Vision System for Mammography Breast Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mammography and biopsy procedures face challenges in achieving high-quality images due to improper breast positioning, which can lead to missed cancers and increased recall rates, especially with less experienced technologists, and existing methods require radiation exposure for image review to assess positioning.
Innovation Solution
A vision sensing system integrated into the x-ray mammography system evaluates breast and patient positioning in real-time using cameras and AI-based image processing, providing feedback to guide technologists for optimal positioning and reducing radiation exposure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If technologists review x-ray images to evaluate breast positioning, then positioning quality can be assessed, but radiation dose is delivered to the patient even if positioning is incorrect
Solution Approach 1:
The system performs breast positioning evaluation using vision sensors before x-ray image acquisition. The processor analyzes camera images to assess positioning quality, and only proceeds with radiation exposure if positioning meets quality criteria. This preliminary evaluation prevents unnecessary radiation exposure to patients who are improperly positioned.
Solution Approach 2:
The system introduces vision sensors and image processing algorithms as an intermediary between positioning and radiation exposure. This intermediary layer provides a non-radiative method to evaluate positioning quality, eliminating the need for patients to receive radiation solely for positioning assessment.
2Productivity
If technologists with less training and experience perform mammography, then operational efficiency may be maintained, but image quality and cancer detection accuracy deteriorate
Solution Approach 1:
The system provides real-time feedback to technologists during the mammography workflow. Vision sensors continuously monitor breast positioning, and the processor provides guidance recommendations to improve positioning accuracy. This feedback mechanism enables less experienced technologists to achieve positioning quality comparable to experienced practitioners.
Solution Approach 2:
The system performs automated positioning evaluation and quality assessment without requiring extensive human expertise. The vision sensing system and processor automatically analyze positioning quality, reducing dependency on technologist experience and training level while maintaining high positioning accuracy.
3Manufacturing precision
If real-time vision sensing and feedback systems are implemented, then positioning accuracy and cancer detection sensitivity improve, but device complexity increases
Solution Approach 1:
The system uses existing mammography system components (cameras, processors, displays) for multiple purposes: patient monitoring, breast positioning evaluation, and quality assessment. This multi-functionality approach minimizes the need for entirely new hardware while achieving real-time positioning feedback.
Solution Approach 2:
The system uses visual copies (camera images) of the breast and positioning setup to evaluate positioning quality without requiring complex physical measurement devices. The processor analyzes these visual representations to determine positioning accuracy, simplifying the overall system architecture.
Data Source
Figure 1A
Figure 1B
Figure 1C~1D
AI summary
Various methods and systems are provided for breast positioning assistance during mammography and image guided interventional procedures. In one example, a vision system is utilized to evaluate one or more of a patient position, a breast position, and breast anatomy to determine if the patient and breast are adjusted to desired positions preferred for a desired view and imaging procedure. Further, based on the evaluation, prior to acquiring x-ray images, real-time feedback may be provided to guide the user to position the breast and/or the patient.