Search Results

The Second Look® Viewer is intended to be used to display low resolution, nondiagnostic medical images with annotations such as pre-computed regions-ofinterest or pre-computed CAD marks.

The Second Look® Viewer is composed of three primary components. The major component is the computer (1), which is supported by a touchscreen monitor (2) and a barcode reader (3). The computer is a conventional Intel based computer that is connected to the Second Look® CAD processing unit via a network. The Second Look Viewer serves no other purpose than viewer support. The physician interfaces to the software using the touch screen or barcode reader. The physician first barcodes a given patient whose mammography case has already been processed by the Second Look CAD processing unit. The viewer displays the Mammagraph™s with the pre-computed CAD marks overlayed. Second Look Viewer allows a radiologist to review Second Look® Analog CAD output, in softcopy format. The physician may touch any of the small images and see a higher resolution, magnified image along with characterization information for that image. After viewing the mammography case, the radiologist may use the Second Look® Viewer to review pre-computed ultrasound results, such as CADStream® output, if such results already exist for the case under review.

The provided text is a 510(k) summary for the Second Look® Viewer and related FDA correspondence. It describes the device, its intended use, and states that performance and validation testing indicate substantial equivalence to a predicate device. However, it does not contain the detailed information necessary to fully address all aspects of your request regarding acceptance criteria and a specific study proving the device meets those criteria.

Specifically, the document lacks:

• A table of acceptance criteria and reported device performance.
• Sample sizes for test sets, data provenance, number of experts, their qualifications, or adjudication methods for ground truth.
• Information on Multi-Reader Multi-Case (MRMC) comparative effectiveness studies or standalone algorithm performance.
• Details about the type of ground truth used (e.g., pathology, outcomes).
• Sample size for the training set or how ground truth was established for the training set.

The document states, "Results of performance and validation testing indicate that the Second Look® Viewer is substantially equivalent to the predicate device." This is a high-level conclusion required for 510(k) clearance, but the specific data and methodology of those tests are not included in this summary.

Therefore, given the provided text, I can only provide the information that is present:

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

• Acceptance Criteria: Not explicitly stated in this document. The overarching acceptance criterion for 510(k) clearance is "substantial equivalence" to a predicate device for its intended use.
• Reported Device Performance: "Results of performance and validation testing indicate that the Second Look® Viewer is substantially equivalent to the predicate device." No specific performance metrics (e.g., sensitivity, specificity, accuracy, display quality, latency) are provided.

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

• Not specified.

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)

• Not specified.

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

• Not specified.

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

• Not specified. The device is a "Viewer" for pre-computed CAD marks; it is not described as an AI algorithm itself for diagnosis or detection. Therefore, an MRMC study comparing human readers with and without AI assistance is unlikely to be directly relevant to the Viewer's specific function as described, though it would be relevant to the CAD system that generates the marks.

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

• This device is a "Viewer," which by definition is a human-in-the-loop device (displaying information to a physician). It is not an algorithm that performs a diagnostic task independently.

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

• Not specified.

8. The sample size for the training set

• Not specified.

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

• Not specified.

Conclusion from the provided text:
The provided 510(k) summary focuses on the administrative aspects of regulatory clearance based on substantial equivalence. It describes the device, its intended use (displaying low-resolution, non-diagnostic images with annotations/CAD marks), and states that performance and validation testing were conducted, the results of which supported the substantial equivalence claim. However, it does not disclose the detailed results, methodologies, sample sizes, or ground truth establishment processes from those underlying tests.

Ask a specific question about this device