K Number
K211257
Date Cleared
2021-09-10

(137 days)

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

EFAI PACS PICTURE ARCHIVING AND COMMUNICATION SYSTEM is intended to be used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The EFAI PACS PICTURE ARCHIVING AND COMMUNICATION SYSTEM displays, processes, stores, and ransfers medical data from original equipment manufacturers (OEMs) that support the DICOM standard, with the exception of mammography. It provides the capability to store images and patient information from OEM equipment, and perform filtering, digital manipulation and quantitative measurements. The client software is designed to run on standard personal and business computers. The product is intended to be used by trained medical professionals, including but not limited to radiologists. oncologists, and physicians. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not diagnosis or potential findings.

Device Description

The software is a stand-alone software as medical device (Stand-alone SaMD) which provide to instant services for clinician can able to use web browser at client stations to search and view medical data of desired patient which is stored in the software also provides the following visualization, annotation and quantification functionalities which can be applied to the images on the web browser at client stations:

Visualization Functionalities:

  • a). 2D image view
  • b). Zoom ratio adjust
  • c). Pan
  • d). Window Level and Window Width adjust
  • e). Positive & Negative film effect
  • f). Mirror Flip
  • g). Multi-screen display
  • h). Cine Loop Play

Annotation Functionality:

  • Point Annotation

Quantification Functionalities:

  • a). Distance measurement
  • b). Area measurements
  • c). Angle measurement
  • d). Single Point measurement
AI/ML Overview

The provided document, a 510(k) Premarket Notification for the EFAI PACS Picture Archiving and Communication System, primarily focuses on demonstrating substantial equivalence to a predicate device (Arterys Viewer K171544) rather than presenting a detailed study proving the device meets specific acceptance criteria through extensive empirical performance testing.

The document explicitly states on page 7, Section 5.8 "Performance Date - Clinical": "EFAI PACS did not require clinical study since substantial equivalence to the currently market and predicate device was demonstrated with the following attribute: Design features; Indications for Use; Fundamental scientific technology; Non-clinical performance testing; Safety and effectiveness."

Therefore, a table of acceptance criteria and reported device performance based on a dedicated clinical study cannot be extracted from this document, as such a study was not performed for this 510(k) submission.

Instead, the submission relies on the successful completion of non-clinical tests (software verification and validation, usability engineering) and a clinical evaluation based on existing literature and adverse event data to support substantial equivalence.

Here's an analysis of the provided information concerning the device's acceptance, focusing on what can be extracted:


1. Table of Acceptance Criteria and Reported Device Performance (as inferred from Non-Clinical Testing and Equivalence Claim):

Since no specific "performance criteria" for a clinical study are provided, the acceptance criteria are implicitly those of demonstrating substantial equivalence to the predicate device and meeting software/usability standards.

Acceptance Criteria (Implied)Reported Device Performance (as stated in document)
Non-Clinical Performance:
Software Verification & Validation (IEC 62304/FDA Guidance)"Results confirm that the design inputs and performance specifications for the device are met. The EFAI PACS passed the testing in accordance with internal requirements, national standards, and international standards shown below, supporting its safety and effectiveness, and its substantial equivalence to the predicate device." (Page 7, Section 5.7) "In Compliance with." (Page 7, Section 5.7)
Usability Engineering (IEC 62366-1 & 62366-2)"In Compliance with." (Page 7, Section 5.7)
Clinical Performance (via Equivalence and Evaluation):
Substantial Equivalence to Predicate Device (Arterys Viewer K171544) for indicated uses and technological characteristics, without raising new safety/effectiveness questions."EFAI PACS did not require clinical study since substantial equivalence to the currently market and predicate device was demonstrated with the following attribute: Design features; Indications for Use; Fundamental scientific technology; Non-clinical performance testing; Safety and effectiveness." (Page 7, Section 5.8)
"The EFAI PACS has the same intended use as the Arterys Viewer, and the same or similar technological characteristics. The differences in technological characteristics do not raise new or different questions of safety and effectiveness. Performance testing has demonstrated the EFAI PACS is as safe and effective as the predicate device. Therefore, the EFAI PACS is substantially equivalent to the predicate device." (Page 8, Section 5.9)

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

  • Sample Size: Not applicable in the context of a prospective clinical performance study. The document refers to "non-clinical tests" and a "clinical evaluation" which relied on existing data.
  • Data Provenance: Not explicitly stated as a sampled test set. The clinical evaluation involved reviewing "adverse event data base search results" and "three clinical articles mentioned in the CEP and CER" (Page 8, Section 5.8). The country of origin for these databases or articles is not specified. It's retrospective analysis of existing information.

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

  • Not applicable. No new test set requiring expert ground truth establishment was used for performance validation in a clinical study. The clinical evaluation relied on existing literature and adverse event data.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

  • Not applicable. No test set requiring adjudication of findings was used for a clinical study.

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, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. The device is a PACS system for image management, display, and basic manipulation, not an AI-assisted diagnostic tool. Its functionality explicitly states it "does not directly generate any diagnosis or potential findings" (Page 4, Section 5.4).

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

  • The device itself is a "Stand-alone Software as Medical Device (SaMD)" (Page 4, Section 5.5). However, a standalone performance test in the sense of an algorithm producing diagnostic output was not done because the device's function is as an image management system, not a diagnostic AI. The non-clinical testing verified its functional performance (e.g., display, measurement accuracy, DICOM compliance).

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

  • For functional non-clinical tests: The "ground truth" would be against design specifications and expected outputs for image display, processing, storage, and measurement tools. This would be established through internal verification and validation procedures.
  • For the clinical evaluation: It relied on available "adverse event data base search results" and data from "three clinical articles," which represent existing clinical information rather than a newly established ground truth for device performance.

8. The sample size for the training set:

  • Not applicable. This is a PACS system, not a machine learning algorithm that learns from training data for diagnostic or predictive tasks.

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

  • Not applicable, as there is no training set for this type of device.

In summary, the EFAI PACS 510(k) submission primarily demonstrates safety and effectiveness through substantial equivalence to an existing predicate device and compliance with relevant software and usability engineering standards, rather than through a dedicated clinical performance study with defined acceptance criteria and a test set.

§ 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).