(157 days)
SubtleMR is an image processing software that can be used for image enhancement in MRI images. It can be used to reduce image noise for head, spine, neck, abdomen, pelvis, prostate, breast, and musculoskeletal MRI, or increase image sharpness for head MRI.
SubtleMR is Software as a Medical Device (SaMD) consisting of a software algorithm that enhances images taken by MRI scanners. As it only processes images for the end user, the device has no user interface. It is intended to be used by radiologists in an imaging center. clinic, or hospital. The software can be used with MR images acquired as part of MRI exams on 1.2 Tesla, 1.5 Tesla or 3 Tesla scanners. The device's inputs are standard of care MRI images. The outputs are images with enhanced image quality.
Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria Category | Specific Criteria | Reported Device Performance |
|---|---|---|
| Noise Reduction | Signal-to-noise ratio (SNR) of a selected region of interest (ROI) in each test dataset is on average improved by greater than or equal to 5% after SubtleMR enhancement compared to the original images. | Passed: SNR of a selected ROI in each test dataset was on average improved by greater than or equal to 5% after SubtleMR enhancement compared to the original images. |
| Noise Reduction | Visibility of small structures in the test datasets after SubtleMR was rated on average non-inferior to that before SubtleMR based on a Likert reader study. | Passed: Visibility of small structures in the test datasets after SubtleMR was rated on average non-inferior to that before SubtleMR based on a Likert reader study. |
| Sharpness Enhancement | The thickness of anatomic structure and the sharpness of structure boundaries are improved after SubtleMR enhancement in at least 90% of the test datasets. | Passed: The thickness of anatomic structure and the sharpness of structure boundaries were improved after SubtleMR enhancement in at least 90% of the test datasets. |
Study Details
2. Sample Sizes and Data Provenance
- Test Set Sample Size: Not explicitly stated, but the text mentions "each test dataset" for noise reduction and "at least 90% of the test datasets" for sharpness enhancement, implying a quantifiable number of datasets were used.
- Data Provenance: Retrospective clinical data. The specific country of origin is not mentioned.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Not explicitly stated for either test.
- Qualifications of Experts: For the noise reduction test, a "Likert reader study" was conducted, implying human expert readers were involved in rating, but their specific qualifications (e.g., radiologist with X years of experience) are not provided in this document.
4. Adjudication Method for the Test Set
- The document mentions a "Likert reader study" for the noise reduction test to assess non-inferiority. This typically involves multiple readers, and their ratings would be aggregated or adjudicated, but the specific adjudication method (e.g., 2+1, 3+1) is not detailed. For the sharpness enhancement test, the method of assessing "improved" thickness and sharpness in 90% of datasets is not described in terms of human adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The document mentions a "Likert reader study" for the noise reduction assessment, which is a type of reader study. However, it does not explicitly state that a formal MRMC comparative effectiveness study (comparing human readers with AI vs without AI assistance) was conducted, nor does it provide an effect size for human reader improvement with AI assistance. The focus seems to be on the device's standalone performance or impact on image quality as assessed by readers.
6. Standalone (Algorithm Only) Performance
- Yes, standalone performance was assessed.
- For Noise Reduction: "signal-to-noise ratio (SNR) of a selected region of interest (ROI) in each test dataset is on average improved by greater than or equal to 5% after SubtleMR enhancement compared to the original images." This is an objective, algorithm-only performance metric.
- For Sharpness Enhancement: "the thickness of anatomic structure and the sharpness of structure boundaries are improved after SubtleMR enhancement in at least 90% of the test datasets." While this might involve some human interpretation of "improved," the phrasing suggests an objective, algorithm-driven assessment of image characteristics.
7. Type of Ground Truth Used
- Noise Reduction:
- Objective: Original (unenhanced) MRI images served as a baseline for SNR improvement.
- Subjective/Expert-based: A "Likert reader study" was used for assessing "visibility of small structures," implying expert human opinion as part of the ground truth for this aspect.
- Sharpness Enhancement: Original (unenhanced) MRI images served as a baseline, and the ground truth for "improved" anatomic structure thickness and boundary sharpness appears to have been derived from a comparison to these original images, likely through objective measurements or expert assessment. The specific method is not fully detailed.
8. Sample Size for the Training Set
- The sample size for the training set is not provided in the given text.
9. How Ground Truth for Training Set Was Established
- The method for establishing ground truth for the training set is not described in the provided text. The document states that the "subject device was validated with test methods identical to those used to test the predicate device" and that the main performance study utilized "retrospective clinical data" for testing, but it does not elaborate on the training data or its ground truth establishment.
§ 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).