(114 days)
DICOM Viewer is a software device for display of medical images and other healthcare data. It includes functions for image review, image manipulation, basic measurements and 3D visualization (MPR reconstructions and 3D volume rendering).
It is not intended for primary image diagnosis or the review of mammographic images.
The DICOM Viewer is software for web based viewing of DICOM data.
The provided document is a 510(k) summary for a DICOM Viewer. It describes the device's intended use, features, and declares substantial equivalence to predicate devices. However, it does not contain information about specific acceptance criteria or a detailed study proving the device meets those criteria, especially in terms of diagnostic performance metrics.
The document states that the "DICOM Viewer is a software device for display of medical images and other healthcare data," and explicitly clarifies: "It is not intended for primary image diagnosis or the review of mammographic images." This means the device is for general viewing and not for a specific diagnostic task that would require rigorous performance metrics like sensitivity, specificity, or AUC, as these would be associated with a "primary image diagnosis" function.
Therefore, many of the requested details, such as specific performance metrics, sample sizes for test and training sets, ground truth establishment, expert qualifications, and MRMC studies, would not be applicable or expected for a device with this stated intended use.
Here's an attempt to answer the questions based only on the provided text, highlighting where information is absent or not relevant given the device's purpose:
1. A table of acceptance criteria and the reported device performance
Based on the provided text, the device's intended use is not for primary image diagnosis. As such, the acceptance criteria are focused on functionality, safety, and substantial equivalence to predicate devices, rather than diagnostic performance metrics (e.g., sensitivity, specificity, accuracy) that would be relevant for a diagnostic AI device.
| Acceptance Criterion (Inferred from Text) | Reported Device Performance (Inferred from Text) |
|---|---|
| Display medical images and other healthcare data | DICOM Viewer is software for web-based viewing of DICOM data. |
| Functions for image review, manipulation, basic measurements, 3D visualization (MPR, VRT) | Includes these functions. |
| Not intended for primary image diagnosis or mammography review | Explicitly stated (this is a limitation, not a performance metric). |
| Safety and effectiveness similar to predicate devices | Verified and validated activities ensure design specifications met and no new safety/effectiveness issues. |
| Substantial equivalence to predicate devices (K093117, K130624) | Found to have similar functionality, intended use, technological characteristics, and typical users. |
| Software risks analyzed, no non-acceptable risks identified | Stated directly. |
| User interface is substantially equivalent to previous version (2.2) | Formative usability tests performed, prototype substantially equivalent to final device with minimal changes. |
| Meets design specifications | Verification of the System DICOM Viewer thoroughly carried out. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable. This device is not an AI/ML algorithm performing a diagnostic task that typically involves a defined "test set" of patient data for performance evaluation in the way an AI diagnostic tool would. The validation focused on functional verification and safety, not on diagnostic accuracy on a dataset. The document mentions reviews of MAUDE, BfArM, and Brainlab internal complaint databases for incidents of similar products, but this is not a test set for performance.
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)
Not applicable. As the device is for viewing and not primary diagnosis, there is no "ground truth" establishment for diagnostic accuracy purposes on a test set mentioned in the document.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. No test set for diagnostic performance requiring adjudication is mentioned.
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. This document does not suggest an MRMC study was performed, nor would it be expected given the device's stated intended use (not for primary diagnosis). The device displays images but does not actively assist in interpretation beyond basic viewing tools.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
This question is largely irrelevant for a DICOM Viewer whose primary function is image display. The device is a "standalone" software in the sense that it operates independently to display images, but it doesn't perform diagnostic interpretations that would be measured for standalone performance as an AI algorithm would.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable. No ground truth for diagnostic accuracy is mentioned in context of performance evaluation.
8. The sample size for the training set
Not applicable. This device is a software viewer, not an AI/ML algorithm that requires a "training set" in the conventional sense for learning and inference.
9. How the ground truth for the training set was established
Not applicable. (See #8)
§ 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).