Search Results

The DexTop Mammography Workstation is a mammography review workstation software package, which provides very high performance viewing, processing and analysis of multimodality two and three dimensional, as well as planar, medical image data.

The DexTop Workstation is designed to assist the radiologist in conducting screening and primary diagnosis through flexible, fast and efficient image hanging and processing of multimodality softcopy images with special emphasis and optimization for mammography.

When interpreted by a skilled physician, this software provides information that may be useful in screening and diagnosis. However, the final judgment must rely on the knowledge and skill of the physician.

The DexTop Mammography Workstation is a software product, which runs on a high end personal computer, for the purpose of non-invasive multi-modality review. It provides very high performance viewing, processing and analysis of multimodality two and three dimensional, as well as planar medical image data.

The DexTop Mammography Workstation receives digital image data from various sources including a variety of diagnostic imaging systems, Hospital PACS, Electronic media and local file systems.

The architecture of the DexTop Workstation means that it can be deployed as a central base station with satellite workstations all using the same user configuration store and image data.

The Dexela DexTop Mammography Workstation supports the following image network communications:

• Standard 10/100/1000 Base-T Ethernet protocols .
• . DICOM 3.0 Storage SCP and Query/Retrieve SCU.
• . TCP/IP network layer

The hardware configuration used with the software typically will include a PC, a single standard color monitor, a multi-function keypad (for increased productivity), and two high resolution monitors for mammographic Image review.

The provided text is a 510(k) summary for the DexTop Mammography Workstation. It describes the device, its indication for use, and technological characteristics. However, it does not contain specific acceptance criteria, performance metrics, or details of a study that proves the device meets such criteria.

The document states:

• "The non-clinical testing for the DexTop Workstation includes performance of system requirements testing according to the Software Testing Strategy and following the test cases as defined in the Software Requirements Test Specification Document."
• "Therefore Dexela is confident that the system as developed will perform according to the specifications detailed in the User Requirements Specification and System Requirements Specification."

This indicates that internal system requirements testing was performed, but the results, acceptance criteria, or specifics of these tests are not included in the provided summary. There is no information regarding a clinical study or a comparative study against a predicate device in terms of diagnostic performance (e.g., sensitivity, specificity, reader performance).

Therefore, based only on the provided text, I cannot provide the requested information in detail. I will answer the questions to the best of my ability with the available text, noting where information is missing.

Here's an analysis based on the provided text:

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

The provided 510(k) summary does not include a table of acceptance criteria or specific reported device performance metrics related to diagnostic accuracy or clinical effectiveness. It focuses on the device's functional capabilities and compliance with DICOM standards and regulatory requirements for a workstation.

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

The document mentions "non-clinical testing for the DexTop Workstation includes performance of system requirements testing," but it does not specify a sample size for a test set (e.g., number of images or cases) or the data provenance (e.g., country of origin, retrospective/prospective nature). These tests appear to be internal system-level and software verification tests, not clinical performance studies.

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

This information is not provided in the 510(k) summary. Given that the testing described is non-clinical system requirement testing, the concept of "ground truth" derived from expert consensus for diagnostic performance is not applicable within the scope of the provided text.

4. Adjudication method for the test set

This information is 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

A multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned in the provided text. The device is a workstation for viewing and processing images, not an AI diagnostic tool. Therefore, an "effect size of how much human readers improve with AI vs without AI assistance" is not applicable to the description of this device.

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

A standalone performance study of an algorithm is not described in the provided text. The device is a workstation, intended to be used by a "skilled physician" who makes the "final judgment."

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

The specifics of "ground truth" are not mentioned as the described testing is non-clinical system testing related to software functions and specifications, not diagnostic accuracy.

8. The sample size for the training set

Given that this is a workstation software product, and not an AI/CADe device, the concept of a "training set" in the context of machine learning or deep learning is not applicable or mentioned in the provided document.

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

As there is no mention of a training set for an AI/CADe algorithm, how ground truth for such a set was established is not applicable or mentioned.

Ask a specific question about this device