white circle in the lower left corner, partially covered by a gray square with rounded corners. To the right of the graphic is the text "MIM" in large, bold, black letters, with the word "SOFTWARE" in smaller black letters below.
25800 Science Park Drive - Suite 180 Cleveland, OH 44122 866-421-2536 www.mimsoftware.com
13
Image /page/13/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 in the red square. To the right of the squares is the text "MIM" in a bold, sans-serif font, with the word "SOFTWARE" below it in a smaller font. The logo is simple and modern, and the colors are eye-catching.
14
Image /page/14/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 large, bold, black letters, with the word "SOFTWARE" in smaller black letters below it. The logo is simple and modern, with a clean design.
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 ProtégéAI and MIM Atlas † Comparisons for both atlas and Contour ProtégéAI calculated only on axial slices that contained the ground truth.
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 K210632. In addition, the proposed device performs as well as the reference device, MIM 4.1 SEASTAR K071964.