Rotary ABUS and AI Screening for X-Ray-Dense Breasts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current breast cancer screening methods for x-ray dense breasts are inefficient, costly, and require extensive training for physicians, with existing ultrasound technologies like ABUS generating large volumes of images that overwhelm human readers and lack effective AI for autonomous reading.
Innovation Solution
A rotary automated breast ultrasound scanner (Rotary ABUS) combined with advanced AI is used for supine scanning, processing ultrasound data to identify suspicious lesions, and comparing volume changes over time to triage benign cases, reducing the need for human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional X-ray mammography is used for screening, then it is widely available and cost-effective, but it cannot effectively detect cancer in x-ray dense breasts
Solution Approach 1:
The patent replaces X-ray imaging with ultrasound imaging to screen dense breasts. The rotary ABUS system uses ultrasound waves to penetrate and image dense breast tissue, overcoming the limitation of X-ray mammography which cannot effectively visualize dense breasts. This substitution of imaging modality enables reliable cancer detection in the previously unscreenable population.
Solution Approach 2:
The patent changes the imaging parameter from X-ray attenuation (which fails in dense breasts) to ultrasound echo patterns (which work effectively in dense breasts). By changing the physical principle and imaging parameters, the system achieves both reliability in cancer detection and adaptability to dense breast anatomy.
2Reliability
If automated breast ultrasound (ABUS) is used for screening, then it improves detection capability for dense breasts, but it generates large volumes of images that overwhelm human readers
Solution Approach 1:
The patent segments the massive volume of ultrasound images into manageable units by automatically identifying and extracting suspicious regions of interest (ROIs). The AI system processes only these segmented suspicious areas rather than the entire image volume, reducing processing complexity while maintaining detection reliability.
Solution Approach 2:
The patent introduces AI/ML algorithms as an intermediary between the ABUS scanner and human readers. This intermediary automatically analyzes the large volumes of images, identifies suspicious lesions, and prioritizes them for human review, thereby reducing the overall processing complexity burden on human readers.
3Measurement precision
If physicians manually read and analyze ultrasound images, then they can identify suspicious lesions, but extensive training is required and throughput is limited
Solution Approach 1:
The patent implements self-service by enabling the AI system to autonomously perform initial image analysis and lesion identification without requiring physician intervention for every case. The AI serves itself by automatically detecting suspicious lesions and generating prioritized lists for human review, dramatically increasing throughput while maintaining precision through AI's consistent application of detection algorithms.
Solution Approach 2:
The patent replaces the manual mechanical process of physician image review with an automated AI-based system. This substitution maintains measurement precision in lesion identification while achieving superior productivity through rapid automated analysis of large image volumes, eliminating the bottleneck of physician training and review capacity.
4Productivity
If rotary scanning is used to improve throughput, then screening efficiency increases, but ensuring stable breast positioning becomes more challenging
Solution Approach 1:
The patent applies local quality by providing differentiated contact pressure zones on the rotary template. The area where the transducer contacts the breast applies high pressure for stable imaging, while other areas of the template apply minimal pressure to maintain overall breast stability without discomfort. This localized pressure distribution enables both high throughput and stable positioning.
Solution Approach 2:
The patent uses a curved/spheroidal rotary template that conforms to the breast surface geometry. This curvature distributes contact forces more evenly across the scanning area, maintaining breast stability during rotation while enabling continuous scanning motion for high throughput. The spherical geometry ensures consistent acoustic coupling throughout the rotational scan path.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system efficiently screens dense breasts with high throughput, reduces capital and operating costs, and enables autonomous reading, potentially eliminating the need for extensive physician training, thereby improving sensitivity and specificity in breast cancer detection.
Implementation Method 1
a rotary automated breast ultrasound scanner (Rotary ABUS) combined with advanced AI is used for supine scanning, processing ultrasound data
Data Source
AI summary
An ultrasound system for breast cancer screening scans a breast by rotating a dish-shaped template with one or more breast-facing recesses and a smoother nipple covering area about a center or rotation that is at the breast but is spaced from the nipple, to produce a multiplicity of radially oriented two-dimensional images, and speeds up assessment of the images by subjecting them to an artificial intelligence process that identifies likely abnormalities in the breast as volumes of interest (VOIs) and characterizes each VOI as benign, suggestive of a follow-up sooner than a normal interval, or likely cancerous, and computer-generates a report directing the patient accordingly, wherein the process includes comparing volumes of suspected abnormalities estimated from a current scan with volumes of corresponding regions of the breast from one or more previous scans.