(153 days)
Segment CMR is a software that display and analyzes medical images in DICOM-format using multi-slice, multi-frame and velocity encoded MR images. Segment CMR provides features for analysis of cardiac function, such as cardiac pumping and blood flow. The ventricular analysis is provided for usage in both pediatric (from newborn) and adult population. Images and associated data analysis can be stored, communicated, rendered, and displayed within the system and across PACS system. The data produced by Segment CMR is intended to support qualified cardiologist, radiologist or other licensed professional healthcare for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.
Segment CMR is a software that displays and analyzes multi-slice, multiphase and velocity encoded DICOM compatible medical MR images. Segment CMR provides quantitative measures for analysis of function of the cardiovascular system. The data produced by Segment CMR is intended to be used to support qualified cardiologist, radiologist or other professional healthcare practitioners for clinical decision making. Functional, flow, valve, vessel, and tissue analysis is performed using standardized algorithms and user input. The quantification methods are validated and reproducible. The ventricular analysis is provided for usage in both pediatric (from newborn) and adult population. MR images may be imported from various sources including images stored on portable media, network storage devices, and other vendor systems and supports cardiovascular MR images from all of the major MRI scanner vendors.
The provided text describes the acceptance criteria and a study proving the device meets them for "Segment CMR", a cardiovascular MRI analysis software.
Here's a breakdown of the requested information:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a discrete table of acceptance criteria with numerical targets and corresponding device performance metrics. Instead, it makes a general statement about the device's performance relative to reference methods and its predicate device. This is typical for a 510(k) submission where substantial equivalence is demonstrated rather than meeting specific performance thresholds for a novel device.
Acceptance Criteria (Implied from the text):
- Safety and Effectiveness: Segment CMR should be as safe and effective as the predicate devices.
- Agreement with Reference Methods: Values from the evaluated features in Segment CMR should be in good agreement with values from established reference methods.
- No Adverse Events/Complications: No adverse events or complications associated with the device should be observed in studies.
- Acceptable Residual Risk: All identified hazards should be mitigated to accepted levels of residual risk, and the overall risk evaluation should conclude that the risk is acceptable.
- Benefit Outweighs Risk: Specifically for pediatric use, the benefits should outweigh the risks.
- Performance in Accordance with Intended Use: The device performs in accordance with its intended use and similarly to existing cardiovascular MRI image analysis products.
- No Alteration of MRI Data: The device should not alter MRI imaging data in the analytical process.
Reported Device Performance:
- "The results by the studies show that the values from the evaluated features in Segment CMR were in good agreement with values from the reference method." (Page 6)
- "No adverse advents or complications associated with the subject device were observed in the studies." (Page 6)
- "Based on the clinical performance as documented in the performance studies, Segment CMR was found to have a safety and effectiveness profile that is similar to the predicate device." (Page 6)
- "We conclude that the subject device Segment CMR is as safe and effective as the predicate devices." (Page 7)
- "All identified hazards for Segment CMR have been mitigated to accepted levels of the residual risk and the overall risk residual evaluation concluded that the risk of Segment CMR is acceptable." (Page 7)
- "The extension of pediatric use for the left ventricular analysis did not, according to the hazard analysis, increase the overall residual risk and by evaluating safety and effectiveness, the benefits with pediatric use can be considered to outweigh the risks." (Page 7)
- "Segment CMR performs in accordance with its intended use as well as the cardiovascular MRI image analysis products currently on the market." (Page 7)
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size for Test Set: Not explicitly stated in terms of a specific number of cases or patients. The document refers to "studies" in the plural, implying multiple tests and evaluations.
- Data Provenance: "The studies were performed in US or in Europe." The text does not specify whether the data was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Number of Experts: Not explicitly stated for establishing ground truth.
- Qualifications of Experts: Not explicitly stated. The device is intended to support "qualified cardiologist, radiologist or other licensed professional healthcare practitioners for clinical decision making." This implies that the reference methods or ground truth would be established by such qualified professionals.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: Not explicitly stated.
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
- MRMC Study: The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study designed to measure the improvement of human readers with AI assistance. The focus is on the standalone performance of the software in agreement with established methods. The device is presented as a "support tool" that provides data "as a resource to the clinician," implying it does not replace human interpretation but assists it.
- Effect Size of Human Reader Improvement: Not applicable, as no such MRMC study is described.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Yes, the performance data presented (e.g., "values from the evaluated features in Segment CMR were in good agreement with values from the reference method") primarily focuses on the standalone performance of the algorithms within the software compared to established reference methods or predicate devices. The software "provides quantitative measures for analysis," suggesting its output is directly compared.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: "establish methods as reference standard." This implies ground truth was based on validated and recognized clinical methods, likely expert interpretations, other validated software, or established measurement techniques. The specific nature (e.g., expert consensus vs. pathology) is not detailed.
8. The sample size for the training set
- Sample Size for Training Set: Not explicitly stated. The document mentions that the predicate device Segment, "on which Segment CMR is built upon, is used by more than 200 research groups," which suggests a large body of data might have been implicitly involved in the development and refinement of the underlying algorithms, but a specific "training set" for this device (Segment CMR) is not quantified.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not explicitly described. The general statement about "establish methods as reference standard" likely applies to both training and testing, but the process of establishing ground truth specifically for a training set (if one was formally used) is not detailed.
§ 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).