(274 days)
EZPACS® is intended for use by radiologists (for primary diagnosis), and other medical professionals who needs access to radiological images and reports.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 Mpixel resolution and meets other technical specifications reviewed and accepted by FDA.
EZPACS® is a PACS system that runs on off-the-shelf monitors and PCs running the Microsoft Windows® operating system. It consists of software that displays images and provides functions for image manipulation, enhancement, compression and quantification.
The provided document (K062878) does not describe a study proving the device meets specific acceptance criteria in the way a clinical performance study for an AI-powered CADe or CADx device would. This 510(k) pertains to a Picture Archiving Communications System (PACS) software called EZPACS®, which is a medical image management system, not an AI diagnostic or assistive tool.
Therefore, many of the requested elements (like sample size for test set, number of experts for ground truth, MRMC study effect size, standalone performance, training set details) are not applicable to this type of device and submission.
The submission focuses on establishing substantial equivalence to predicate devices. This means demonstrating that the new device has the same intended use, features, safety, and effectiveness as already legally marketed devices.
Here's how to address the questions based on the provided information:
1. Table of Acceptance Criteria and Reported Device Performance
For a PACS system like EZPACS®, the "acceptance criteria" are primarily related to its functional equivalence and conformity to standards, rather than diagnostic performance metrics. The "performance" is its ability to perform the stated functions.
| Acceptance Criteria (Implied from Substantial Equivalence Claim) | Reported Device Performance (as stated in submission) |
|---|---|
| Functional Equivalence to Predicate PACS Systems: | |
| - Runs on Commercial PCs (Windows® O/S) | Yes |
| - Supports Commercial Monitors | Yes |
| - Multi-monitor support | Yes |
| - JPEG/wavelet compression | Yes |
| - DICOM conformance | Yes |
| - Measurement tools (ROI, distance, angle) | Yes |
| - Viewing tools (window/level, magnify, pan, annotation) | Yes |
| - Comparison cases functionality | Yes |
| - Cine/stack view functionality | Yes |
| - Supports teleradiology | Yes |
| - 3D viewing functionality | Yes |
| Intended Use: | Same as predicate devices |
| Safety and Effectiveness: | Same as predicate devices |
Note: The "study" that proves the device meets "acceptance criteria" in this context is the substantiation of substantial equivalence through comparison of features and intended use with the identified predicate devices (IMPAX by Agfa and DirectView by Kodak). No quantitative performance metrics are provided because it's not an AI diagnostic device.
2. Sample size used for the test set and the data provenance
- Not Applicable. This submission is for a PACS software system, not a diagnostic AI algorithm that requires a test set of medical images for performance evaluation. The "test" is a feature-by-feature comparison against predicate devices.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not Applicable. There is no "test set" of medical images for diagnostic performance evaluation for this type of device.
4. Adjudication method for the test set
- Not Applicable. No test set requiring expert adjudication.
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 is not an AI diagnostic or assistive device. An MRMC study is not relevant to demonstrating substantial equivalence for a PACS system.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Not Applicable. This device is a PACS system, primarily for image management and display, not a standalone diagnostic algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not Applicable. For this submission, the "ground truth" is effectively the functionality and regulatory status of the predicate devices. The claim is that EZPACS® performs the same functions as those already approved devices.
8. The sample size for the training set
- Not Applicable. As this is a PACS software system, there is no "training set" in the context of machine learning or AI.
9. How the ground truth for the training set was established
- Not Applicable. No training set is involved for this type of device.
Summary of the "Study" and "Proof":
The "study" in this context is a feature-by-feature comparison and analysis for substantial equivalence against legally marketed predicate devices. The "proof" is the detailed comparison table provided in the submission (see "Substantial Equivalence" section in the document) which demonstrates that EZPACS® shares the same core functionalities, hardware requirements, and intended use as the predicate devices. The conclusion reached by the FDA (as stated in the letter) is that based on this comparison, the device is substantially equivalent, and therefore, its safety and effectiveness are established.
§ 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).