AI-Based Radiology Workflow Stratification for Faster Breast Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current breast cancer screening methods, such as mammography, face challenges due to poor patient experience, variations in radiologist performance, and inconsistencies in pricing and delivery times among providers.
Innovation Solution
The use of artificial intelligence to stratify medical image data into distinct radiological workflows for further screening and diagnostic assessment, directing images to appropriate radiologists based on classifications as normal, ambiguous, or suspicious.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If screening mammography is performed to identify early-stage cancers, then survival rate is improved, but patient experience deteriorates due to long wait times and inconsistent service delivery
Solution Approach 1:
The system performs preliminary classification of mammography images using AI algorithms before radiologist review. Images are pre-stratified into normal, benign, and suspicious categories, allowing radiologists to prioritize suspicious cases and reducing overall wait times for patients while maintaining early cancer detection capability
Solution Approach 2:
The radiology workflow is segmented into distinct pathways based on AI classification results. Normal cases follow a rapid clearance pathway, benign cases undergo standard review, and suspicious cases receive expedited radiologist attention. This segmentation reduces wait times for most patients while ensuring suspicious cases get appropriate review
2Measurement precision
If multiple radiologists review images to improve diagnostic accuracy, then measurement precision is improved, but productivity deteriorates due to increased complexity and coordination requirements
Solution Approach 1:
Different levels of radiologist review are applied to different cases based on their risk stratification. Normal cases require no radiologist review, benign cases receive standard review, and suspicious cases receive expert review. This local differentiation maintains diagnostic accuracy for high-risk cases while improving overall system productivity
Solution Approach 2:
The AI classification system acts as an intermediary between image acquisition and radiologist review. It pre-processes and stratifies images, directing only suspicious and uncertain cases to radiologists. This intermediary role reduces the volume of cases requiring radiologist attention while maintaining diagnostic accuracy for cases that need human review
3Productivity
If AI classification is applied to stratify images into different workflows, then productivity is improved, but device complexity increases due to additional processing requirements
Solution Approach 1:
The AI classification system performs multiple functions: it classifies images by diagnostic likelihood, estimates case difficulty, stratifies cases into workflows, and provides triage recommendations. This multi-functionality justifies the added complexity by delivering comprehensive case management that improves radiologist productivity across diverse case types
Data Source
AI summary
The present disclosure provides methods and systems directed to performing real-time and/or AI-assisted radiology. A method for processing an image of a location of a body of a subject may comprise (a) obtaining the image of the location of a body of the subject; (b) using a trained algorithm to classify the image or a derivative thereof to a category among a plurality of categories, wherein the classifying comprises applying an image processing algorithm; (c) directing the image to a first radiologist for radiological assessment if the image is classified to a first category among the plurality of categories, or (ii) directing the image to a second radiologist for radiological assessment, if the image is classified to a second category among the plurality of categories; and (d) receiving a recommendation from the first or second radiologist to examine the subject based at least in part on the radiological assessment.