(73 days)
The RAYPAX System is intended for the storage, reading, diagnostic review, analysis, annotation, distribution, printing, editing, and processing of digital images acquired from devices such as Computed Tomography (CT), Magnetic Resonance (MR), Computed Radiography (CR), Digital X-Ray (DX), Digital Mammography (MG), Ultrasound (US), Nuclear Medicine (NM), Positron Emission Tomography (PET), X-Ray Angiography (XA), Film Scanners, and any other DICOM supporting devices.
The clients of RAYPAX System are intended for diagnostic and analysis tool by trained healthcare professionals, including radiologists, physicians, technologists, clinicians and nurses. QCW(Quality control Workstation) is intended for technicians to verify exams. DW(Diagnostic Workstation) and RW(Review Workstation) is intended for radiologists to perform a diagnostic analysis of the exams and WCC(Web Client Component) is intended for the clinical review of physicians. Net Point and Lite are intended to acquire exams from remote facilities through the Internet. Net, Exp and Web client versions are intended for a remote access to the images through the Internet.
For the digital mammography images, to be viewed for primary interpretation, images must be acquired from an FDA approved Mammography device for primary interpretation and viewed on a display system with at least 5 Mega Pixel of resolution and has been cleared by the FDA for diagnosis of digital mammography images. Furthermore, the Mammography device must be able to provide, to the RAYPAX System, a viewable DICOM 'for presentation' mammography image. Images that are printed to film must be printed using a FDA approved printer for the diagnosis of digital mammography images.
The RAYPAX System is a complete PACS package to receive medical images from medical modalities, and distribute medical images and reports to enable medical staff to verify, diagnosis, and refer them in multi medical facilities. It consists of RAYPAX PACS server, Getaways and Clients.
RAYPAX PACS server stores the images and information obtained from the medical equipments and other systems, and provides a connection for RAYPAX client to access the information depending on their previledge level. Remote access through the Internet is allowed, and to ensure a secure data transfer, strong data encryption(SSL) is provided. All DICOM images acquired in the RAYPAX System are stored unaltered and all display manipulations and annotations are stored as presentation parameters and they do not alter the original image file.
RAYPAX Gateways communicate with medical modalities and other systems to receive and share image data, patient demographics, order schedule and study results. DICOM Gateway gathers medical exams from modalities and other system in DICOM format. Remote exams are gathered by Net Point or Lite locally and sent to PACS server through the internet. HL7 Gateway exchanges the patient and order information, study results with other information system in HL7 standard.
The clients of RAYPAX System are intended for diagnostic and analysis by trained healthcare professionals, including radiologists, physicians, technologists, clinicians and nurses. RAYPAX Clients connect the PACS server and enables medical staff to view medical data and assign special tasks in the PACS workflow.
OCW is a verification tool for a technician to reconstruct, verify exams. DW (Diagnostic Workstation) and RW (Review Workstation) are for the radiologist to perform diagnostic analysis of the exams. TW (Transcription Workstation) is a tool for the trancriptionist to create a preliminary report. WCC (Web Client Component) is a radiology referring tool for a physican to refer exam and report viewing at remote site. Net, Exp and Web versions of RAYPAX clients are intended to offer a remote access to the images through the Internet.
For PACS administrators, Admin provides with user management, server parameter setting, and Net Monitor provides the status of the PACS system and the performance of the medical organization.
Here's a breakdown of the acceptance criteria and the study information for the RAYPAX System, based on the provided text:
Acceptance Criteria and Reported Device Performance
The provided document is a 510(k) summary for a Picture Archiving and Communications System (PACS). For devices like PACS, acceptance criteria aren't typically defined by quantitative performance metrics (like sensitivity/specificity for a diagnostic algorithm) but rather by demonstrating substantial equivalence to a predicate device. This involves showing similar indications for use, technological characteristics, and safety/effectiveness.
Therefore, the "acceptance criteria" here is that the RAYPAX System is as safe, as effective, and performs as well as the predicate device (CENTRICITY PACS SYSTEM - K043415), and that any differences do not significantly influence safety and effectiveness.
| Acceptance Criteria (Demonstration of Substantial Equivalence) | Reported Device Performance (as claimed by RAYPAX) |
|---|---|
| Similar Indication for Use Statements: The device's intended purpose and target medical images/professionals should align with the predicate. | The RAYPAX System's indications for use are described as: "storage, reading, diagnostic review, analysis, annotation, distribution, printing, editing, and processing of digital images acquired from devices such as Computed Tomography (CT), Magnetic Resonance (MR), Computed Radiography (CR), Digital X-Ray (DX), Digital Mammography (MG), Ultrasound (US), Nuclear Medicine (NM), Positron Emission Tomography (PET), X-Ray Angiography (XA), Film Scanners, and any other DICOM supporting devices." It also specifies use by "trained healthcare professionals, including radiologists, physicians, technologists, clinicians and nurses" for various functions (e.g., QCW for technicians, DW/RW for radiologists, WCC for physicians). This aligns with the general purpose of a PACS, like the predicate. |
| Similar Technological Characteristics: The underlying technology, standards compliance, and functional components should be comparable. | The RAYPAX System is described as a "complete PACS package" consisting of a server, gateways, and clients. It stores images, provides secure remote access (SSL), stores manipulations as presentation parameters, and supports DICOM 3.0 and HL7. It's built on "standard Microsoft technology, general purpose software and hardware platform" using C#, C++, ASP, and Microsoft Dot NET framework. Key components include: |
- RAYPAX PACS Server: Stores images, information, and provides client access.
- RAYPAX Gateways: Communicate with modalities and other systems via DICOM and HL7 for image data, patient demographics, etc.
- RAYPAX Clients: For diagnostic and analysis by healthcare professionals (OCW, DW, RW, TW, WCC) and remote access (Net, Exp, Web versions).
The document explicitly states: "Both the predicative device and the RAYPAX system employs a database, an image storage, HL-7 interfacing and DICOM services. Images are acquired into the system from DICOM supporting devices." |
| Similar Safety and Effectiveness Profile: The device should not raise new questions of safety or effectiveness. This often involves demonstrating compliance with relevant standards and performing software validation. | The document states: "The RAYPAX System is as safe, as effective, and performs as well as the predicate devices. Any differences between the RAYPAX system and the substantially equivalent system have no significant influence on safety and effectiveness." It also mentions a "hazard analysis that there is no software component in the RAYPAX System that we know of whose failure or design flaw would result in death of injury to a patient, and the 'Level of Concern' of the RAYPAX System is 'minor'." The system "has no contact with the patient, nor does it control any life sustaining device." |
Study Details from the 510(k) Summary:
The provided document is a 510(k) Summary, which typically focuses on demonstrating substantial equivalence rather than reporting on a specific clinical study with detailed performance metrics. For a device like a PACS, the "study" is often a comparison of technical characteristics and functionalities to the predicate, along with software validation and hazard analysis. The document does not describe a traditional clinical study with patient cohorts, expert readers, or quantitative performance data like sensitivity/specificity.
Therefore, many of your requested details (sample size, data provenance, number of experts, adjudication, MRMC, standalone performance, ground truth types for test/training sets, training set sample size, how ground truth for training set was established) are not applicable or not provided in this 510(k) Summary because it relies on demonstrating equivalence through comparison to a predicate device and technical documentation, not through a clinical performance study as might be conducted for an AI diagnostic algorithm.
Here's what can be inferred or explicitly stated based on the document:
-
Sample size used for the test set and the data provenance: Not applicable/not provided. This document doesn't describe a test set of medical images with ground truth for performance evaluation in the way a diagnostic algorithm would. The "testing" referred to here for a PACS primarily involves software validation, functional testing, and verification of DICOM/HL7 compliance.
- Data Provenance: Not applicable.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable/not provided. No such ground truth establishment process is described.
-
Adjudication method for the test set: Not applicable/not provided.
-
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 MRMC study was done. This device is a PACS, which is infrastructure. It doesn't incorporate AI for diagnostic assistance that would be evaluated in an MRMC study.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The RAYPAX System is a PACS, which is designed to be used by human healthcare professionals. It is not an AI algorithm that provides standalone diagnostic assessments.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable/not provided. No ground truth in the context of diagnostic accuracy is discussed.
-
The sample size for the training set: Not applicable/not provided. As a PACS, there is no AI algorithm being "trained" on a dataset in the conventional sense.
-
How the ground truth for the training set was established: Not applicable/not provided.
§ 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).