Search Results

Image Management is intended to provide complete and scalable local and wide area PACS solutions for hospital and related institutions/sites, which will archive, retrieve, process and display medical images and data from hospital medical imaging and information systems. The device contains clinical applications that assist the processing, analyzing and comparing of medical images. It is a single device that integrates the review, dictation and reporting tools to create a productive work environment for the radiologists and physicians.

The Image Management viewers are used for patient exam management by clinicians in order to access and display patient data, medical reports, medical images from different modalities including but not limited to CR, DR, CT, MR, NM, ECG, US, MG*, DBT*, OP and OPT. The device provides wireless and portable access to medical images for remote reading or referral purposes from web browsers using current standard HTML.

*For primary interpretation and review of mammography images, only use display hardware that is specifically designed for and cleared by FDA for mammography.

Image Management V15 is a software based system and is intended to provide completely scalable local and wide area PACS (Picture Archiving and Communication System) solutions for hospital and related institutions/sites, which will archive, distribute, retrieve, process and display images and data from all hospital modalities and information systems. The device is to be used by trained professionals including, but not limited to, physicians and medical technicians. The device contains clinical applications that assist the processing, analyzing and comparing medical images. It is a single device that integrates review, dictation and reporting tools to create a productive work environment for the radiologists and physicians.

IM V15 supports receiving, sending, printing, storing and displaying studies received from the following modality types via DICOM (Digital Imaging and Communications in Medicine): Computed Tomography (CT), Magnetic Resonance (MR), Nuclear Medicine (NM), Ultrasound (US), X-Ray (XR), X-Ray Angiography (XA), Positron Emission Tomography (PET), Computed Radiography (CR), Digital Radiography (Abbreviation not defined by the DICOM standard) (DR) Radio Fluoroscopy (RF), Radiation Therapy (RT), Mammography (MG), Secondary Capture (SC), Visible Light (VL), Optical Coherence Tomography (OCT), Electrocardiogram (ECG) and Ophthalmic Photography (OP) as well as hospital/radiology information systems.

The provided document, a 510(k) summary for Philips Medical Systems' Image Management V15, does not contain the detailed information necessary to fully answer the request.

Specifically, an AI/algorithm-centric study proving the device meets acceptance criteria for specific performance metrics is not described. The document primarily focuses on demonstrating substantial equivalence to a predicate device (CARESTREAM PACS K110919) based on indications for use, technological characteristics, and compliance with general medical device standards.

However, based on the information provided, here's what can be inferred and what remains unknown regarding acceptance criteria and a "study" of device performance:

Acceptance Criteria and Reported Device Performance:

The document states that "Verification and validation tests have been performed to address intended characteristics, technological use. specifications and risk management results." and that "The test results in this 510(k) premarket notification demonstrate that Image Management v15 complies with the aforementioned international and FDA-recognized consensus standards and FDA guidance documents, and is substantially equivalent to the primary predicate device."

This implies that the acceptance criteria are tied to:

• Compliance with ISO 14971, IEC 62304, and NEMA PS 3.1-3.22 (DICOM Standard).
• Meeting "intended characteristics" and "technological specifications."
• Successful mitigation of risks identified through risk management.
• Demonstrating substantial equivalence to the predicate device.

Without explicit performance metrics (e.g., accuracy, sensitivity, specificity for a specific clinical task), a table of acceptance criteria and reported device performance cannot be generated as requested. The document doesn't provide quantitative results of these "verification and validation tests" beyond a statement of compliance.

*Study Information (Based on what is and is not in the document):

1. A table of acceptance criteria and the reported device performance:

   • Acceptance Criteria: As inferred above, these include compliance with specified standards (ISO 14971, IEC 62304, DICOM), meeting intended characteristics and technological specifications, and addressing risk management results. However, no specific quantitative performance metrics (e.g., accuracy, precision, recall) are listed as acceptance criteria, nor are their corresponding reported device performance values provided.
   • Reported Device Performance: Not explicitly stated in quantitative terms in this summary. The summary focuses on compliance and equivalence, not on specific performance results that would be typically seen in a study evaluating an AI algorithm's diagnostic capabilities.

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

   • Not provided. The document mentions "verification and validation tests" but gives no details about the data (e.g., sample size, type of images, country of origin, retrospective/prospective collection). Given the nature of the device as an "Image Management System" (PACS), the testing might involve functional performance, data integrity, and display capabilities rather than diagnostic accuracy on a specific disease.

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

   • Not provided. Ground truth establishment is typically relevant for diagnostic AI algorithms. Since this is an image management system, the "ground truth" for its testing would likely be related to correct image archiving, retrieval, processing, and display, rather than a clinical diagnosis.

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

   • Not provided. Adjudication methods are relevant for establishing ground truth in diagnostic studies, which is not described here.

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 evidence of an MRMC comparative effectiveness study involving AI assistance and human readers is present. The device is described as an "Image Management System" with "clinical applications that assist the processing, analyzing and comparing medical images." While it processes images, it is not described as an AI intended to directly assist or augment human diagnostic performance in the way an AI CADx (Computer-Aided Detection/Diagnosis) system would. Therefore, an MRMC study aimed at quantifying human improvement with AI assistance would not be applicable or described for this type of device based on this summary.

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

   • No evidence of a standalone algorithm performance study is present. Again, the summarized device appears to be a PACS system, not a standalone diagnostic AI algorithm.

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

   • Not explicitly stated and likely not applicable in the typical diagnostic sense. For an image management system, "ground truth" would relate to the correctness of data handling, image fidelity, display accuracy, and functionality as per DICOM standards and internal specifications, rather than a clinical diagnosis confirmed by pathology or outcomes.

8. The sample size for the training set:

   • Not applicable and not provided. This device is described as a software system primarily for image management. While it may contain "clinical applications that assist the processing, analyzing and comparing medical images," it is not described as a deep learning or machine learning-based AI that requires a "training set" in the conventional sense for a diagnostic task.

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

   • Not applicable and not provided. (See point 8).

In Summary:

The provided document describes a 510(k) submission for an "Image Management V15" system, which is a PACS. The focus of the submission is on demonstrating substantial equivalence to an existing predicate device and compliance with general medical device standards for software and risk management. It does not describe a clinical study of an AI algorithm with specific diagnostic performance acceptance criteria, test sets, or ground truth establishment relevant to AI diagnostic capabilities. The "clinical applications" mentioned within the PACS are for "processing, analyzing and comparing medical images" and would likely refer to standard image manipulation tools (e.g., 3D reconstruction, volume matching, MPR) rather than novel AI diagnostic algorithms requiring specific performance validation studies as requested in the prompt.

Ask a specific question about this device

eUnity is a software application that displays medical image data and associated clinical reports to aid in diagnosis for healthcare professionals. It performs operations relating to the transfer, storage, display, and measurement of image data.

eUnity allows users to perform image manipulations, including window/level, rotation, measurement and markup. eUnity provides 2D display, Multi-Planar Reformating and 3D visualization of medical image data, and mobile access to images.

eUnity displays both lossless and lossy compressed images. For lossy images, the medical professional user must determine if the level of loss is acceptable for their purposes. Display monitors or mobile devices used for reading medical images for diagnostic purposes must comply with applicable regulatory approvals and with quality control requirements for their use and maintenance. For mobile diagnostic usage when a full workstation is not available.

Mobile usage for mammography is for reference and referral only.

Client Outlook has developed eUnity to load, display and manipulate medical (DICOM) images within a web-browser without installing client software. eUnity is a server-based software solution that extends common web-browsers on the most popular operating systems into medical review stations; removing a technical barrier that had long been a key contributor to poor medical image access.

eUnity is an enterprise medical image viewer that provides access to full quality images from anywhere using nothing more than a standard web browser. Combined with a calibrated monitor, it can be used to make diagnostic decisions. Secure, fast, immediate access to information means less time spent searching for specialized workstations and supports greater efficiency for care, greater collaboration, and faster turnaround times.

This device is the successor to eUnity predicate (K161515) and adds the following functionality: MIP/MPR/3D and Mobile Diagnostic Use.

Here's a breakdown of the acceptance criteria and study information for the eUnity device based on the provided text, structured to answer your specific questions.

1. Table of Acceptance Criteria and Reported Device Performance

The provided document (K172490) is a 510(k) summary for a medical image processing software (eUnity). It's primarily a comparison document to demonstrate substantial equivalence to predicate devices rather than a detailed report of a performance study with numerical acceptance criteria. The "acceptance criteria" here are implied by the comparison to already cleared predicate devices and the statement that the device "meets its design requirements and intended use, and that it is safe and effective."

The capabilities added to the new eUnity version (K172490) are:

• MIP/MPR/3D functionality
• Mobile Diagnostic Use

The reported performance is qualitative and based on clinical validation:

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

• Test Set Sample Size: The document does not specify a numerical sample size (e.g., number of images, number of cases) for the "Additional Clinical Validation testing." It mentions "several different hardware devices" and testing "on several different hardware devices."
• Data Provenance: Not explicitly stated whether the data used for clinical validation was retrospective or prospective, nor its country of origin.

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

• Number of Experts: The document states "multiple team members" performed verification and validation activities, and "trained radiologists" performed the clinical validation. It also notes "consensus among all the Radiologists." The exact number of radiologists involved is not specified, but it implies more than one.
• Qualifications of Experts: The experts are identified as "trained radiologists." No further details on their years of experience or specific subspecialties are provided.

4. Adjudication Method for the Test Set

• The document states, "There was consensus among all the Radiologists that the same diagnosis would be made on the mobile device with eUnity as on the predicate device in various lighting conditions." This indicates a consensus-based adjudication method, but the specific process (e.g., initial independent reads followed by a consensus meeting, voting, etc.) is not detailed. It implies that agreement was reached among the radiologists.

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, particularly one measuring the improvement of human readers with AI assistance, was not conducted or reported. This device is a medical image viewing and processing software, not an AI-powered diagnostic aid. The clinical validation was a comparison of diagnostic capability on different platforms (mobile with eUnity vs. predicate device).

6. If a Standalone (i.e. algorithm only without human-in-the loop performance) Was Done

• No, a standalone (algorithm-only) performance study was not conducted as this device is a viewing platform and requires human interpretation for diagnosis. Its intended use states "a licensed medical practitioner reviews the output, providing ample opportunity for competent human intervention for the interpretation of images and information being displayed."

7. The Type of Ground Truth Used

• The ground truth for the clinical validation appears to be the diagnosis made using an existing predicate device/workstation. The test aimed to determine if "the same diagnosis would be made on the mobile device with eUnity as on the predicate device." This suggests the predicate's output served as the reference.

8. The Sample Size for the Training Set

• This document describes a 510(k) submission for a software that displays and manipulates medical images. It is not an AI/ML device in the sense of requiring a "training set" to learn diagnostic patterns. Therefore, there is no mention of a training set or its sample size. The software's functionality is based on established imaging principles and display technologies, not learned algorithms from a dataset.

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

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

Ask a specific question about this device