K Number
K031473
Date Cleared
2003-10-30

(174 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Rational Imaging PACS is intended for use by a physician or other medical professionals in the acquisition of medical images and demographic detail from all institutional imaging modalities, including CT, MRI, NM, DR, US, nuclear medicine, Angio and secondary capture devices such as film digitizers or other imaging sources. The acquired medical images and demographic information may be displayed, processed, reviewed optionally utilizing Multi-planar Reconstruction (MPR), Anatomic Triangulation (AT) and 3D display, sent to and retrieved by radiologists at remote sites, stored, archived or printed.

Device Description

Rational Imaging PACS is designed for use by a physician or other medical professionals in the acquisition of medical images and demographic detail from all institutional imaging modalities, including CT, CR, MRI, NM, DR, US, Angio, nuclear medicine, and secondary capture devices such as film digitizers or other imaging sources. The acquired medical images and demographic information may be displayed, processed, reviewed, sent to and retrieved by radiologists at remote sites, stored, archived or printed. Multi-planar Reconstruction (MPR). Anatomic Triangulation (AT) and 3D display are optionally available.

AI/ML Overview

The provided text describes a 510(k) summary for the Rational Imaging PACS. However, it does not contain specific acceptance criteria, performance data from a study, or details about such a study (sample size, expert qualifications, adjudication methods, MRMC study, standalone performance, ground truth types, or training set details).

The document primarily focuses on establishing substantial equivalence to a predicate device (Algotec Systems Ltd.'s MediSurf) based on functional and technical similarities. It discusses the device's intended use, safety, and general description.

Here's a breakdown of the requested information based on the provided text:


Acceptance Criteria and Device Performance Study

The provided document does not specify numerical acceptance criteria for performance (e.g., accuracy, sensitivity, specificity, processing speed targets, or image quality metrics) or detail a specific study proving the device meets such criteria.

The submission focuses on demonstrating substantial equivalence to a predicate device (Algotec Systems Ltd.'s MediSurf) by highlighting that both are software suites that process DICOM compliant images and provide comparable features for image processing, archiving, and networking.

Given the nature of a Picture Archiving and Communication System (PACS) as a foundational imaging infrastructure product, the "performance" demonstrated for regulatory purposes here is primarily its ability to perform its stated functions reliably and safely, similar to its predicate. This typically involves software validation and verification against functional specifications rather than a clinical performance study with specific metrics like those for a diagnostic AI algorithm.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance CriteriaReported Device Performance
Not explicitly stated as quantifiable metrics in the document. The overarching "acceptance criterion" from a regulatory perspective is substantial equivalence to the predicate device in terms of intended use, technological characteristics, and safety and effectiveness.Fulfills the functions described for a PACS system: acquisition, display, processing, review, transmission, storage, archiving, and printing of medical images and demographic information. The device is described as "DICOM compliant" and having "comparable" image manipulation tools and storage techniques to the predicate.

2. Sample size used for the test set and the data provenance:

  • Not applicable / Not provided. The document does not describe a clinical performance study with a test set of medical images. The evaluation appears to be based on functional verification and validation of the software's capabilities and compliance with standards (e.g., DICOM).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

  • Not applicable / Not provided. This information is relevant for clinical performance studies, which are not detailed in this submission.

4. Adjudication method for the test set:

  • Not applicable / Not provided. This information is relevant for clinical performance studies, which are not detailed in this submission.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance:

  • No. The document does not mention an MRMC study. This type of study is more common for diagnostic AI algorithms rather than a PACS system, which provides infrastructure for image management.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

  • Not applicable / Not provided. The Rational Imaging PACS is an infrastructure system for managing and displaying images, not a standalone diagnostic algorithm. Its "performance" is inherently tied to its functionality as a system.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

  • Not applicable / Not provided. Ground truth is used in performance studies to validate diagnostic or predictive algorithms. This document describes a PACS system, for which the "ground truth" would be its adherence to functional specifications and industry standards like DICOM.

8. The sample size for the training set:

  • Not applicable / Not provided. This document does not describe the development or training of an AI algorithm based on a training set of medical images.

9. How the ground truth for the training set was established:

  • Not applicable / Not provided. Similar to point 8, this document does not describe the training of an AI algorithm.

Summary of the Study (or Lack thereof, in the context of performance metrics):

The provided 510(k) summary for the Rational Imaging PACS describes a regulatory submission focused on demonstrating substantial equivalence to a predicate device (MediSurf, K971347). The "study" in this context is a comparison of the Rational Imaging PACS's intended use, technological characteristics (e.g., DICOM compliance, image manipulation tools, networking, archiving capabilities), and safety measures against those of the predicate device.

The document states: "The proposed Rational Imaging PACS... and the predicate device MediSurf are both software suites that process DICOM compliant images and provide a standard set of features pertaining to image processing, archiving and networking. The image manipulation tools and storage techniques are essentially comparable."

Safety is addressed by a risk management plan, software development and validation process, and verification plan.

Therefore, the "proof" the device meets its "acceptance criteria" (which are implicit in the concept of substantial equivalence for a PACS) is through this detailed comparison of features and capabilities to a legally marketed predicate device, rather than a clinical performance study with quantitative metrics.

§ 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).