Medical Report System Automates Focus Image Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radiologists face inefficiencies when comparing and referencing previous medical images during current examinations, as they manually select and display focus images, which can be time-consuming and prone to errors, especially when documenting temporal changes.
Innovation Solution
A report generation support system that records image operation and input histories, allowing for the automatic extraction and display of focus images based on selected findings and their corresponding operation and input times, thereby streamlining the comparison process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radiologists manually select and display focus images from archived medical images, then they can compare current and previous examination images, but the process becomes time-consuming and reduces productivity
Solution Approach 1:
The system performs preliminary actions by automatically extracting candidate focus images from archived medical images based on examination data before the radiologist needs to make selections. This pre-processing reduces the manual workload during the actual report generation process, resolving the contradiction between selection accuracy and report generation speed
Solution Approach 2:
The system enables self-service by automatically identifying and displaying candidate focus images without requiring manual intervention from the radiologist. The automatic extraction and display mechanisms allow the system to serve itself in selecting relevant images, thereby improving productivity while maintaining reliability through automated consistency
2Loss of information
If radiologists manually search through archived images to find focus images, then they can locate relevant previous examination images, but the complexity of the operation increases
Solution Approach 1:
The system extracts only the necessary candidate focus images from the large archive of medical images based on relevant examination data. By taking out only the essential images that match the current examination context, the system prevents information loss while dramatically simplifying the operation for the radiologist
Solution Approach 2:
The system introduces an intermediary mechanism that automatically matches current examination data with archived images to generate candidate focus images. This intermediary process bridges the gap between the radiologist's needs and the archived image database, making the operation simpler while ensuring relevant images are retrieved
3Measurement precision
If radiologists review multiple previous examination images to identify focus images, then they can ensure accurate comparison, but the time required for report generation increases
Solution Approach 1:
The system applies partial action by extracting only a limited number of candidate focus images that are most relevant to the current examination, rather than requiring review of all archived images. This selective approach maintains measurement precision for temporal change detection while significantly reducing the time investment required
Solution Approach 2:
The system performs preliminary extraction and prioritization of candidate focus images based on examination data matching, so that when the radiologist needs to make comparisons, the most relevant images are already prepared and displayed. This preliminary work ensures precision is maintained while time is saved during the actual review process
Data Source
AI summary
The report generation support system according to the embodiment comprises an input history recording part, operation history recording part, selection part, extraction part, and a display controller. The input history recording part records findings input at the time of generating a medical report and, by linking with an input start time and/or finish time of the findings. The operation history recording part records, as an operation history, the type of operation conducted on an image at the time of generating a report and the time when the operation was conducted by linking with the operated image. The selection part selects at least a part of findings in a report. The extraction part extracts a focus image in the selected findings, based on an input start time and/or finish time of the findings corresponding to the selected location, and the contents of the operation history of the corresponding time.