(79 days)
PowerLook Density Assessment is a software application intended for use with digital breast tomosynthesized 2D images from tomosynthesis exams. PowerLook Density Assessment provides an ACR BI-RADS Atlas 5th Edition breast density category to aid health care professionals in the assessment of breast tissue composition. PowerLook Density Assessment produces adjunctive information. It is not a diagnostic aid.
The PowerLook Density Assessment Software analyzes digital breast tomosynthesis 2D synthetic images to calculate the dense tissue area of each breast. The measured dense tissue area is then used to provide a Category of 1-4 consistent with ACR BI-RADS 5th edition a-d. The top-level design sub-systems are as follows: Initialization, Breast Segmentation, Breast Thickness Correction, and Breast Density Computation. The assessment results in a final density map and, in conjunction with its pixel size (in square cm), is used to compute the area of the dense tissue (square cm). The area of the breast (square cm) is computed by counting the total number of pixels in the valid regions of the breast segmentation mask). The ratio of the dense area to the total breast area gives the percent breast density (PBD) for the given view. The dense areas, breast areas, percent breast densities, and dispersion for the CC and MLO views are averaged in order to report measurements for each breast. The average PBD and the average dispersion are then taken, and mapped to a density category from 1 through 4 consistent with ACR BI-RADS 5th edition a-d for each breast, using a set of calibrated boundaries. The higher category of the two breasts is reported as the overall case score. The PowerLook Density Assessment is designed as a stand-alone executable operating within the larger software framework provided by PowerLook AMP. As such, the PowerLook Density Assessment software is purely focused on processing tomosynthesis 2D synthetic images and is not concerned with system issues such as managing DICOM image inputs or managing system outputs to a printer, PACS or Mammography Workstation. The PowerLook Density Assessment software is automatically invoked by PowerLook AMP. The results of PowerLook Density Assessment are designed to display on a mammography workstation, high resolution monitor, or in a printed case report. PowerLook Density Assessment is designed to process approximately 60-120 cases per hour.
Here's a summary of the acceptance criteria and the study details for the PowerLook Density Assessment Software, based on the provided FDA 510(k) document:
Acceptance Criteria and Device Performance
The document states that the PowerLook Density Assessment Software performed "substantially equivalent to the predicate device." While specific numerical acceptance criteria (e.g., minimum kappa score, percentage agreement) are not explicitly listed in the provided text as pass/fail thresholds, the performance was assessed based on:
- Kappa score: A statistical measure of inter-rater agreement, commonly used for categorical data.
- Percent correct in each BI-RADS category: Measures the accuracy of the software's classification into each of the four BI-RADS density categories (1, 2, 3, 4).
- Combined A/B and C/D BI-RADS categories: Assesses performance when categories are grouped (e.g., non-dense vs. dense).
The document states: "PowerLook Density Assessment performed substantially equivalent to the predicate device." This implies that the device's performance metrics were within an acceptable range compared to the already cleared predicate.
Table of Acceptance Criteria and Reported Device Performance
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Kappa Score | Substantially equivalent to predicate device | Performance substantially equivalent to predicate device |
| Percent Correct (Each BI-RADS Category) | Substantially equivalent to predicate device | Performance substantially equivalent to predicate device |
| Combined A/B and C/D BI-RADS Categories | Substantially equivalent to predicate device | Performance substantially equivalent to predicate device |
Study Details
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated in the provided text. The document mentions "a set of digital breast tomosynthesis synthesized 2D images."
- Data Provenance: Not explicitly stated (e.g., country of origin, specific clinics). The study used "digital breast tomosynthesis synthesized 2D images from." It is retrospective, as it refers to images for which BI-RADS scores "were obtained from radiologists."
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated. The document mentions "BI-RADS scores were obtained from radiologists." It does not specify if this was a single radiologist or multiple.
- Qualifications of Experts: The experts are identified as "radiologists." No specific experience level (e.g., "10 years of experience") is provided.
-
Adjudication method for the test set:
- The document states that BI-RADS scores "were obtained from radiologists," but it does not specify an adjudication method (such as 2+1, 3+1, or none) for determining a consensus ground truth if multiple radiologists were involved.
-
If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
- No, an MRMC comparative effectiveness study was not explicitly mentioned or described. The study primarily focused on the standalone performance of the PowerLook Density Assessment Software against radiologist assessments (ground truth). It did not describe a scenario where human readers' performance with and without AI assistance was compared.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone study was performed. The described validation involved running the "PowerLook Density Assessment Software... followed by a comparison of the results between the predicate results, desired results, and observed performance..." This indicates the algorithm's performance was evaluated independently against the established ground truth.
-
The type of ground truth used:
- Expert Consensus (Radiologist BI-RADS Scores): The ground truth was established by "BI-RADS scores... obtained from radiologists." This implies the radiologists' interpretations served as the reference standard for breast density categorization.
-
The sample size for the training set:
- Not specified. The document does not provide any information regarding the training set's sample size or characteristics.
-
How the ground truth for the training set was established:
- Not specified. Since information about the training set size or its establishment is absent, the method for establishing ground truth for training data is also not provided.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).