Search Results

This device is to serve as a workstation for the capture, storage, review and analysis of ultrasound images, both still and dynamic. This devices is designed to support functional diagnósis by performing display, processing, measurement and analysis of ultrasound images.
Retrieval and storage of both passive and active ultrasound images
Analysis of ultrasound images

The UIWS-300A, Ultrasound Workstation, is an all digital workstation that can be connected to Toshiba PowerVision diagnostic ultrasound scanners. Its function is to provide the user with the ability to view images, annotate image data and perform analysis on image data. The unit is comprised of a standard desktop type personal computer, keyboard, mouse, monitor and connecting cables.

This 510(k) submission describes an Ultrasound Workstation, UIWS-300A, which is an all-digital workstation designed to capture, store, review, and analyze ultrasound images. It is not a device that uses an AI algorithm to perform diagnosis or analysis, but rather a tool for human users to perform these functions. Therefore, many of the typical acceptance criteria and study elements associated with AI/ML-enabled devices are not applicable.

Here's an analysis based on the provided text, while acknowledging the device's nature:

1. Table of Acceptance Criteria and Reported Device Performance

As this is a workstation for viewing and analyzing images, the 'acceptance criteria' are primarily related to its functional performance and compliance with relevant standards, rather than diagnostic accuracy metrics like sensitivity or specificity.

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

This information is not provided in the submission. For a device like this, the "test set" would likely refer to a set of images or data used to verify the proper functioning of the workstation's display, storage, and analysis tools. The submission focuses on functional conformance and substantial equivalence, not retrospective or prospective studies on diagnostic accuracy.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This information is not provided and is not applicable for this type of device. The UIWS-300A is a tool that allows human experts (e.g., radiologists, sonographers) to analyze images. It does not generate its own "ground truth" or diagnostic output that would require expert consensus for verification in the context of FDA clearance.

4. Adjudication Method for the Test Set

This information is not provided and is not applicable for this type of device. Adjudication methods like 2+1 or 3+1 are used in studies where multiple human readers or an AI algorithm make a diagnostic call, and discrepancies need to be resolved to establish a definitive ground truth.

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

A MRMC comparative effectiveness study was not done and is not relevant for this device. Such studies are typically performed for AI/ML diagnostic tools to assess whether the AI improves human reader performance (e.g., sensitivity, specificity, reading time). The UIWS-300A is a workstation, not a diagnostic AI.

6. Standalone (Algorithm Only) Performance Study

A standalone performance study was not done and is not applicable. This device is a workstation designed for human interaction; it does not have a standalone algorithm that performs diagnostic tasks independently of a human operator. Its performance is related to its ability to display, store, and process images as intended.

7. Type of Ground Truth Used

The concept of "ground truth" as a diagnostic reference (e.g., pathology, outcomes data) is not applicable to this device in the context of its regulatory clearance. The "ground truth" for this device's performance would be against functional specifications and standards (e.g., does it accurately display DICOM images? Does it perform measurements correctly?).

8. Sample Size for the Training Set

This information is not provided and is not applicable. As a workstation, the UIWS-300A does not employ machine learning or AI algorithms that require a "training set" of data in the diagnostic sense. Its development involved software engineering and hardware integration, not data-driven model training.

9. How Ground Truth for the Training Set Was Established

This information is not provided and is not applicable. Since there is no "training set" in the context of machine learning, there is no process for establishing its ground truth.

In summary, the provided 510(k) submission for the Toshiba UIWS-300A Ultrasound Workstation focuses on demonstrating substantial equivalence to a predicate device and compliance with relevant technical standards for image handling, display, and safety. It is not an AI/ML diagnostic device, and therefore, many of the typical study elements for such devices (e.g., expert reads, ground truth adjudication, training/test sets, MRMC studies) are not present or relevant.

Ask a specific question about this device