K Number
K092125
Device Name
PRESIDIO PACS
Date Cleared
2009-12-10

(148 days)

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

The Presidio PACS software is intended for the manipulation, management, and display of medical images. It can manage and display images from different modalities and interfaces and can distribute those images to various workstation, image storage and printing devices using DICOM or similar standards. Typical users of this system are trained medical professionals, including physician, nurses, technicians and computer system professionals.

To support the diagnostic interpretation of mammography studies, Presidio PACS will display the full fidelity DICOM image in a non-compressed format. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5Mpixel resolution and meets other technical specifications reviewed and accepted by FDA. Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary diagnosis or image interpretation.

It is the user's responsibility to ensure quality, ambient light conditions and image compression ratios are consistent with the clinical application.

Device Description

The Presidio PACS include the following major components: Workstation, Enterprise and RIS.

The Presidio PACS workstation is used to view, edit, manipulate, annotate, analyze, store and distribute images and data that are stored and managed in the Presidio PACS Enterprise for diagnosis. This software-based product provides capabilities for the acceptance, transmission, printing, display, storage, editing and digital processing of medical images and associated data.

All acquired image data is preserved in the format in which it is received. Changes may be made to the presentation of the images. These changes are saved as display definitions only and do not alter the acquired image pixel data. Any and all display definitions applied to an image can always be reversed to the acquired state.

The Presidio PACS workstation may also be used in a remote location, away from the healthcare facility, as long as the workstation has the ability to connect, via network, to the primary healthcare facility where the Presidio PACS Enterprise is located.

The Presidio PACS Workstation extends its diagnostic and productivity capabilities into the mammography reading environment and may also be used for the primary interpretation of digital mammography images with a FDA approve 5MP monitor.

The Presidio PACS Workstation has a modular software architecture which allows adding addition feature or enhancements in the form of plug-ins without any modification to the existing software code base.

Presidio PACS Enterprise software delivers a complete, scalable storage solution for diagnostic images. Images can be stored in uncompressed, lossless or lossy. The system also has the ability to send data to DICOM ready devices via the DICOM standard protocol. It is a DICOM compliant solution for image storage, retrieval and transmission. The Enterprise Archive provides redundancy in long-term storage in several ways, including Redundant Archives, Media Copy, and Application Service Provider (ASP) Archive.

Presidio RIS provides a hospital or clinic with automated tools to electronically schedule and manages patient exam information. The Presidio RIS utilizes a Workstation client that provides referring physicians the added flexibility to instantly view and schedule their own patients' radiographic services.

The Presidio PACS software application is a software only solution and will use 'off the shelf' PC and server hardware technology that meets defined minimum specifications.

AI/ML Overview

Here's an analysis of the provided text regarding the acceptance criteria and study for the Presidio PACS device:

1. Table of Acceptance Criteria and Reported Device Performance:

The provided document does not explicitly state specific numerical acceptance criteria for performance metrics like sensitivity, specificity, or accuracy. It focuses on functional equivalence to predicate devices and software validation. The "reported device performance" is primarily articulated through the comparison table against predicate devices and the general statement about software validation.

Acceptance Criterion (Inferred from comparison to predicates and general descriptions)Reported Device Performance (as stated in the document)
Functional Equivalence:
Communications (TCP/IP)YES (vs. YES for predicates)
Image Archive capabilitiesYES (vs. YES for predicates)
Image Processing capabilitiesYES (vs. YES for predicates)
Image Edit capabilitiesYES (vs. YES for predicates)
Edit Patient DemographicsYES (vs. YES for predicates)
Add and remove imagesYES (vs. YES for predicates)
Combine studiesYES (vs. YES for predicates)
Edit Patient Orientation InformationYES (vs. YES for predicates)
Set and Edit Routing InformationYES (vs. YES for predicates)
JPEG Lossy/Lossless CompressionYES (vs. YES for predicates)
JPEG 2000 Lossy/Lossless CompressionYES (vs. YES for ImageSVR, NO for DATACOM DC-PACS)
Image SegmentationYES (vs. YES for predicates)
Image SmoothingYES (vs. YES for predicates)
Window Level, Pan, Zoom, Variable Smooth Filter, Cine DisplayYES (vs. YES for predicates)
DICOM PrintYES (vs. YES for predicates)
Safety:
No patient contactMeets (stated that device has no patient contact)
Utilized by trained professionalsMeets (stated that device is utilized only by trained professionals)
"Off-the-shelf" hardwareMeets (stated that device uses "off-the-shelf" PC and server hardware)
Compliance with electrical safety standardsMeets (stated that device complies with applicable electrical safety standards)
Software Validation:
Ability to meet intended use and specificationsConfirmed (stated "Software validation has established the device's ability to meet its intended use and established specifications.")
Risk analysis and potential hazards classificationMinor (stated that risks analysis and potential hazards have been classified Minor)
Mammography Interpretation:
Display full fidelity DICOM imageMeets (stated that device displays full fidelity DICOM image in non-compressed format)
Requires FDA approved 5MP monitorMeets (stated that mammographic images interpreted using FDA approved 5MP monitor)
Lossy compressed/digitized film screen images NOT for primary diagnosisPolicy adhered to (stated these images must not be reviewed for primary diagnosis)

2. Sample Size Used for the Test Set and Data Provenance:

The document does not specify a sample size for any test set or provide details on data provenance (e.g., country of origin, retrospective/prospective). The evaluation is primarily based on functional equivalence to predicate devices and general software validation.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

The document does not mention the use of experts to establish ground truth for a test set. The evaluation relies on direct comparison of features and capabilities with predicate devices and internal software validation processes.

4. Adjudication Method for the Test Set:

Since no expert review or specific test set with ground truth is described, there is no adjudication method mentioned.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

A MRMC comparative effectiveness study was NOT done according to this document. The submission focuses on substantial equivalence based on technological characteristics and functional comparison to predicate devices, not on the impact of AI assistance on human readers.

6. Standalone (Algorithm Only) Performance Study:

The document does not describe a standalone (algorithm only) performance study. The device, Presidio PACS, is a Picture Archiving and Communication System, which is a software platform for image management and display, not an AI algorithm designed to make diagnostic predictions independently. The document explicitly states: "The software does not provide any diagnostic assistance to the physician. Any diagnostic determination or treatment is solely determined by a physician and not the software."

7. Type of Ground Truth Used:

No specific "ground truth" (e.g., pathology, outcomes data, expert consensus) is mentioned as being used for performance evaluation in the context of this 510(k) submission. The evaluation centers on functional compliance and equivalence, not diagnostic accuracy of an AI component.

8. Sample Size for the Training Set:

The document does not mention a training set or its sample size. As a PACS system, it handles various medical images but does not involve training an AI model on a dataset in the way a diagnostic AI algorithm would.

9. How the Ground Truth for the Training Set Was Established:

Since there is no mention of a training set, the method for establishing its ground truth is not applicable/described.


Summary of the Study:

The study proving the Presidio PACS meets acceptance criteria is primarily a software validation and substantial equivalence comparison against two predicate devices (ImageSVR PACS and DATACOM DC-PACS).

The key elements of the study are:

  • Functional Comparison: Demonstrated that Presidio PACS possesses the same core functionalities (image archiving, processing, editing, communication, compression, DICOM capabilities) as its predicates.
  • Safety Assessment: Declared that the device has no patient contact, is used by trained professionals, utilizes "off-the-shelf" hardware, and complies with electrical safety standards.
  • Risk Analysis: Concluded that the risks and potential hazards were classified as "Minor."
  • Software Validation: Stated that software validation confirmed the device's ability to meet its intended use and established specifications.

This submission focuses on the system's capabilities and safety as an image management and display platform rather than the diagnostic performance of an AI component. Therefore, many of the typical performance metrics and study designs associated with AI devices (like specific sample sizes, ground truth establishment, or MRMC studies) are not present in this 510(k).

§ 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).