Search Results

The Senographe DS and Senographe Essential FFDM systems generate digital mammographic images that can be used for screening and in the diagnosis of breast cancer. The Senographe DS and Senographe Essential FFDM systems are intended to be used in the same clinical applications as traditional film-based mammographic systems.
Premium View is an image-processing algorithm, which increases the visibility of breast structures. The main advantage is to provide a single breast image, where the contrast in the fatty tissues is similar to that obtained by setting WW (window width) and WL (window level) for optimum visualization of fatty tissues, and the contrast in the fibro-glandular tissue is similar to that obtained by setting WW and WL for optimal visualization of fibro-glandular tissues.
PV i is an option that can simplify the presentation of mammographic images, improve workflow, and streamline the review process of images with very dark or bright areas by presenting the image with the WW and WL optimized for review with minimal need for the user to make adjustments for the various tissue areas. This could be especially useful with patients who have very dense breasts, or implants that currently require multiple adjustments of WW and WL to review.

The Senographe DS and Senographe Essential are both full field digital mammography systems consisting of a digital detector, a dual track x-ray tube (molybdenum / rhodium) and an x-ray generator with control. The digital detector is a flat panel of amorphous silicon on which cesium iodide is deposited to maximize the detection of x-rays. The x-ray filter is a wheel with both a molybdenum and a rhodium filter to allow various combinations of xray tube track and filter when imaging breasts of different radiological densities. The system includes a feature called Automatic Optimization of Parameters (AOP) that automatically selects the kVp, the optimal x-ray tube track and beam filtration and then terminates the exposure based on the breast density to provide consistent image quality for the user across a wide range of breast sizes and densities.
The subject of this submission will introduce a modification to a previously approved (P990066 / S015 and P990066 S020) image processing algorithm called Premium View. Premium View is an image-processing algorithm, which increases the visibility of breast structures. The main advantage is to provide a single breast image, where the contrast in the fatty tissues is similar to that obtained by setting WW (window width) and WL (window level) for optimum visualization of fatty tissues, and the contrast in the fibro-glandular tissue is similar to that obtained by setting WW and WL for optimal visualization of fibro-glandular tissues.
Premium View i, when utilized with the Senographe DS or Senographe Essential introduces a software change that applies different LUT values during the image processing prior to display of a very dense breast, or one with implants. This Premarket Notification will implement this technology on GE Healthcare's existing Full Field Digital Mammography systems as an upgrade to existing systems, or as an option to new installations.

The provided document describes a 510(k) premarket notification for the "Premium View i" (PVi) image processing option for GE Healthcare's Full Field Digital Mammography (FFDM) systems (Senographe DS and Senographe Essential). The document focuses on demonstrating substantial equivalence to predicate devices and describes the intended use and technical aspects of the PVi algorithm. However, it does not contain specific details about acceptance criteria, a formal study proving explicit device performance against those criteria, or quantitative results of such a study.

The document mentions "clinical testing to quantify the clinical acceptance of images that had been retrospectively processed with this image processing algorithm," but it does not provide the results, metrics, sample sizes, expert qualifications, or adjudication methods for this clinical testing.

Therefore, for the information requested, I can only extract what is explicitly stated or can be reasonably inferred from the provided text. Many specific details about the study design and results are missing.

Here's a summary based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state specific acceptance criteria in terms of quantitative performance metrics (e.g., sensitivity, specificity, AUC) or provide a table directly comparing these criteria to the device's reported performance.

Instead, the conclusion states: "GE Healthcare considers the Premium View i option to be as safe, as effective, and performance is substantially equivalent to the predicate device(s)." This implies that the 'acceptance criteria' were met by demonstrating substantial equivalence, which is the primary regulatory pathway for 510(k) submissions. However, no specific performance metrics are given.

The closest to "performance" stated is a qualitative description of the algorithm's effect:
"Premium View is an image-processing algorithm, which increases the visibility of breast structures. The main advantage is to provide a single breast image, where the contrast in the fatty tissues is similar to that obtained by setting WW (window width) and WL (window level) for optimum visualization of fatty tissues, and the contrast in the fibro-glandular tissue is similar to that obtained by setting WW and WL for optimal visualization of fibro-glandular tissues."

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

• Sample Size for Test Set: Not specified. The document only mentions "clinical testing to quantify the clinical acceptance of images."
• Data Provenance: Retrospective ("retrospectively processed with this image processing algorithm"). The country of origin is not specified.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The document only refers to "clinical testing" for "clinical acceptance."

4. Adjudication method for the test set:

• Adjudication Method: Not specified.

5. Multi-Reader Multi-Case (MRMC) comparative effectiveness study:

• MRMC Study Done: Not specified. The document does not mention an MRMC study or any comparison of human readers with vs. without AI assistance. The focus is on the image processing algorithm itself.

6. Standalone (algorithm only without human-in-the-loop performance) study:

• Standalone Study Done: Yes, implicitly. The "clinical testing to quantify the clinical acceptance of images that had been retrospectively processed with this image processing algorithm" suggests an evaluation of the algorithm's output (processed images) rather than a human-in-the-loop study comparing diagnostic accuracy. However, no specific performance metrics are provided.

7. Type of ground truth used:

• Type of Ground Truth: Not specified. Given the context of "clinical acceptance of images," it's likely based on radiologists' subjective evaluation of image quality or visibility of structures rather than definitive pathology or outcome data.

8. Sample size for the training set:

• Sample Size for Training Set: Not specified. The document describes the algorithm's functionality and its development processes (risk analysis, requirements reviews, design reviews, various levels of testing) but does not detail the training set size for the algorithm itself. It's possible the algorithm was developed through iterative refinement rather than a single distinct "training set" like in modern deep learning contexts.

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

• Ground Truth for Training Set: Not specified. The document outlines general quality assurance measures applied during development but does not detail how ground truth was established for "training" the image processing algorithm.

Ask a specific question about this device