Automated Image Analysis System for Reducing Medical Re-scans
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging workflows are inefficient due to time-consuming radiologist decisions on imaging protocols, unnecessary re-scans, and inadequate assessment of diagnostic utility, leading to increased healthcare costs and patient inconvenience.
Innovation Solution
An automated image analysis system that evaluates diagnostic utility in real-time using rule-based or deep learning algorithms, determining if images are sufficient for diagnosis and suggesting alternative protocols to address artifacts, thereby optimizing re-scan decisions based on diagnostic purpose and radiologist preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radiologists manually determine imaging protocols for each patient, then diagnostic accuracy is maintained, but workflow efficiency deteriorates due to significant time consumption
Solution Approach 1:
The imaging system automatically evaluates image quality and determines whether re-scanning is needed based on diagnostic utility assessment, eliminating the need for radiologists to manually review each image and make re-scan decisions. The system serves itself by autonomously quality-controlling the imaging workflow.
Solution Approach 2:
The patent replaces the manual mechanical process of radiologist image review with an automated computer-based evaluation system that uses algorithms to assess diagnostic utility, substitute human decision-making with automated computational analysis.
2Measurement precision
If technologists re-scan patients to ensure image quality, then diagnostic utility is improved, but productivity deteriorates due to unnecessary re-scans
Solution Approach 1:
The system performs preliminary automated evaluation of image quality immediately after acquisition, determining before patient discharge whether re-scanning is necessary. This preliminary assessment prevents unnecessary re-scans and ensures adequate image quality without delaying patient flow.
Solution Approach 2:
The imaging system implements automated feedback loops where image quality metrics are continuously monitored and evaluated against diagnostic requirements, providing real-time feedback on whether re-scanning is needed based on objective criteria rather than subjective technologist judgment.
3Device complexity
If imaging protocols are selected without considering artifacts, then device complexity is reduced, but image quality deteriorates due to artifact contamination
Solution Approach 1:
The system automatically adjusts imaging parameters and protocol selection based on detected artifacts and patient-specific factors. When artifacts are present, the system modifies acquisition parameters or selects alternative protocols that are more tolerant of the specific artifact types detected, optimizing image quality without requiring complex manual intervention.
Data Source
AI summary
The present disclosure provides, in certain implementations, a rule-based or deep learning-based approach capable of assessing diagnostic utility of images in near real time with respect to acquisition. Correspondingly, an automated implementation of such an algorithm on the scanner would, in fact, emulate the doctor himself rating images in real time, and reduce the number of unneeded re-scans and recalls. In one aspect of the present invention it was found that diagnostic utility of an image is not an absolute measure, but instead depends upon the reading radiologist and the scan indication (i.e., the purpose of the scan). Therefore, adapting the threshold (probability of an imaging volume to be deemed good) as a function of reading radiologist and scan indication can result in decreasing the number of re-scans and recalls.