(276 days)
BI-RADS Companion™ ("BRC") is a computer-aided image viewing and report generating tool designed to assist radiologists in the analysis of ultrasound images of breast masses by making the ACR "BI-RADS Classification Form and Lexicon® ("ABCFL") available in electronic format. The user can view any selected image from a case and segment the background by applying a user selected threshold or outlining the lesion manually with a cursor.
The user can annotate, tag, measure, and record selected views. Under user control and review, the software electronically assembles reports from inputs selected by the user from the ultrasound ABCFL during the image interpretation process. The assembled report complies with the ABCFL for ultrasound. The output may be viewed and sent to electronic storage media, or standard film or paper printers or other document manipulation programs such as Adobe or Microsoft.
When used by a skilled radiologist, this device provides information that may be useful in image interpretation. Paticnt management decisions should not be based solely on forms generated by BRC.
The ultrasound images displayed by BRC must not be used for primary diagnostic interpretation.
BI-RADS Companion™ ("BRC") is a computer-aided image viewing and report generating tool designed to assist radiologists in the analysis of ultrasound images of breast masses by making the ACR "BI-RADS Classification Form and Lexicon® ("ABCFL") available in electronic format. The user can view any selected image from a case and segment the background by applying a user selected threshold or outlining the lesion manually with a cursor.
The user can annotate, tag, measure, and record selected views. Under user control and review, the software electronically assembles reports from inputs selected by the ultrasound ABCFL during the image interpretation process. The assembled report complies with the ABCFL for ultrasound. The output may be viewed and sent to electronic storage media, or standard film or paper printers or other document manipulation programs such as Adobe or Microsoft.
The provided text does not contain specific acceptance criteria or details of a study conducted to prove that the BI-RADS Companion device meets acceptance criteria. Instead, it focuses on establishing substantial equivalence to a predicate device based on functional comparisons.
Here's a breakdown of what can be extracted and what information is missing:
1. A table of acceptance criteria and the reported device performance
No explicit acceptance criteria or reported device performance are provided. The document focuses on a comparison of functions with a predicate device to establish substantial equivalence. The table presented compares functionalities, not performance metrics against acceptance criteria.
| Function | BI-RADS Companion, Version 1.0 (K072258) | B-CAD System, Version 1.0. (K050846) |
|---|---|---|
| Intended as aide to radiologists' reviewing of images of masses in the human female breast | yes | yes |
| Windows 2000/XP based DICOM File Set Reader (FSR) compatible platform may be installed on a PC, Notebook or Workstation with HL7 compatibility | yes | yes |
| User interface designed to follow typical clinical workflow patterns to process, review and analyze digital images | yes | yes |
| User may annotate, tag, calibrate, measure and automatically record selected views | yes | yes |
| Automatically generates reports with user annotations during image analysis process. Allows saving custom annotations of images of confirmed cases to be used for future reference and education | yes | yes |
| Annotations is based on ACR ABCFL Breast Imaging Atlas | yes | yes |
| Report format supports compliance with ACR ABCFL | yes | yes |
| Outputs may be viewed and sent to standard film or paper printers or sent electronically to intranet web server or other HL7 compliant media format | yes | yes |
| Display multiple and full study views | yes | yes |
| Radiologist's BI-RADS assessment based on visual impressions of the user ABCFL | yes | yes |
2. Sample size used for the test set and the data provenance
No information is provided about a test set sample size or data provenance. The submission relies on functional equivalence, not performance testing on a specific dataset.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. There is no mention of a test set with established ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. There is no mention of a test set or ground truth adjudication.
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 MRMC study was done, or at least, none is described in this document. The device is a viewing and reporting tool, not an AI-assisted diagnostic algorithm in the sense of providing automated interpretations that would typically be evaluated in an MRMC study for improved human reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
No standalone performance study is mentioned. The device is intended to be used by a skilled radiologist as an aid, not as a standalone diagnostic tool. "The ultrasound images displayed by BRC must not be used for primary diagnostic interpretation." and "Patient management decisions should not be based solely on forms generated by BRC." reinforces this.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable, as no performance study requiring ground truth is described.
8. The sample size for the training set
Not applicable. This device does not appear to be an AI/machine learning algorithm that requires a training set in the typical sense. It is a software tool for data entry, viewing, and report generation based on predefined BI-RADS classifications.
9. How the ground truth for the training set was established
Not applicable.
§ 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).