Search Results

UbiPACS™ by ICM Co. Ltd. is a device that receives medical images (including mammograms) and data from various imaging sources. Images and data can be stored, communicated, processed and displayed within the system or across computer networks at distributed locations. Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA approved monitor that offers at least 5 Mpixel resolution and meets other technical specifications reviewed and accepted by FDA. Typical users of this system are trained professionals, i.e. physicians, radiologists, nurses, medical technicians, and assistants.

The system is a server-based software application. UbiPacs™ is a distributed image management system that manages the archival, retrieval, and distribution of medical images within a Picture Archiving and Communication System (PACS) environment. UbiPacs™ provides network access to patients' current and historical radiological images and relevant examination data. The system is designed for facilitating the clinical practice of radiologists and physicians. UbiPacs™ implementation is based on the Digital Imaging and Communication in Medicine (DICOM) standard. The standard allows communications of images and relevant information such as patient demographics and examination data between the system and other DICOM-compliant imaging devices such as CT scanners, MR imager, CR systems, digital modalities and image viewing workstations.

The provided text is a 510(k) summary for the UbiPACS™ device, which is a Picture Archiving Communications System. Based on the document, this device is a software application for managing medical images and data.

The document does not contain information about specific acceptance criteria related to performance metrics (e.g., sensitivity, specificity, accuracy) that would typically be associated with AI or CADx devices. It primarily focuses on demonstrating substantial equivalence to a predicate device (SmartPACS™) and describing the device's intended use and technological characteristics as a PACS system.

Therefore, many of the requested items related to performance studies, sample sizes, expert qualifications, and ground truth establishment for AI/CADx devices are not applicable or not provided in this regulatory submission.

Here's a breakdown of the information available based on your request:

1. Acceptance Criteria and Reported Device Performance

The document does not specify quantitative acceptance criteria or reported device performance in terms of clinical accuracy (e.g., sensitivity, specificity, AUC) for the UbiPACS™ system. As a PACS system, its "performance" is generally related to its ability to store, retrieve, communicate, and display images effectively in compliance with standards like DICOM. The acceptance criteria for such a device are typically related to:

• Functionality: Does it perform the stated functions (archiving, retrieval, distribution, display)?
• Interoperability: Does it comply with DICOM standards to communicate with other compliant devices?
• Safety/Risk Mitigation: Is it designed to minimize potential hazards (e.g., preventing loss of data, ensuring proper image display as per regulations)?
• Substantial Equivalence: It must be as safe and effective as a legally marketed predicate device.

The "reported device performance" is essentially that it "contains adequate information and data to enable FDA - CDRH to determine substantial equivalence to the predicate device."

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

Not applicable/Not provided. This is a PACS system, not a device that processes images to produce a diagnostic output that would be evaluated with a test set of medical cases. The "test set" would likely be a functional verification and validation of the software itself.

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

Not applicable/Not provided. As above, this information is typically relevant for diagnostic AI/CADx devices, not for a PACS system which manages and displays images.

4. Adjudication method for the test set

Not applicable/Not provided.

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. The document does not describe any MRMC or comparative effectiveness study involving human readers or AI assistance. The device is a PACS system, not an AI or CADx tool designed to assist human interpretation.

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

Not applicable. The UbiPACS™ device is a PACS system, not a standalone diagnostic algorithm. The description explicitly states a physician interprets images, "providing ample opportunity for competent human intervention."

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

Not applicable. Ground truth generation is not relevant for a PACS system in the same way it is for a diagnostic algorithm. The "truth" for a PACS is whether it correctly stores, retrieves, and displays the original image data and metadata.

8. The sample size for the training set

Not applicable/Not provided. PACS systems are not typically "trained" in the machine learning sense with a "training set" of medical images for diagnostic purposes. Their development involves software engineering, testing, and validation against functional specifications and standards.

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

Not applicable/Not provided.

Ask a specific question about this device