(70 days)
Arterys Oncology DL is a medical diagnostic application for viewing, manipulation and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering.
Arterys Oncology DL enables visualization of information that would otherwise have to be visually compared disjointedly. Arterys Oncology DL provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations.
Arterys Oncology DL is designed to support the oncological workflow by helping the user confirm the absence or presence of lesions, including evaluation, quantification, follow-up and documentation of any such lesions.
Note: The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of the separate unregistered images. Arterys Oncology DL is a complement to these standard procedures.
This traditional 510(k) is being submitted for Arterys Oncology DL which is intended for viewing, manipulation, 3D-visualization and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering. The software supports the oncological workflow by helping the user to confirm the absence or presence of lesions, including evaluation, follow-up and documentation of any such lesions.
Key features of the software are:
- 2D and 3D visualization and comparative review
- Manual volumetric segmentation
- Semi-automatic volumetric segmentation of lung nodules and liver lesions
- Co-registration
- Longitudinal tracking
- Nodule/lesion size quantifications
- Data reporting based on Lung-RADS and LI-RADS guidelines
The provided text describes the Arterys Oncology DL device and its 510(k) submission for FDA clearance. While it outlines general performance data and verification activities, it lacks the specific details required to fully address all aspects of the acceptance criteria and the study that proves the device meets them.
Here's an analysis based on the available information:
1. A table of acceptance criteria and the reported device performance
The document mentions "software specifications" and "design requirements" but does not explicitly state quantitative acceptance criteria for the device's performance (e.g., specific accuracy, sensitivity, or specificity thresholds). Instead, it broadly states that "the device meets its design requirements and intended use, that it is as safe and as effective as the predicate devices, and that no new issues of safety and effectiveness were raised."
Therefore, a precise table of acceptance criteria and reported device performance cannot be generated from the given text.
2. Sample size used for the test set and the data provenance
The document mentions "Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." However, it does not specify the sample sizes used for these test sets.
It also does not provide information on the data provenance (e.g., country of origin, retrospective or prospective nature) for the test sets.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide any information regarding the number of experts used to establish the ground truth for the test set or their qualifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not provide any information about the adjudication method used for the test set.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The document does not explicitly state that a multi-reader multi-case (MRMC) comparative effectiveness study was done, nor does it provide any effect size for human reader improvement with AI assistance. It mentions that "the clinician retains the ultimate responsibility" and that the device "is a complement to these standard procedures," suggesting an AI-assisted workflow, but no specific study details are provided.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document states, "Arterys non-clinical V&V testing included Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." This suggests that performance of the deep learning models themselves was evaluated, which would align with standalone algorithm performance, particularly for the "segmentation of lung nodules and liver lesions" feature. However, the document does not explicitly present or detail standalone (algorithm only) performance metrics or studies.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not specify the type of ground truth used for any of the testing mentioned (Liver MR Deep Learning Model Testing, Lung MR Deep Learning Model Testing, Lung Longitudinal Tracking).
8. The sample size for the training set
The document does not provide 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.
Summary of Missing Information:
The provided text focuses on the regulatory submission process, the device's intended use, and its general adherence to safety and performance standards. It lacks the detailed technical and scientific study information typically found in a clinical study report or technical performance evaluation, specifically:
- Quantitative acceptance criteria.
- Specific sample sizes for test and training sets.
- Data provenance for test and training sets.
- Details on expert involvement (number, qualifications, adjudication) for ground truth establishment.
- Specific performance metrics for the deep learning models (standalone or assisted).
- Details of any comparative effectiveness studies with human readers.
- Methods for establishing ground truth for both training and testing.
§ 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).