Medical Information Processing Apparatus for Adaptive Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Medical image diagnostic apparatuses face challenges in balancing image quality and patient exposure time, as longer imaging times improve diagnostic accuracy but increase patient burden and radiation exposure, while noise in medical images affects machine learning model accuracy.
Innovation Solution
A medical information processing apparatus that adaptively determines imaging conditions for medical image diagnostic apparatuses based on desired accuracy, using a single trained model to classify data groups by lesion size and image quality, and automatically adjusts data collection time to optimize lesion extraction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the imaging time is increased to improve image quality and diagnostic accuracy, then the image quality and diagnostic accuracy are improved, but the patient burden and radiation exposure increase
Solution Approach 1:
The patent changes the parameter of image quality assessment from fixed thresholds to dynamic parameter ranges based on lesion size. By correlating lesion size with acceptable image quality parameters (noise, contrast), the system determines minimum imaging conditions needed, avoiding excessive radiation exposure while maintaining diagnostic accuracy for detecting lesions of specific sizes
Solution Approach 2:
The patent performs preliminary classification of lesions by size before determining imaging conditions. By pre-establishing the relationship between lesion size and required image quality parameters, the system can determine appropriate imaging conditions in advance, optimizing the balance between diagnostic accuracy and radiation exposure before actual imaging occurs
2Measurement precision
If the imaging time is increased to improve image quality, then the image quality is improved, but the patient burden increases
Solution Approach 1:
The patent dynamically adjusts imaging time based on lesion size and required image quality parameters. By establishing correlations between lesion size, image quality parameters (noise, contrast), and imaging time, the system determines the minimum imaging time needed to achieve sufficient image quality for detecting lesions of specific sizes, reducing unnecessary imaging time and patient burden
3Measurement precision
If the noise in medical images is reduced to improve machine learning model accuracy, then the feature value accuracy is improved, but the imaging time or radiation exposure increases
Solution Approach 1:
The patent sets noise thresholds based on lesion size and required feature value accuracy. By correlating lesion size with acceptable noise levels that still maintain sufficient machine learning model accuracy, the system determines imaging conditions that reduce noise to the minimum necessary level, avoiding excessive radiation exposure while maintaining feature value accuracy needed for reliable lesion detection
Data Source
AI summary
According to one embodiment, a medical information processing apparatus includes processing circuitry. The processing circuitry is configured to acquire information on an accuracy of a trained model that outputs information on a lesion included in data related to a medical image based on inputted data related to the medical image. Further, the processing circuitry is configured to determine a data collection condition for the medical image in a medical image diagnostic apparatus based on the information on the accuracy.