(103 days)
Not Found
Yes.
The document explicitly states: "TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images" and "The device comprises an AI inference module". It further details that the AI inference module "consists of image preprocessing, deep learning neural networks, and postprocessing components".
No.
This device is a software tool intended to assist medical professionals in the detection and contouring of brain metastases for radiation therapy treatment planning, not to deliver therapy itself.
No.
The device is described as a software device intended to assist trained medical professionals by providing initial object contours on MR images to accelerate workflow for radiation therapy treatment planning. It explicitly states that it is an "adjunctive tool and not intended for replacing the users' current standard practice of manual contouring process" and that "The physician retains the ultimate responsibility for making the final diagnosis and treatment decision." This indicates it's a tool for treatment planning, not for diagnosing a condition.
Yes
The description explicitly states, "TAIMedImg DeepMets is a software device" and "The device comprises an AI inference module and a DICOM Radiotherapy Structure Sets (RTSS, or RTSTRUCT) converter module," with both modules described as software components utilizing deep learning neural networks. There is no mention of hardware components provided or required by the device itself beyond the existing infrastructure for receiving and viewing DICOM images, which is standard for medical imaging software.
No.
The device processes medical images (MRIs) to assist in radiation therapy treatment planning by providing contours of brain metastases. It does not perform tests on biological samples or provide diagnostic information from in vitro analysis, which is characteristic of IVDs.
No
The provided text does not contain any explicit language indicating that the FDA has reviewed, approved, or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning.
TAIMedImg DeepMets is intended only for patients with known (imaging diagnosed) brain metastases (BM) when cancer cells spread from primary site to the brain. It is not intended to be used with images of other brain tumors or other body parts. The software is intended for use with BM lesions with a diameter of ≥ 10 mm.
TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The software is an adjunctive tool and not intended for replacing the users' current standard practice of manual contouring process. All automatic output generated by the software shall be thoroughly reviewed by a trained medical professional prior to delivering any therapy or treatment. The physician retains the ultimate responsibility for making the final diagnosis and treatment decision.
TAIMedImg DeepMets is intended to be used by medical professionals trained in the use of the device.
Only DICOM images of adult patients are considered valid input. DeepMets does not support DICOM images of patients that have one of the following exclusions:
- (i) presence of prior craniotomy
- (ii) patients with clinical imaging diagnosis of brain tumors other than BM
- (iii) Images with patient motion: excessive motion leading to artifacts that make the scan technically inadequate
Medical professionals must finalize (confirm or modify) the contours generated by TAIMedImg DeepMets, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
Product codes
QKB, QIH
Device Description
TAIMedImg DeepMets is a software application system intended for use in the contouring (segmentation) of brain magnetic resonance (MR) images. The device comprises an AI inference module and a DICOM Radiotherapy Structure Sets (RTSS, or RTSTRUCT) converter module.
The AI inference module consists of image preprocessing, deep learning neural networks, and postprocessing components, and is intended to contour brain metastasis on the axial T1-weighted contrast-enhanced (T1WI+C) MR images. It utilizes deep learning neural networks to generate contours and annotations for the diagnosed brain metastases.
The DICOM RTSS converter module converts the contours, annotations, along with metadata, into a standard DICOM-RTSTRUCT file, making it compatible with radiotherapy treatment planning systems.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images
Anatomical Site
Brain
Indicated Patient Age Range
Only DICOM images of adult patients are considered valid input.
Intended User / Care Setting
Medical professionals trained in the use of the device.
Description of the training set, sample size, data source, and annotation protocol
The DeepMets model was initially trained on a retrospective dataset of 1,029 patients with brain metastases who underwent Gamma Knife radiosurgery, collected from a major medical center in Taiwan between 1993 and 2017. Further tuning was conducted using an additional dataset from 559 patients included in a nationwide healthcare database covering the years 2018 to 2019.
Description of the test set, sample size, data source, and annotation protocol
Standalone performance testing was conducted using an independent U.S. dataset consisting of 158 MRI scans from 158 patients with 289 measurable lesions (≥10 mm in diameter, as defined by RANO-BM criteria). The dataset included MRI scans from 16 imaging facilities, acquired using scanners from GE, Philips, Siemens, and Toshiba, with standardized parameters (axial T1WI+C with gadolinium-based contrast, slice thickness ≤ 5 mm, pixel size 0.3-1 mm, and 0-1 mm slice gap). The validation dataset was from the U.S., completely independent and not used in any stage of algorithm development.
The demographic distribution of the dataset:
Gender: 75 Female, 83 Male
Age: Adult, range from 41 to 92 years old; the average age is 66.65 years with a standard deviation of 9.72.
Ethnicity: 4 Not Hispanic or Latin, 154 Unknown
Race: 1 African American, 104 White, 53 Unknown
Note: due to anonymization, ethnicity and race information were not available for all cases.
Ground truth annotations were manually established based on consensus NRG/RTOG clinical guidelines by three clinically experienced radiologists/neuroradiologists. These annotations reflected established clinical segmentation standards for brain metastases and served as the reference standard for all performance evaluations.
Summary of Performance Studies
Study type: Standalone performance testing
Sample size: 158 patients with 289 measurable lesions
Key metrics and results:
Lesion-Wise Sensitivity (Se) (%): Mean 89.97, 95%CI (86.51, 93.43)
False-Positive Rate (FPR) (FPs/case): Mean 0.354, 95%CI (0.215, 0.481)
Dice Similarity Coefficient (DSC): Mean 0.70, 95%CI (0.67, 0.72)
Hausdorff Distance (HD) (mm): Mean 6.66, 95%CI (5.86, 7.41)
Centroid Distance (CD) (mm): Mean 1.75, 95%CI (1.33, 2.11)
Key results: Subgroup analysis demonstrated consistent Se and FPR across categories including sex, age, number of metastases, lesion size, MRI magnetic field strength, slice thickness, manufacturer, and imaging source. Slightly higher FPRs were noted in subjects older than 71 years (FPR: 0.568 FPs/case, Se: 92.19%), subjects imaged with 3T field strength (FPR: 0.509 FPs/case, Se:93.88%), subjects scanned using Philips MRI devices (FPR: 0.537 FPs/case, Se: 94.90%), and subjects with more than 15 lesions (FPR: 0.750 FPs/case, Se: 80.0%). The results demonstrate that DeepMets performs as expected.
Key Metrics
Lesion-Wise Sensitivity (Se) (%), False-Positive Rate (FPR) (FPs/case), Dice Similarity Coefficient (DSC), Hausdorff Distance (HD) (mm), Centroid Distance (CD) (mm).
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
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).
FDA 510(k) Clearance Letter - TAIMedImg DeepMets
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.07.05
May 28, 2025
Taiwan Medical Imaging Co., Ltd.
Paul Chang
Regulatory Affairs Staff
3F., No. 1, Fuxing 4th Rd., Qianzhen Dist.,
Kaohsiung City, 806611
Taiwan
Re: K250427
Trade/Device Name: TAIMedImg DeepMets
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical image management and processing system
Regulatory Class: Class II
Product Code: QKB, QIH
Dated: May 15, 2025
Received: May 15, 2025
Dear Paul Chang:
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.
Page 2
K250427 - Paul Chang Page 2
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 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 (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-reporting-combination-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.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
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-devices/medical-device-safety/medical-device-reporting-mdr-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/medical-devices/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-devices/device-advice-comprehensive-regulatory-
Page 3
K250427 - Paul Chang Page 3
assistance/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,
Lora D. Weidner, Ph.D.
Assistant Director
Radiation Therapy Team
DHT8B: Division of Radiologic Imaging
and Radiation Therapy Devices
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
Page 4
Indications for Use
Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K250427
Please provide the device trade name(s).
TAIMedImg DeepMets
Please provide your Indications for Use below.
TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning.
TAIMedImg DeepMets is intended only for patients with known (imaging diagnosed) brain metastases (BM) when cancer cells spread from primary site to the brain. It is not intended to be used with images of other brain tumors or other body parts. The software is intended for use with BM lesions with a diameter of ≥ 10 mm.
TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The software is an adjunctive tool and not intended for replacing the users' current standard practice of manual contouring process. All automatic output generated by the software shall be thoroughly reviewed by a trained medical professional prior to delivering any therapy or treatment. The physician retains the ultimate responsibility for making the final diagnosis and treatment decision.
TAIMedImg DeepMets is intended to be used by medical professionals trained in the use of the device.
Only DICOM images of adult patients are considered valid input. DeepMets does not support DICOM images of patients that have one of the following exclusions:
- (i) presence of prior craniotomy
- (ii) patients with clinical imaging diagnosis of brain tumors other than BM
- (iii) Images with patient motion: excessive motion leading to artifacts that make the scan technically inadequate
Medical professionals must finalize (confirm or modify) the contours generated by TAIMedImg DeepMets, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
Please select the types of uses (select one or both, as applicable).
☑ Prescription Use (Part 21 CFR 801 Subpart D)
☐ Over-The-Counter Use (21 CFR 801 Subpart C)
TAIMedImg DeepMets Page 9 of 37
Page 5
510(k) Summary
The following information is provided as required by 21 CFR 807.92.
1 Submitter Information
| Company Name: | Taiwan Medical Imaging Co., Ltd. |
|---|---|
| Address: | 3F., No. 1, Fuxing 4th Rd., Qianzhen Dist., Kaohsiung City 806611 Taiwan |
| Contact Person: | Bo-Ru Lin |
| Phone: | +886-2-25555835 |
| Email: | boru.lin@ailabs.tw |
| Date Prepared | February 14, 2025 |
2 Proposed Device
| Trade Name: | TAIMedImg DeepMets |
|---|---|
| Common Name: | DeepMets |
| Classification Name | Radiological Image Processing Software for Radiation Therapy |
| Regulation Description | Medical Image Management and Processing System |
| Product Code | QKB, QIH |
| Regulation Number | 21 CFR 892.2050 |
| Device Class | Class II |
3 Predicate Device
| Device Name: | VBrain |
|---|---|
| 510(k) Number: | K203235 |
| Manufacturer: | Vysioneer Inc. |
| Product Code: | QKB |
Page 1 of 8
Page 6
4 Device Description
TAIMedImg DeepMets is a software application system intended for use in the contouring (segmentation) of brain magnetic resonance (MR) images. The device comprises an AI inference module and a DICOM Radiotherapy Structure Sets (RTSS, or RTSTRUCT) converter module.
The AI inference module consists of image preprocessing, deep learning neural networks, and postprocessing components, and is intended to contour brain metastasis on the axial T1-weighted contrast-enhanced (T1WI+C) MR images. It utilizes deep learning neural networks to generate contours and annotations for the diagnosed brain metastases.
The DICOM RTSS converter module converts the contours, annotations, along with metadata, into a standard DICOM-RTSTRUCT file, making it compatible with radiotherapy treatment planning systems.
5 Intended Use/ Indication for Use
TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning.
TAIMedImg DeepMets is intended only for patients with known (imaging diagnosed) brain metastases (BM) when cancer cells spread from primary site to the brain. It is not intended to be used with images of other brain tumors or other body parts. The software is intended for use with BM lesions with a diameter of ≥10 mm.
TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The software is an adjunctive tool and not intended for replacing the users' current standard practice of manual contouring process. All automatic output generated by the software shall be thoroughly reviewed by a trained medical professional prior to delivering any therapy or treatment. The physician retains the ultimate responsibility for making the final diagnosis and treatment decision.
TAIMedImg DeepMets is intended to be used by medical professionals trained in the use of the device.
Only DICOM images of adult patients are considered valid input. DeepMets does not support DICOM images of patients that have one of the following exclusions:
- (i) presence of prior craniotomy
- (ii) patients with clinical imaging diagnosis of brain tumors other than BM
- (iii) Images with patient motion: excessive motion leading to artifacts that make the scan technically inadequate
Medical professionals must finalize (confirm or modify) the contours generated by TAIMedImg DeepMets, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system.
Page 2 of 8
Page 7
6 Comparison with Predicate Device
The proposed device, TAIMedImg DeepMets, is substantially equivalent to the claimed predicate, VBrain (K203235). Both are AI (deep learning)-based software used in the workflow of radiation therapy for tumor contouring on MRI images and are regulated under the Product Code QKB. The primary difference is that DeepMets focused solely on Gross Tumor Volume (GTV) contours of brain metastases, while VBrain also includes meningiomas and acoustic neuromas. DeepMets is intended for use with BM lesions with a diameter of ≥ 10 mm.
Please see Table A below for a comparison of the intended use and key technological characteristics of the proposed device and the predicate device.
Table A. Comparison with the predicate device.
| Item | Proposed Device | Predicate Device |
|---|---|---|
| Company | Taiwan Medical Imaging Co., Ltd. | Vysioneer Inc. |
| Device Name | TAIMedImg DeepMets | VBrain |
| 510k Number | Pending | K203235 |
| Regulation No. | 21CFR 892.2050 | 21CFR 892.2050 |
| Classification | II | II |
| Product Code | QKB, QIH | QKB |
| Intended Use/Indication for Use | TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning. |
TAIMedImg DeepMets is intended only for patients with known (imaging diagnosed) brain metastases (BM) when cancer cells spread from primary site to the brain. It is not intended to be used with images of other brain tumors or other body parts. The software is intended for use with BM lesions with a diameter of ≥ 10 mm.
TAIMedImg DeepMets uses an artificial intelligence algorithm to | VBrain is a software device intended to assist trained medical professionals, during their clinical workflows of radiation therapy treatment planning, by providing initial object contours of known (diagnosed) brain tumors (i.e., the region of interest, ROI) on axial T1 contrast-enhanced brain MRI images.
VBrain uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) brain tumor on MRI images for trained medical professionals' attention, which is meant for informational purposes only and not intended for replacing their current standard practice of manual contouring process. VBrain does not alter the original MRI image, nor does it intend to be used to detect tumors for |
Page 3 of 8
Page 8
| | contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The software is an adjunctive tool and not intended for replacing the users' current standard practice of manual contouring process. All automatic output generated by the software shall be thoroughly reviewed by a trained medical professional prior to delivering any therapy or treatment. The physician retains the ultimate responsibility for making the final diagnosis and treatment decision.
TAIMedImg DeepMets is intended to be used by medical professionals trained in the use of the device.
Only DICOM images of adult patients are considered valid input. DeepMets does not support DICOM images of patients that have one of the following exclusions:
(i) presence of prior craniotomy, (ii) patients with clinical imaging diagnosis of brain tumors other than BM, (iii) Images with patient motion: excessive motion leading to artifacts that make the scan technically inadequate.
Medical professionals must finalize (confirm or modify) the contours generated by TAIMedImg DeepMets, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system. | diagnosis. VBrain is intended only for generating Gross Tumor Volume (GTV) contours of brain metastases, meningiomas, and acoustic neuromas on axial T1 contrast-enhanced MRI images; It is not intended to be used with images of other brain tumors. The user must know the tumor type when they use VBrain. VBrain is intended to be used on adult patients only.
Medical professionals must finalize (confirm or modify) the contours generated by VBrain, as necessary, using an external platform available at the facility that supports DICOM-RT viewing/editing functions, such as image visualization software and treatment planning system. |
|---|---|---|
| Operating System | Linux | Linux |
| User Population | The software is only used by trained medical professionals. | Trained medical professionals including, but not limited to, radiologists, oncologists, physicians, |
Page 4 of 8
Page 9
| medical technologists, dosimetrists, and physicists. | |
|---|---|
| Patient Population | Adult patients with known primary cancer (outside brain) and brain metastasis scheduled for radiation therapy. |
| Anatomical Site | Brain |
| Supported Modalities | Axial T1-weighted contrast-enhanced (T1WI+C) brain magnetic resonance (MR) images |
| Localization and Definition of Objects | Known (imaging diagnosed) brain metastases with a diameter of ≥ 10 mm |
| Performance Testing | A performance evaluation of TAIMedImg DeepMets for brain metastasis segmentation is proceeded, the clinical testing dataset comprised 158 cases from 16 MRI scan sources in US. Five metrics are calculated and evaluated: (1) lesion-wise sensitivity, (2) false positive rate, (3) Dice Similarity Coefficient, (4) Hausdorff distance and (5) centroid distance between DeepMets' segmentation and clinicians' segmentation. |
| Segmentation (Contouring) Technology | Deep learning |
| Design: Data Visualization/Graphical User Interface | No |
| Design: Manual editing feature | No |
| Alteration of Original Images | No |
| Data Export | DICOM-RT |
7 Performance Data
7.1 Software Verification and Validation Testing
For software design, Taiwan Medical Imaging Co., Ltd. conducted and documented the software verification and validation testing activities, in accordance with FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions" dated June 14, 2023, for software devices identified as Enhanced Documentation Level.
In addition, the following standards have also been consulted during the software V & V activities:
- IEC 62304:2006/A1:2016 Medical device software - Software life cycle processes
- ISO 14971: 2019 Medical devices - Applications of risk management to medical device
The Software V & V activities and documentation are based on the Enhanced Documentation Level.
7.2 Training Dataset
The DeepMets model was initially trained on a retrospective dataset of 1,029 patients with brain metastases who underwent Gamma Knife radiosurgery, collected from a major medical center in Taiwan between 1993 and 2017. Further tuning was conducted using an additional dataset from 559 patients included in a nationwide healthcare database covering the years 2018 to 2019.
7.3 Standalone Performance Testing
Standalone performance testing was conducted using an independent U.S. dataset consisting of 158 MRI scans from 158 patients with 289 measurable lesions (≥10 mm in diameter, as defined by RANO-BM criteria). The dataset included MRI scans from 16 imaging facilities, acquired using scanners from GE, Philips, Siemens, and Toshiba, with standardized parameters (axial T1WI+C with gadolinium-based contrast, slice thickness ≤ 5 mm, pixel size 0.3-1 mm, and 0-1 mm slice gap). The validation dataset was from the U.S., completely independent and not used in any stage of algorithm development.
The demographic distribution of the dataset:
Gender: 75 Female, 83 Male
Page 6 of 8
Page 10
Age: Adult, range from 41 to 92 years old; the average age is 66.65 years with a standard deviation of 9.72.
Ethnicity: 4 Not Hispanic or Latin, 154 Unknown
Race: 1 African American, 104 White, 53 Unknown
Note: due to anonymization, ethnicity and race information were not available for all cases.
Ground truth annotations were manually established based on consensus NRG/RTOG clinical guidelines by three clinically experienced radiologists/neuroradiologists. These annotations reflected established clinical segmentation standards for brain metastases and served as the reference standard for all performance evaluations
Primary performance endpoints of performance testing included Lesion-Wise Sensitivity (Se) and False Positive Rate (FPR), while secondary endpoints included Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and Centroid Distance (CD).
Acceptance criteria for model performance were established by referencing published benchmarks from FDA-cleared deep learning devices using deep learning for lesion detection and segmentation, along with clinical standards relevant to brain metastasis management. A summary of performance results along with the acceptance criteria is presented below:
Table B: Summary of DeepMets performance
| Metric | Mean | 95%CI | Acceptance Criteria | Source |
|---|---|---|---|---|
| Lesion-Wise Sensitivity (Se) (%) | 89.97 | (86.51, 93.43) | > 80 | Deep learning |
| False-Positive Rate (FPR) (FPs/case) | 0.354 | (0.215, 0.481) |