(60 days)
ZIOSTATION is an image processing workstation software package designed to run on standard PC hardware. The required hardware consists of standard 'off-the-shelf' computer components. It receives image data from standard modalities (medical image scanning devices) or from image archives. It provides for the viewing, quantification, manipulation, communication, printing, and management of medical images. It can be used as a just a workstation or as a client-server within a network. It is intended for use by trained medical imaging professionals to aid in their reading and review of such data.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammograpic 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.
ZIOSTATION is a software-only imaging workstation that installs on one or more of a customer's standard PCs and integrates with a customer's 'off the shelf' PC-based computer components to provide viewing, quantification, manipulation, communication, printing, and management capabilities for medical images. It provides access to both local and centralized (networked) image data.
ZIOSTATION can acquire and work with image data from multiple DICOM-compliant modalities and image archives. It provides querying and listing based on user-selected criteria. It provides for multiple types of 2D and 3D image displays. It provides interactive menus and tools for image manipulation and measurement. ZIOSTATION provides workflow enhancement and optional specialist tools for clinical applications.
ZIOSTATION uses only lossless compression for images used for diagnostic purposes. It does use lossy compression when exporting to JPEG and AVI files, but its labeling indicates that those files are not to be used for clinical evaluations.
The ZIOSTATION is a PACS system that has not conducted any clinical studies to establish specific acceptance criteria or performance metrics directly from the provided text. The document states that the device has been "thoroughly tested by Ziosoft in accordance with their software development and validation procedures" and "independently evaluated by trained physicians specializing in medical imaging disciplines." However, no specific acceptance criteria or performance data from these evaluations are presented in the document.
Instead, the submission relies on demonstrating substantial equivalence to a legally marketed predicate device, the Barco Voxar 3D Enterprise (K061326). The "acceptance criteria" in this context are implicitly met by showing that ZIOSTATION's features and intended use are essentially identical to the predicate device, and that it does not introduce any new safety or efficacy concerns.
Given the information in the provided text, the specific details requested for a study proving device adherence to acceptance criteria (such as sample size, data provenance, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, or standalone performance) are not available. The document focuses on regulatory clearance through substantial equivalence rather than explicit performance evaluation against predefined numerical criteria.
Therefore, the table of acceptance criteria and reported device performance cannot be filled with numerical values, and many of the questions regarding study design cannot be answered from this document.
Here's a breakdown of what can and cannot be answered based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Based on the provided document, no specific numerical acceptance criteria or performance metrics are reported for ZIOSTATION. The submission relies on substantial equivalence to a predicate device.
| Acceptance Criteria (Not Explicitly Stated - Inferred from Equivalence Claim) | Reported Device Performance (Not Explicitly Stated - Inferred from Equivalence Claim) |
|---|---|
| Functional Equivalence: Must perform core image processing and management functions similarly to the predicate device. | ZIOSTATION provides identical basic functions (view, quantify, manipulate, communicate, print, and manage medical images) as the predicate device (Voxar 3D Enterprise). |
| Technical Equivalence: Must be compatible with standard hardware, DICOM compliant, and offer comparable imaging capabilities (2D, 3D, measurement, segmentation, remote rendering). | ZIOSTATION is compatible with PC/Windows OS, DICOM 3.0, acquires data from multiple sources, offers 2D/3D imaging, measurement tools, segmentation tools, and remote rendering, all "same" as the predicate. |
| Clinical Application Equivalence: Must provide comparable optional specialist tools and workflow enhancements for clinical applications. | ZIOSTATION offers "optional specialist tools and workflow enhancements for clinical applications such as coronary, colon, and vessel analysis," which are "same" as the predicate. |
| Intended Use Equivalence: Must have the same intended use by trained medical imaging professionals. | ZIOSTATION is "intended for use by trained medical imaging professionals to aid in their reading and review of such data," which is "same" as the predicate. |
| Safety and Efficacy: Must not raise new safety or efficacy concerns compared to the predicate. | Ziosoft "demonstrated that ZIOSTATION is safe and effective for its intended use" and "does not raise any new safety or efficacy concerns." |
| Interpretation Restrictions: Must adhere to specific restrictions for mammographic image interpretation. | "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." (This is a condition of use rather than a performance metric.) |
2. Sample size used for the test set and the data provenance
- Not specified. The document mentions internal testing and independent evaluation by physicians but provides no details on sample size or data provenance (e.g., country of origin, retrospective/prospective nature).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not specified. The document vaguely states "independently evaluated by trained physicians specializing in medical imaging disciplines" but does not quantify the number of experts or their specific qualifications (e.g., years of experience, subspecialty). No explicit "ground truth" establishment process for a test set is described.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
- Not specified. No details on adjudication methods for any evaluation are provided.
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 indication of an MRMC study. The ZIOSTATION is an image processing workstation, not specifically an AI-driven diagnostic aid that would typically undergo such a study to measure reader improvement. The document does not describe AI functionality or a reader improvement study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable/Not specified as a standalone algorithm. ZIOSTATION is described as an "image processing workstation software package" intended for use by "trained medical imaging professionals to aid in their reading and review." It is not presented as a standalone diagnostic algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not specified. Since no specific performance study with a test set is detailed, the type of ground truth used is not mentioned. The primary argument is substantial equivalence to a predicate, not performance against a ground truth dataset.
8. The sample size for the training set
- Not applicable/Not specified. ZIOSTATION is an image processing and visualization system, not an AI/machine learning model where a distinct "training set" would typically be referenced for model development. The document does not mention any machine learning components requiring a training set.
9. How the ground truth for the training set was established
- Not applicable/Not specified. As there's no mention of a training set, the method of establishing ground truth for it is also not discussed.
§ 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).