(59 days)
Philips MammoDiagnost VU is a software workstation for viewing, manipulati reporting and communication of digital mammography images (DICOM "For Presentation" images) and other modality images. It interfaces to image storage, printing and CAD devices using DICOM or similar interface standards
Philips MammoDiagnost VU workstation software package is intended for viewing, manipulation, reporting and communication of digital mammography images (DICOM "For Presentation" images) as well as other modality images. It interfaces to mammography acquisition stations and image storage, printing and CAD devices using DICOM or similar interface standards. It uses and builds further on the Stentor iSite PACS v4.x software (Stentor is now a Philips owned company). Philips MammoDiagnost VU workstation software package runs on standard information technology hardware and software. The proprietary software in the Philips MammoDisonost VU workstation software package uses a standard Microsoft Operating System and user interface. Communication and data exchange are done using standard TCP/IP, DICOM and HL7 protocols.
The provided text is a 510(k) summary for the Philips MammoDiagnost VU, a Picture Archiving and Communication System (PACS) workstation software package for digital mammography images. The document focuses on demonstrating substantial equivalence to predicate devices rather than presenting a detailed study with specific acceptance criteria and performance metrics for the device itself as one would expect for a new AI/CAD device.
Therefore, the requested information, particularly regarding acceptance criteria and the study that proves the device meets the acceptance criteria, is not explicitly available in the provided document in the format requested. The document does not describe a clinical study of the Philips MammoDiagnost VU's diagnostic performance against specific metrics with human readers or as a standalone algorithm.
Instead, the summary establishes substantial equivalence based on:
- Intended Use: The MammoDiagnost VU shares the same intended use as predicate devices: viewing, manipulation, reporting, and communication of digital mammography images and other modality images, interfacing with standard imaging devices.
- System Description: It builds upon existing, cleared technology (Stentor iSite PACS v4.x) and uses standard components (Microsoft OS, TCP/IP, DICOM, HL7 protocols).
- General Safety and Effectiveness: Compliance with ISO 13485, 21 CFR Part 820, NEMA XR 22-2006, and NEMA PS 3.2 DICOM standards.
- No new indications for use or new potential hazards.
Since the device is a PACS workstation for viewing and managing images, and not a diagnostic AI algorithm that provides interpretations or detections, a typical "acceptance criteria" table for diagnostic performance (e.g., sensitivity, specificity, AUC) alongside "reported device performance" is not applicable here. The "performance" in this context is its ability to correctly display and manage images according to industry standards, which is assessed through engineering validation and adherence to regulatory standards rather than a clinical trial measuring diagnostic accuracy.
Therefore, many parts of your request about a diagnostic performance study cannot be answered from this document.
However, I can extract the following information based on what is available:
1. A table of acceptance criteria and the reported device performance
As explained above, this device is a PACS workstation. Its "performance" is primarily related to its functional capabilities and adherence to existing industry and regulatory standards for image display and management. The acceptance criteria relate to these functional and compliance aspects rather than diagnostic accuracy.
| Acceptance Criteria (Implied from document) | Reported Device Performance (Implied from document) |
|---|---|
| Functional Capabilities: | |
| - Viewing digital mammography images (DICOM "For Presentation" images) | - Intended for viewing digital mammography images. |
| - Manipulation of digital mammography images | - Intended for manipulation of digital mammography images. |
| - Reporting capabilities for digital mammography images | - Intended for reporting on digital mammography images. |
| - Communication of digital mammography images | - Intended for communication of digital mammography images. |
| - Interfacing with mammography acquisition stations | - Interfaces to mammography acquisition stations. |
| - Interfacing with image storage, printing, and CAD devices | - Interfaces to image storage, printing, and CAD devices. |
| - Support for DICOM standards | - DICOM support included (DICOM "For Presentation" images, DICOM protocols). |
| - Support for generic and mammography hanging protocols | - Generic and Mammography hanging protocols included. |
| - CAD overlays functionality | - CAD overlays functionality included. |
| - Double blind read workflow support | - Double blind read workflow functionality included. |
| - Automatic breast tissue alignment | - Automatic breast tissue alignment functionality included. |
| - Background suppression at inversion | - Background suppression at inversion functionality included. |
| Technical & Regulatory Compliance: | |
| - Operates on standard information technology hardware and software | - Runs on standard information technology hardware and software (Microsoft Operating System, standard user interface, TCP/IP, DICOM, HL7 protocols for communication). |
| - Developed under ISO 13485 and 21 CFR Part 820 compliant Quality System | - Software specified, validated, and tested under a registered ISO 13485 and 21 CFR Part 820 compliant Quality System. |
| - Complies with NEMA XR 22-2006 (Display & Workstation Quality Control) | - Complies with NEMA XR 22-2006 for manufacturers of displays and workstations labeled for final interpretation in full-field digital mammography. |
| - Complies with NEMA PS 3.2 DICOM set | - Complies with the NEMA PS 3.2 DICOM set. |
| - Instructions for use, cautions, and warnings provided for safe, effective use | - Device labeling contains instructions for use and necessary cautions/warnings for safe and effective use. (User responsibilities for display quality/environmental lighting also noted). |
| - Hardware components are "off the shelf" computer components | - Hardware components specified are all "off the shelf" computer components. |
| - Monitors used for interpretation in USA must be FDA cleared (≥5 Mpixel) | - Utilized with high-resolution monitors suitable for screening and diagnostic mammography; for USA, monitors must be FDA cleared offering at least 5 Mpixel resolution and meeting other FDA-reviewed technical specifications. |
| - No new indications for use compared to predicate devices | - The device does not introduce new indications for use compared to predicate devices. |
| - No new potential hazards compared to predicate devices | - The use of the device does not result in any new potential hazard compared to predicate devices. |
| - Device is substantially equivalent to predicate devices | - Philips Medical Systems considers the Philips MammoDiagnost VU to be substantially equivalent to Stentor (Philips) iSite PACS v 4.x (K063267), GE Seno Advantage (K033400), and Hologic SecurView DX (K062107). This equivalence was accepted by the FDA (K083740). |
Regarding the absence of other requested information:
- 2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- No clinical performance study on a test set is described.
- 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)
- No clinical performance study on a test set is described.
- 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- No clinical performance study on a test set is described.
- 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
- This is a PACS workstation, not an AI/CAD diagnostic device. No such comparative effectiveness study is described. The device facilitates a "Double blind read workflow," which is a feature of the workstation rather than a study outcome.
- 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- This is a PACS workstation, not a standalone diagnostic algorithm. No such study is described.
- 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- No clinical performance study is described that would require ground truth for diagnostic accuracy.
- 8. The sample size for the training set
- This is a PACS workstation. There is no "training set" in the context of an AI algorithm learning diagnostic patterns.
- 9. How the ground truth for the training set was established
- Not applicable as there is no training set for an AI algorithm.
In summary, the provided 510(k) pertains to a medical imaging workstation rather than an AI-driven diagnostic tool. Therefore, the information typically associated with AI device performance studies (like test sets, ground truth, reader studies) is not present because it's not relevant for demonstrating the substantial equivalence of a PACS workstation. The device's "acceptance" is based on its functional design, adherence to established standards, and its similarity in intended use and technological principles to already cleared predicate devices.
§ 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).