Incidental Finding Augmentation in MRI Radiology
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Incidental findings outside the region of interest (ROI) in radiological scans are often overlooked, leading to undiagnosed conditions due to lack of communication and focus by radiologists and physicians.
Innovation Solution
A system and method that utilize a computing device connected to an MRI device to segment MR data, identify and highlight anatomical structures within or outside the ROI, and provide a graphical representation of actionable findings, along with a probability of concurrence and recommended actions, to ensure these findings are communicated and addressed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If radiologists focus only on the region of interest (ROI) for examination, then the diagnostic efficiency for the primary condition is improved, but incidental findings outside the ROI are overlooked
Solution Approach 1:
The system segments the radiology report into multiple components: primary findings within the ROI and incidental findings outside the ROI. By automatically parsing and categorizing different sections of the report, the system enables separate analysis and tracking of incidental findings without requiring radiologists to manually separate them, thus maintaining diagnostic efficiency while preventing information loss.
Solution Approach 2:
The system introduces an intermediary computational layer that processes the radiology report and identifies incidental findings. This intermediary automatically extracts, categorizes, and flags incidental findings outside the ROI, serving as a bridge between the radiologist's focused examination and the need for comprehensive finding documentation, thereby resolving the contradiction without additional manual effort.
2Reliability
If radiologists visually review all anatomical structures in radiological images, then all findings including incidental ones are detected, but the time and effort required for examination increases
Solution Approach 1:
The system performs preliminary automated analysis of the radiology report to identify and flag incidental findings before the radiologist completes their visual review. By pre-processing the report text and extracting potential incidental findings, the system prepares a summary that highlights areas outside the ROI, enabling the radiologist to quickly verify rather than manually search for all findings, thus maintaining detection completeness while reducing examination time.
Solution Approach 2:
The system replaces the mechanical process of manual visual review of all anatomical structures with an automated text-based analysis system. Instead of requiring radiologists to visually scan entire images to detect incidental findings, the system uses natural language processing to analyze the radiology report and identify incidental findings, substituting manual mechanical review with automated computational analysis.
3Reliability
If incidental findings are communicated to the ordering physician, then patient follow-up care is improved, but the complexity of the radiology reporting process increases
Solution Approach 1:
The system segments the radiology reporting process into automated components: incidental finding identification, categorization, and structured output generation. By automatically parsing the radiology report and extracting incidental findings into a standardized format, the system reduces the complexity of manual processing and communication while ensuring reliable transmission of findings to the ordering physician for appropriate patient follow-up.
Solution Approach 2:
The system enables self-service automated identification and communication of incidental findings. The computational system independently performs the tasks of identifying incidental findings in the radiology report, categorizing them by anatomical location and clinical significance, and preparing them for communication to the ordering physician, thereby reducing the manual workload and complexity for radiologists while maintaining reliable finding communication.
Data Source
AI summary
Systems and methods for magnetic resonance (MR) examination are provided. In an embodiment, a method for MR examination includes receiving, at a computing device in communication with a magnetic resonance imaging (MRI) device, MR data of a patient body comprising a plurality of anatomical structures, the plurality of anatomical structures including a region of interest, segmenting, by the computing device, the MR data to obtain geometries of the plurality of anatomical structures, receiving, at the computing device, a report comprising text descriptions representative of the plurality of anatomical structures, associating, by the computing device, the text descriptions with respective geometries of the plurality of anatomical structures, identifying, by the computing device, the text descriptions associated with anatomical structures within or outside of the region of interest; and outputting, by the computing device, a graphical representation based on the identified text descriptions associated with anatomical structures within or outside of the region of interest.