Search Results
Found 1 results
510(k) Data Aggregation
(93 days)
The Neosoma software uses an artificial intelligence algorithm (i.e., deep learning neural networks) to contour (segment) known or previously diagnosed brain tumors on MRI images for qualified and trained medical professionals.
The technology is meant for informational purposes only and not intended to replace the clinician's current standard practice of manual contouring. The software does not alter the original MRI image, nor is it intended to be used to detect tumors for diagnosis. The software is intended to be used on adult patients only.
When using the Neosoma software in a radiation oncology planning workflow, or other clinical workflows, it is intended for generating Gross Tumor Volume (GTV) contours. For all clinical workflows, medical professionals must finalize (confirm or modify) the contours generated by the Neosoma software, as necessary, using an external platform available at the facility that supports DICOM viewing/editing functions, such as image visualization software and treatment planning system.
Neosoma Brain Mets is a Software as a Medical Device (SaMD) that is designed specifically for the semi-automatic segmentation of previously diagnosed brain metastases. This functionality is applicable to the T1 post-contrast sequence, which is routinely obtained in clinical practice through brain Magnetic Resonance Imaging (MRI).
It is important to note that the standard criterion for diagnosing brain metastasis includes the presence of a known primary cancer that has been identified as having metastasized to the brain. Accordingly, Neosoma Brain Mets is not intended for use with images representing other types of brain lesions.
Furthermore, Neosoma Brain Mets is specifically designed for use in adult patient populations (age 22 and older). As such, its usage should be confined to this demographic to ensure compliance with its intended use parameters and to maximize the accuracy and relevance of its results.
The analysis performed by the AI includes semi-automatic segmentation of the metastasis based on pixel signal intensity. The volumes are calculated using non-machine-learning post-processing from the AI segmentation output. For this segmentation, the software requires one MRI sequence (T1 post-contrast) as input, and it outputs post-processed images that contain color-coded segmentations, as well as volumetric measurements.
Here's an analysis of the acceptance criteria and study details for the Neosoma Brain Mets device, based on the provided FDA 510(k) clearance letter:
Neosoma Brain Mets - Acceptance Criteria and Study Details
1. Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Sensitivity | ≥ 0.85 | 0.90 (95% CI: 0.87 - 0.94) |
| False Positive Rate | ≤ 5 false positive lesions per MRI | 0.57 lesions per MRI (95% CI: 0.35 - 0.80) |
| DSC (Dice Similarity Coefficient) | ≥ 0.70 | 0.86 (95% CI: 0.83 - 0.89) |
| HD95 (95th percentile Hausdorff Distance) | ≤ 2.94 mm | 1.78 mm (95% CI: 1.02 - 2.54) |
| MSD (Mean Surface Distance) | ≤ 0.66 mm | 0.36 mm (95% CI: 0.16 - 0.56) |
2. Test Set Sample Size and Data Provenance
- Sample Size for Test Set: 70 subjects, each with one MRI (total of 70 MRIs).
- Data Provenance: Retrospective, multicenter study. Acquired from medical sites inside and outside of the US that were not included in the training dataset to ensure device generalizability. The data involved standard-of-care MRI protocols on Canon, GE, Siemens, and Toshiba scanners at both 1.5T and 3.0T.
- Patient Demographics in Test Set: Age range of 28 to 84, covering a diverse group of ethnic backgrounds. The distribution of primary cancers was consistent with the known epidemiology of brain metastases. A subgroup analysis demonstrated consistent device performance across various factors including site, imaging manufacturer, field strength, patient race and ethnicity, age, gender, primary cancer, and site geography.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Three.
- Qualifications of Experts: US board-certified neuroradiologists with expertise in measuring brain metastases.
4. Adjudication Method for the Test Set
The document explicitly states that the reference standard (ground truth) was established using three US board-certified neuroradiologists. However, it does not specify the adjudication method used (e.g., 2+1, 3+1, majority vote, or consensus). It simply states that the "reference standard (ground truth) was established using" these three experts.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study involving human readers with and without AI assistance is described in the provided text. The study focuses on the standalone performance of the AI algorithm compared to an expert-established ground truth.
6. Standalone Performance (Algorithm Only)
Yes, a standalone (algorithm only, without human-in-the-loop performance) study was done. The report describes the clinical performance of the "Neosoma Brain Mets" device (the AI algorithm) against a reference standard established by experts. The performance metrics (Sensitivity, False Positive Rate, DSC, HD95, MSD) are all measures of the algorithm's direct output compared to the ground truth.
7. Type of Ground Truth Used
The ground truth used was expert consensus (or interpretation by multiple experts). It was established by three US board-certified neuroradiologists.
8. Sample Size for the Training Set
The document states that the test dataset was acquired from medical sites that were not included in the training dataset. However, it does not specify the sample size for the training set.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established. It only describes the establishment of the ground truth for the test set.
Ask a specific question about this device
Page 1 of 1