(75 days)
The Samsung RAYPAX™ Display Workstation is a device that receives digital images and data from various image sources, (including but not limited to CT Scanners, MR Scanners, Ultrasound Systems, R/F Units, Computed & Direct Radiographic devices, secondary capture devices, film scanners, imaging gateways, or other imaging sources). Images and data can be stored, communicated, processed, and displayed within the workstation or across computer networks at distributed locations.
The typical users of this system are trained professionals, including but not limited to physicians, nurses, and medical technicians.
The Display Workstation is one of the components of the RAYPAX, a PACS solution by Samsung or can be a separate device for other manufacturer's PACS. The Display Workstation provides image-processing functions and workflow for the radiology department for medical images that are acquired and stored in the RAYPAX image server in DICOM 3.0 format.
Furthermore, the Display Workstation can transfer medical images stored in RAYPAX system to other PACS through a DICOM compatible network and can export images to other applications in bitmap format.
This 510(k) submission (K992306) describes the Samsung RAYPAX™ Display Workstation System. However, it does not contain a study or data proving the device meets specific acceptance criteria in the manner you've requested for a modern AI/CADe device.
This submission is from 1999 for a "Digital Imaging Workstation" which is essentially a specialized computer for viewing medical images. It predates the widespread use of AI/Machine Learning in medical devices and the rigorous performance testing and reporting requirements we see today for such algorithms.
Here's a breakdown based on the information provided, highlighting why most of your requested points cannot be answered from this document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Not specified in this document. The submission focuses on substantial equivalence to a predicate device, primarily through technological characteristics and intended use. | No performance metrics (e.g., sensitivity, specificity, AUC) are reported. The document confirms the device functions as a display workstation for medical images. |
2. Sample size used for the test set and the data provenance
- Not applicable / Not specified. This type of device (a display workstation) does not typically undergo performance testing with a "test set" of medical images in the way an AI algorithm would. Its function is to display images, not to autonomously interpret them or produce diagnostic outputs.
- The document mentions receiving digital images from various sources (CT, MR, Ultrasound, etc.), but this refers to its functionality, not a test dataset for performance evaluation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable / Not specified. No ground truth establishment is mentioned because no performance study is detailed.
4. Adjudication method for the test set
- Not applicable / Not specified. No test set performance study is detailed.
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, an MRMC comparative effectiveness study was not done. This device is a display workstation, not an AI-powered diagnostic tool intended to assist human readers diagnostically.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- No, a standalone performance study was not done. The device's purpose is to display images for human interpretation, not to provide standalone diagnostic outputs. The document explicitly states: "A physician, providing ample opportunity for competent human intervention interprets images and information being printed."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable / Not specified. No performance study with ground truth is mentioned.
8. The sample size for the training set
- Not applicable / Not specified. This device is not an AI algorithm that requires a training set.
9. How the ground truth for the training set was established
- Not applicable / Not specified. No training set or ground truth establishment for a training set is mentioned.
Summary of the Study (as described in the 510(k) submission):
The "study" or justification for this device's acceptance is based on demonstrating substantial equivalence to a predicate device (Olicon Imaging Systems, Inc 02-Workstation & PACS View Software, K973959). The submission outlines:
- Device Description: What the device is and what it does (receives, stores, communicates, processes, and displays medical images in DICOM format).
- Indications for Use: The specific medical purposes for which the device is intended.
- Technological Characteristics: How it operates, noting it does not contact the patient, control life-sustaining devices, and that a physician interprets the images.
- Conclusion: The claim that the device is substantially equivalent to the predicate device, implying similar safety and effectiveness based on its technical features and intended use. The submission also mentions compliance with voluntary standards and a hazard analysis classifying potential hazards as "Minor."
In essence, this 510(k) application demonstrates that the Samsung RAYPAX™ Display Workstation performs the same functions, has similar technological characteristics, and is therefore as safe and effective as a previously cleared workstation. It does not involve the type of clinical performance study with specific acceptance criteria typically associated with AI/CADe 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).