(20 days)
RA600/CA1000/Digital Hardcopy is intended for viewing and diagnostic interpretation of images acquired from CT, MR, CR, DR, US, XA and other DICOM-compliant medical imaging systems when installed on suitable commercial-standard PC hardware. RA600 / CA1000 is intended for use as a primary diagnostic and analysis workstation in Radiology/ Cardiology or other departments. It is also intended for use as a clinical review workstation throughout the healthcare facility and may be part of a larger PACS configuration.
Digital Hardcopy is intended for use primarily as a workstation for the high volume burning of CDs or DVDs containing DICOM medical images and associated diagnostic report or analysis information. CD /DVD burning and disk labeling are done via a commercially available external robotics device.
RA600/CA1000/Digital Hardcopy receives imaging studies and data over LAN, WAN, intranet or internet from a PACS server or directly from a DICOM -compliant modality or archive utilizing both lossless and lossy compression. It is the user's responsibility to ensure quality, ambient light conditions and image compression ratios are consistent with the clinical application. The R4600/CA1000/Digital Hardcopy workstation may interface with various information systems within the healthcare environment, such as the HIS, RIS, and CVIS. It may be sold as software only, or as a turnkey system
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.
Centricity Radiology RA600 / Centricity Cardiology CA1000 / Centricity Digital Hardcopy is a PC-based DICOM workstation platform which provides scaleable image and data management solutions for medical imaging. This software-based product provides capabilities for the acceptance, transmission, printing, display, storage, editing and digital processing of medical images and associated data.
RA600/CA1000 / Digital Hardcopy may be combined with a PACS network or connected directly to a modality through the use of DICOM networking. The RA600/CA1000 / Digital Hardcopy software application may be sold as a standalone product for use with 'off the shelf' PC hardware that meets minimum specifications or as a turnkey solution integrated with hardware components to be configured to meet the users specific needs.
RA600 / CA1000 / Digital Hardcopy can also provide the hardware and OS platform for a user to operate 3rd party software and/or other GE software applications such as RIS, voice recognition, or advanced imaging analysis, and view any data presented through those applications.
RA600 / CA1000 can act as an image repository for the Centricity Web Viewer application.
The provided text describes a 510(k) premarket notification for the Centricity Radiology RA600 / Centricity Cardiology CA1000 / Centricity Digital Hardcopy, which are PC-based DICOM workstation platforms for medical image management. However, the submission does not contain information regarding objective acceptance criteria or a specific study designed to prove the device meets such criteria with quantitative performance metrics for AI/CAD functionality.
The document states that "The Centricity Radiology RA600 / Centricity Cardiology CA1000 / Technology: Centricity Digital Hardcopy employs the same functional scientific technology as its predicate devices" and concludes that "GE considers features of the Centricity Radiology RA600 / Centricity Cardiology CA1000 / Centricity Digital Hardcopy are equivalent to those of the predicate devices." This indicates a reliance on substantial equivalence to predicate devices rather than a de novo performance study with specific acceptance criteria.
Therefore, many of the requested details about acceptance criteria and study design for AI performance cannot be extracted from the provided text because they are not present. The submission focuses on the general function and safety of the PACS workstation and its equivalence to previously cleared devices.
Here's a breakdown of what can and cannot be answered based solely on the provided text:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: Not explicitly stated as quantitative performance metrics for a specific AI/CAD function. The submission focuses on functional equivalence to predicate devices.
- Reported Device Performance: No specific quantitative performance metrics are provided that would typically be associated with AI/CAD device performance (e.g., sensitivity, specificity, AUC). The "Performance testing" mentioned under "Test Summary" likely refers to system-level performance (e.g., speed, reliability, compliance with DICOM standards) rather than clinical diagnostic accuracy of an AI component.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not provided. There is no mention of a test set, sample size, or data provenance for any diagnostic performance evaluation.
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 provided. No test set means no ground truth establishment for a diagnostic performance evaluation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not provided. No test set review process 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
- Not provided. The submission does not describe an MRMC study or any AI assistance feature for human readers. This device is a PACS workstation, not an AI/CAD diagnostic tool in the sense of providing specific interpretations or improving reader performance on a task.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not provided. The device described is a workstation for viewing and managing images, not a standalone AI algorithm that provides diagnostic findings independently.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable / Not provided. As no specific diagnostic performance study for an AI component is described, there's no mention of ground truth types.
8. The sample size for the training set
- Not provided. The device is a software platform, and the submission does not discuss machine learning or AI model training.
9. How the ground truth for the training set was established
- Not applicable / Not provided. As no AI training is discussed, ground truth establishment for a training set is not mentioned.
Summary of available information related to validation/testing based on the provided text:
The submission highlights the following quality assurance measures applied to the development, which are standard for software development and system validation, but do not constitute a clinical performance study with defined diagnostic acceptance criteria for an AI component:
- Risk Analysis
- Requirements Reviews
- Design Reviews
- Testing on unit level (Module verification)
- Integration testing (System verification)
- Final acceptance testing (Validation)
- Performance testing
- Safety testing
The core of the submission relies on the concept of substantial equivalence to predicate devices (K042525, K023178, K023100) rather than presenting novel clinical performance data for new AI algorithms. The device functions as a platform for image viewing and management, not as an AI-powered diagnostic aide.
§ 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).