(50 days)
Synapse MPR/Fusion software enables the display, comparison and fusion of 3D (MIP/MPR) of CT, MR, PET and SPECT studies. Typical users are radiologists, technologists and clinicians. Synapse MPR/Fusion is not intended for Mammography use.
Synapse MPR/Fusion software enables the display, comparison and fusion of 3D (MIP/MPR) of CT, MR, PET and SPECT studies.
This 510(k) summary (K113244) for FUJIFILM's SYNAPSE MPR Fusion V2.5 does not contain the specific acceptance criteria and study details often found in regulatory submissions for AI/ML-powered devices. This document is a special 510(k), which typically relates to minor changes to an already cleared device, and thus may only include a summary of the changes and a declaration of substantial equivalence to a predicate device.
However, based on the information provided, we can infer some details and explicitly state what is not present:
Missing Information:
- A table of acceptance criteria and reported device performance metrics (e.g., sensitivity, specificity, AUC).
- Details on the sample size used for any test set.
- Data provenance (country of origin, retrospective/prospective).
- Number and qualifications of experts for ground truth.
- Adjudication method for the test set.
- Results of a multi-reader multi-case (MRMC) comparative effectiveness study.
- Results of a standalone (algorithm-only) performance study.
- Specific type of ground truth used (beyond implying visual comparison for fusion).
- Sample size for any training set.
- How ground truth for any training set was established.
Inferred/Explicit Information from the Document:
1. A table of acceptance criteria and the reported device performance.
- Acceptance Criteria: Not explicitly stated as quantitative metrics (e.g., sensitivity, specificity). The acceptance here is based on demonstration of substantial equivalence to the predicate device (Mirada XD, K101228) and the new functionalities performing as intended. Given it's a Special 510(k), the "acceptance criteria" likely revolve around verifying the new features perform without negatively impacting safety or effectiveness and are functionally equivalent to the predicate for existing features.
- Reported Device Performance: No quantitative performance metrics are reported (e.g., accuracy, precision, recall for object detection or classification). The document describes functional enhancements and additional functionality rather than diagnostic performance improvements measured against a ground truth. The "performance" demonstrated is the successful implementation of these features, such as "Auto correcting orientation" and "Fusion combination" of various modalities.
2. Sample size used for the test set and the data provenance.
- Sample Size: Not specified.
- Data Provenance: Not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts.
- Not specified. The nature of the enhancements (display, comparison, fusion) suggests that expert review would have been used to verify the correct functioning and visual quality of the fused images, but no formal expert review panel is described.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set.
- Not specified.
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 MRMC comparative effectiveness study is mentioned. This device is described as a software tool for display and fusion, not as an AI-assisted diagnostic aid that directly impacts reader performance in a quantitative way that would necessitate such a study.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done.
- No standalone performance study is mentioned. The device's purpose is to enable "display, comparison and fusion" by human users (radiologists, technologists, clinicians). Its "performance" is inherently tied to its utility as a tool for human interpretation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc).
- Not explicitly stated. For the functionalities described (image fusion, orientation correction, display layouts), the implicit ground truth would be the correctness and utility of the visual presentation as judged by subject matter experts (radiologists/technologists) during internal validation. This would involve verifying that images are correctly registered, oriented, and displayed as intended, and that the new features work without error. It's not a diagnostic ground truth like pathology.
8. The sample size for the training set.
- Not applicable/not specified. This document does not describe an AI/ML model that would have a "training set" in the traditional sense. The SYNAPSE MPR Fusion V2.5 is described as image display and processing software, not a machine learning algorithm requiring a training phase on medical image datasets for learning patterns or classifications.
9. How the ground truth for the training set was established.
- Not applicable/not specified, as there is no described training set for an AI/ML 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).