(617 days)
The NEUROShield™ medical image processing software is intended for automatic labelling, visualization, and volumetric quantification of the Hippocampus brain structure from a set of MR images.
NEUROShield™ is a fully automated brain geometry-based quantifying analytics tool/cloud platform that uses Al/Deep Net to support physicians as a clinical decision support tool for neurologists and neuroradiologists. NEUROShield™ takes 3D MR images as input and calculates brain volumes that can assist physicians in devising optimal treatment plans. The Al tool branded as NEUROShield™ provides volumetric measurements of the Hippocampus brain structure. It replaces time-consuming manual processes with leading-edge automated technology that accelerates the analysis for clinical and research purposes. Brain Volume Quantification is a wellestablished methodology for differential and enhanced interpretation of medical images. We are using a locked algorithm, and any proposed modifications will be submitted to the FDA for review.
Here's a summary of the acceptance criteria and the study that proves NEUROShield meets those criteria, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Measure | Threshold (Acceptance Criteria) | NEUROShield™ 95% Confidence Intervals (Reported Performance) | Criteria (Pass/Fail) |
---|---|---|---|
Dice Coefficient | 0.75 | (0.90, 0.92) | Pass |
Hausdorff Distance (mm) | 6.1 | (3.57, 4.06) | Pass |
Correlation (Volume) | 0.82 | (Not explicitly given as CI, but stated as "passed") | Pass |
Relative Volume Difference | 24.6% | (Not explicitly given as CI, but stated as "passed") | Pass |
Mean Difference in BA plots (Total Hippocampus) | 1010 mm³ | (Not explicitly given as CI, but stated as "passed") | Pass |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: 280 subjects
- Data Provenance:
- Country of Origin: USA (collected from the publicly available ADNI - Alzheimer's Disease Neuroimaging Initiative - dataset, with approximately equal geographical distribution across East, Central, and West US regions).
- Retrospective or Prospective: Retrospective
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: 3
- Qualifications: US Board Certified Radiologists
4. Adjudication Method for the Test Set
- Adjudication Method: The ground truth was established by combining the manual segmentations of the 3 radiologists into one tracing per case using the STAPLE (Simultaneous Truth and Performance Level Estimation) algorithm. This STAPLE-derived ground truth was then compared with individual radiologist segmentations to ensure validity.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No, an MRMC comparative effectiveness study that assesses the effect size of human readers improving with AI vs. without AI assistance was not reported in this summary. The study focuses on evaluating the standalone performance of the NEUROShield™ algorithm against an expert-derived ground truth.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Yes, a standalone performance study was done. The NEUROShield™ algorithm's automated segmentations and volume calculations were directly compared against the ground truth established by expert radiologists.
7. The Type of Ground Truth Used
- Ground Truth Type: Expert consensus, specifically "STAPLE-derived ground truth building on the three US Board Certified Radiologists' provided segmentations."
8. The Sample Size for the Training Set
- Sample Size: 186 cases
9. How the Ground Truth for the Training Set Was Established
- The ground truth for the training set was established by manual segmentation of the Hippocampus structure by subject matter experts. This manually segmented data was then used as input to train the deep net Segmentation Model.
§ 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).