Neural Network Region of Interest Detection for Medical Scanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual selection of regions of interest in medical imaging is time-consuming and limited by physician experience, affecting scanning accuracy and efficiency.
Innovation Solution
A computer-aided scanning method using a pre-trained neural network to analyze pre-scan images, automatically identifying regions of interest and determining scanning parameters, including auxiliary lines, to improve scanning efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual selection of region of interest is performed by physician, then scanning can be performed with personal judgment, but the process is time consuming and accuracy is limited by physician experience
Solution Approach 1:
The system performs self-service by automatically identifying regions of interest and determining scanning parameters through neural network algorithms, eliminating the need for manual physician intervention in parameter selection while maintaining high accuracy
Solution Approach 2:
The manual mechanical process of physician visual inspection and parameter selection is replaced by an automated computational system using deep learning neural networks, achieving both speed and accuracy improvements
2Productivity
If manual selection of scanning parameters is performed, then flexibility in adjusting to different cases is maintained, but scanning efficiency is reduced
Solution Approach 1:
The system automatically determines optimal scanning parameters including layer thickness, scanning range, and auxiliary lines by analyzing pre-scan images through neural networks, dynamically adjusting parameters based on the specific anatomical features detected
Solution Approach 2:
The scanning system performs self-configuration by automatically setting scanning parameters based on automated region of interest detection, eliminating manual intervention while adapting to different anatomical cases
3Measurement precision
If automated neural network method is used to identify region of interest, then scanning time is reduced and accuracy is improved, but system complexity increases
Solution Approach 1:
The neural network model is pre-trained offline with large datasets before deployment, performing the complex learning process in advance so that the actual scanning system only needs to execute the trained model, reducing real-time computational complexity
Solution Approach 2:
A pre-trained neural network model serves as an intermediary between the complex training process and the simple inference process, allowing the scanning system to achieve high accuracy without implementing the complex training algorithms
Data Source
AI summary
A computer aided scanning method for a medical device is provided in the present invention, comprising step 1: recognizing and analyzing a pre-scan image through a pre-trained neural network to determine and identify a region of interest in the pre-scan image; and step 2: determining, according to feature information of the identified region of interest, scanning parameters for further scanning of the region of interest. A medical device employing the above method and a computer readable storage medium for performing the method are further provided in the present invention. The method, the medical device, and the readable storage medium provided by the present invention can automatically identify a region of interest, determine a corresponding auxiliary line and subsequent scanning parameters, and improve the scanning efficiency and accuracy of the medical device.