Automated CT Scanning Protocol Selection via Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Selecting a suitable scanning protocol for CT scans is time-consuming and can lead to inaccuracies due to the diverse nature of clinical diagnoses, causing potential changes in the patient's lesion location during protocol selection, which affects the accuracy of subsequent scans.
Innovation Solution
A method and apparatus that create a plain film positioning image, allow operators to input a region of interest, generate a region to be matched, and compare it with pre-stored reference images to determine a matching degree, selecting a corresponding scanning protocol based on preset correspondences, thereby automating the selection process and improving efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple scanning protocols are pre-established for diverse clinical diagnoses, then the adaptability to different diagnosing requirements is improved, but the device complexity and time required to select a suitable protocol increases
Solution Approach 1:
The system automatically determines the scanning protocol by analyzing the positioning image and matching it with pre-stored reference images, eliminating the need for manual protocol selection by the operator. The apparatus performs self-service by autonomously selecting the appropriate protocol based on image recognition and pattern matching algorithms.
Solution Approach 2:
Multiple scanning protocols are pre-established and stored in the system before actual scanning operations. Reference images corresponding to different anatomical regions and diagnostic requirements are pre-stored and organized. When a positioning image is acquired, the system quickly matches it against the pre-prepared reference images to determine the appropriate protocol, avoiding time-consuming manual selection.
2Measurement precision
If the operator spends more time to carefully select the scanning protocol, then the measurement precision of lesion location is improved, but the loss of time increases and the lesion location may change during selection
Solution Approach 1:
The manual mechanical process of protocol selection by the operator is replaced with an automated image recognition and pattern matching system. The computer system automatically compares the positioning image with reference images, determines the anatomical region and lesion location, and selects the appropriate scanning protocol without human intervention, thereby eliminating time loss while maintaining or improving precision.
Solution Approach 2:
The system introduces an intermediary automated determination process between image acquisition and scanning execution. The apparatus acts as an intermediary that automatically analyzes the positioning image, matches it with reference images, determines the optimal scanning protocol, and presents it to the operator for confirmation, thereby eliminating the need for manual protocol selection and reducing time loss.
3Ease of operation
If manual protocol selection is performed, then the ease of operation is reduced, but the extent of automation is limited
Solution Approach 1:
The system performs self-service by automatically determining the scanning protocol based on the positioning image and pre-stored reference images. The apparatus autonomously completes the protocol selection process without requiring manual intervention from the operator, thereby significantly improving ease of operation while maximizing automation.
Solution Approach 2:
The system implements feedback by automatically analyzing the positioning image, comparing it with reference images, determining the match degree, and selecting the appropriate scanning protocol based on the analysis results. This automated feedback loop eliminates manual protocol selection steps and improves operational ease while increasing automation extent.
Data Source
AI summary
A method for setting a scanning protocol and an apparatus thereof are provided. The method includes: creating a plain film positioning image; receiving a point or a line or a region of interest on the plain film positioning image input by an operator; generating a region to be matched, based on the point or the line or the region of interest; determining whether there is pre-stored reference image having a matching degree greater than a preset threshold by comparing pre-stored reference images with the region to be matched; obtaining a reference image in the case that the reference image has a matching degree greater than the preset threshold; selecting a scanning protocol corresponding to the reference image based on a preset correspondence between reference images and scanning protocols; and completing a setting of the scanning protocol in the case that there is the scanning protocol corresponding to the reference image.