AI Radiology Workflow Routing for Faster Breast Screening Results
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing breast cancer screening methods face challenges such as long delays, unclear pricing, inconsistent delivery times for exam results, and variations in radiologist performance, leading to inconsistent patient experiences and standards of care.
Innovation Solution
A method and system using artificial intelligence to stratify medical image data into distinct radiological workflows by classifying images as normal, ambiguous, or suspicious, directing them to appropriate radiologists for assessment, and providing real-time alerts and diagnostic results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional manual radiological assessment workflows are used, then radiologists can perform comprehensive image analysis, but long delays and inconsistencies in delivering exam results occur
Solution Approach 1:
The radiological workflow is segmented into distinct categories (normal, ambiguous, suspicious) based on AI classification, allowing different handling paths for different image types. This segmentation enables parallel processing and reduces overall delivery time while maintaining consistency through standardized routing rules.
Solution Approach 2:
AI-based image classification is performed preliminarily before radiologist assessment, pre-sorting images into categories that guide subsequent workflow steps. This preliminary action reduces unnecessary delays by preparing images for optimal processing paths before human review begins.
2Loss of time
If AI classification is applied to stratify images into different workflows, then delivery time and consistency are improved, but system complexity increases
Solution Approach 1:
An AI classification system serves as an intermediary between image acquisition and radiologist assessment, automatically stratifying images into categories. This intermediary layer manages the complexity by handling classification logic centrally, while radiologists interact with simplified, pre-categorized workflows.
Solution Approach 2:
The system performs self-service through automated AI classification and workflow routing, reducing the need for manual triage and administrative coordination. The system autonomously directs images to appropriate radiologists based on classification, minimizing human intervention in workflow management.
3Productivity
If images are directed to different radiologists based on classification, then efficiency and standardized care are enhanced, but coordination complexity increases
Solution Approach 1:
Different radiologists are assigned to different image categories (normal, ambiguous, suspicious) based on their expertise and availability. This local quality assignment optimizes productivity by matching radiologist skills with case complexity, while the system manages coordination complexity through automated routing rules.
Solution Approach 2:
The workflow system dynamically changes routing parameters based on image classification results, directing different categories of images to different radiologists or workflow paths. This parameter-based routing enhances efficiency by optimizing case distribution while the system manages coordination through automated parameter adjustment.
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.