(59 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.
PowerLook Density Assessment 4.0 is a software application intended for use with mammography exams containing synthetic 2D images generated from Digital Breast Tomosynthesis (DBT) data. The PowerLook Density Assessment software assesses breast tissue composition and provides a breast density category aligned with BI-RADS® 5th Edition density lexicon. The PowerLook Density Assessment 4.0 algorithm is designed to be used with cases containing up to four synthetic 2D views. When exams contain only DBT and synthetic 2D images generated from DBT, the 4.0 algorithm is used. The PowerLook Density Assessment software is designed to work in conjunction with iCAD's PowerLook DICOM server platform, which is a Class I exempt medical device. The PowerLook Density Assessment 4.0 utilizes data management capabilities of PowerLook for controlling input to and output from the PowerLook Density Assessment algorithm. Results of the PowerLook Density Assessment software application can be displayed on a mammography review workstation, mammography reporting application or radiology information system (RIS), or printed case report.
Here's an analysis of the provided text to extract the acceptance criteria and study details for the PowerLook Density Assessment V4.0.
1. Table of Acceptance Criteria and Reported Device Performance
The FDA submission for PowerLook Density Assessment V4.0 (K211506) does not explicitly state numerical acceptance criteria in terms of metrics like accuracy, sensitivity, or specificity. Instead, it refers to a qualitative acceptance criteria: "The performance of the system on all three datasets were above the desired performance, demonstrating that PowerLook Density Assessment 4.0 accurately calculates the BI-RADS breast density category for Hologic C-View and GE V-Preview data."
However, based on the nature of breast density assessment devices, the implicit acceptance criteria would typically involve a high level of agreement between the device's output and expert-determined ground truth, particularly concerning the assignment of ACR BI-RADS breast density categories. While specific percentages are not provided, the claim of "accurately calculates" suggests that substantial agreement was achieved.
| Acceptance Criteria (Implicit from "accurately calculates BI-RADS breast density category") | Reported Device Performance |
|---|---|
| High agreement with expert-assigned BI-RADS breast density categories | "The performance of the system on all three datasets were above the desired performance, demonstrating that PowerLook Density Assessment 4.0 accurately calculates the BI-RADS breast density category for Hologic C-View and GE V-Preview data." (Specific metrics like accuracy, sensitivity, or specificity are not provided in the document) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document does not specify the exact number of cases (images/patients) used in the test set. It mentions "Hologic C-View, GE V-Preview V3 and GE V-Preview V4.1 cases were run through Density Assessment 4.0."
- Data Provenance: The document does not explicitly state the country of origin of the data or whether it was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not specify the number of experts used or their qualifications (e.g., years of experience as a radiologist) for establishing the ground truth for the test set. It implicitly refers to "BI-RADS® 5th Edition density lexicon," suggesting that expert radiologists were involved in the ground truth labeling process, as this lexicon is used by radiologists.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) used for the test set ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned in the provided text, nor is an effect size for human readers improving with AI assistance. The device is intended to provide "adjunctive information" to aid healthcare professionals, rather than directly assisting in a diagnostic reading task where reader performance would be measured.
6. Standalone Performance
Yes, a standalone performance study was done. The document states: "The performance of the system on all three datasets were above the desired performance, demonstrating that PowerLook Density Assessment 4.0 accurately calculates the BI-RADS breast density category for Hologic C-View and GE V-Preview data." This indicates that the algorithm's performance was evaluated independently in calculating the breast density categories.
7. Type of Ground Truth Used
The ground truth used is based on the ACR BI-RADS Atlas 5th Edition breast density category. This strongly implies expert consensus or expert-assigned categories, as radiologists are trained to use this lexicon.
8. Sample Size for the Training Set
The document does not provide information on the sample size used for the training set. It primarily focuses on the validation of the device.
9. How Ground Truth for the Training Set Was Established
The document does not explicitly state how the ground truth for the training set was established. However, given the device's function and the ground truth used for validation (BI-RADS 5th Edition), it is highly probable that the training data's ground truth was also established by expert radiologists adhering to the same BI-RADS lexicon.
§ 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).