(254 days)
MPXA-2000 is indicated for use in clinical settings where validated and reproducible quantified results are needed to support the calculations in X-ray angiographic images of the coronary arteries, for use on individual patients with coronary artery disease (CAD). MPXA-2000 is indicated for use in adult patient only.
When the quantified results provided by MPXA-2000 are used in a clinical setting on X-ray images of an individual patient, they can be used to support the clinical decisions making for the patient or the evaluation of the treatment applied. In this case, the results are explicitly not to be regarded as the sole, irrefutable basis for clinical diagnosis, and they are only intended for use by the responsible clinicians.
MPXA-2000, the stand-alone application, is cardiovascular image analysis software for the viewing and quantification of X-ray angiographic images of the coronary arteries. Automatic vessel contour detection (i.e. vessel segmentation) forms the basis for the analyses. MPXA-2000 provides automatic analysis through segmentation of vessels and calculation of the segmented vessel's dimensions. MPXA-2000 is developed based on Deep-learning (Classification and Segmentation of vessels) and Computer vision algorithms (Measurements of vessels) to analyze the images and provide quantification of the vessels in real-time. It allows accurate and reproducible quantification of the coronary arteries from a set of those images in DICOM format.
MPXA-2000 is composed of the following key analysis workflow and functionalities:
- Image Uploading, Frame Selection
- Vessel Segmentation
- Classification of Vessel types
- ROIs (regions of Interest) Quantification
- Visualization & Export of the Analysis Results.
The analysis results are available on the screen and can be exported in PDF or Excel file format. MPXA-2000 has been validated for the images produced by FDA-approved X-ray angiography systems from Philips Medical Systems, Siemens Healthineers, GE Healthcare. The input data should be X-ray angiographic images that comply with the DICOM standard.
Here's a breakdown of the acceptance criteria and the study that proves the MPXA-2000 device meets them:
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Vessel Classification Accuracy (Pass criteria not explicitly stated but implied high accuracy is desired) | 0.9934 |
| Vessel Segmentation Dice Similarity Coefficient (DSC) | 0.9200 (Pass criteria: > 0.8) |
| Estimated Minimum Luminal Diameter (MLD) | Comparable to the reported performance of the predicate device QAngio XA |
Study Details
1. A table of acceptance criteria and the reported device performance: Provided above.
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: 305 coronary angiograms.
- Data Provenance: Retrospectively collected from the US population, specifically from Philips Medical Systems Nederland B.V. under a data-sharing agreement.
- Segregation: "Test datasets were strictly segregated from algorithm training datasets."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated, but the document mentions "experienced experts."
- Qualifications: "experienced experts." (No further specific qualifications like years of experience or specialty are detailed in the provided text).
4. Adjudication method for the test set:
- Not explicitly stated. The ground truth was "annotated by experienced experts," implying a single expert or a consensus approach without detailing the specific adjudication method (e.g., 2+1, 3+1).
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:
- No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The study described is a standalone performance test of the device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance test (algorithm only) was done. The document states: "The Deep-learning algorithm used in MPXA-2000 was validated by the standalone performance test (Doc. No. TD-XA2-SPTR) using the method of comparing the analysis results obtained from MPXA-2000 with the ground truth annotated by experienced experts."
7. The type of ground truth used:
- Expert Consensus/Annotation: The ground truth was established by "experienced experts" through "annotation."
8. The sample size for the training set:
- Not explicitly stated. The document only mentions that "Test datasets were strictly segregated from algorithm training datasets." The exact number of images in the training set is not provided within the given text.
9. How the ground truth for the training set was established:
- Not explicitly stated for the training set specifically. However, for the test set, it was established by "annotation by experienced experts." It can be inferred that a similar method was likely used for the training set, but this is not explicitly confirmed in the provided text.
§ 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).