Search Results

The Tractus TissueMapper Reviewer Application provides two and three-dimensional image review, manipulation, and analysis tools to assist users in screening, diagnosis, planning and performing image-guided interventional procedures. The supported imaging modality is Ultrasound (US). Images and data are received from various imaging systems and other sources such as calibrated spatial positioning devices.

This device provides the capability to overlay annotations on 2D or 3D medical image displays. These annotations may represent the position of instruments including but not limited to imaging probes or other tracked devices.

This device is intended to assist skilled medical professionals in clinical screening and interventions, for anatomical structures where imaging is currently used for visualizing such structures, including head and neck, breast, thoracic, and abdominal applications.

The TissueMapper Reviewer Application is an electronic image review and reporting software program intended to operate on a Windows Operating System (OS) computer. The device allows the review of previously recorded ultrasound examinations which are performed using standard ultrasound systems and other sources such as calibrated spatial positioning devices, the images of which were recorded digitally.

The images are displayed on a computer monitor. The images may be reviewed individually or as a self-playing sequence (video clip). Certain image functions may be adjusted by the software, such as image brightness, image contrast and image size magnification or reduction. The speed of the video presentation may be adjusted by the software.

The device software presents sequences of mapped ultrasound images to review previously-recorded hand-held ultrasound examinations, which can be transferred to a computer using a media storage device (USB). Each image is mapped anatomically with respect to a user-identified anatomical landmark, such as the nipple or navel. The image mapping information allows anatomic location of useridentified regions of interest for comparison with other imaging techniques or for procedure planning purposes.

The device software allows the user to measure the size, on two user-defined axes, of the region of interest. The device software allows the user to create and store electronic reports on each region of interest.

The provided text describes the Tractus TissueMapper Reviewer Application, a software device intended for image review, manipulation, and analysis to assist medical professionals in screening, diagnosis, planning, and performing image-guided interventional procedures using Ultrasound images.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based solely on the provided text:

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

The document does not explicitly state quantitative acceptance criteria (e.g., specific accuracy thresholds, sensitivity, specificity). Instead, the performance evaluation focuses on functional requirements and accuracy relative to a predicate device.

2. Sample sized used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Sample Size for Test Set:
  • For the "System Validation Testing," two breast phantoms containing a total of 11 masses were used.
  • For the registration accuracy tests, the number of target locations or phantoms used is not specified beyond "targeting locations within a phantom."
• Data Provenance: The data was generated in-house ("in-house by trained personnel in a simulated work-environment using phantoms"). This indicates it was synthetic data from phantoms, not human clinical data. No country of origin is explicitly stated beyond "in-house," but given the US FDA submission, it's presumed to be within the US. The nature of phantom testing makes it akin to a prospective simulation.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

The document does not specify the number of experts or their qualifications used to establish ground truth. Given that the testing involved phantoms, the "ground truth" for mass locations and registration might have been established during the phantom's creation or by engineering measurements, rather than clinical expert consensus.

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

The document does not describe any adjudication method. Given the nature of phantom testing, a formal adjudication process involving multiple human readers as typically seen in clinical studies is not applicable or described.

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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The performance testing described is a technical validation against phantoms and a comparison of functionality to a predicate device, not a study involving human readers with and without AI assistance to measure improvement. The device is intended to "assist users," but its impact on human performance is not quantified in this submission.

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

The performance testing described primarily evaluates the standalone functionality and accuracy of the software in a simulated environment using phantoms. While the device is intended to assist human users, the tests described (functional checks, registration accuracy, mass identification in phantoms) assess the algorithm's performance on its own.

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

The ground truth used was based on the known characteristics of phantoms. For the mass identification test, the "11 masses total randomly positioned" in the breast phantoms would have had their locations and existence known from the phantom design specification. For registration accuracy, it would be based on the known physical targets within the phantom. This is a form of "engineered truth" or "phantom truth", rather than clinical ground truth like pathology or expert consensus from patient data.

8. The sample size for the training set

The document does not provide information regarding a training set. This submission focuses on the performance and substantial equivalence of the TissueMapper Reviewer Application, but it does not detail its development pipeline, including any machine learning training sets.

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

Since no training set information is provided, how its ground truth was established is not mentioned.

Ask a specific question about this device