Automated Clinical Target Volume Delineation Using Signed Distance Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for clinical target volume delineation in radiotherapy are manual, inefficient, and prone to inaccuracies, leading to suboptimal radiotherapy outcomes due to high variability among oncologists.
Innovation Solution
An automated clinical target volume delineation method using radiotherapy computed tomography images, which involves obtaining binary images of gross tumor volume, lymph nodes, and organs at risk, calculating signed distance maps, and inputting these into a clinical target volume delineation model for precise delineation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual delineation by oncologists is used, then the clinical target volume can be determined, but the delineation efficiency is low and the results may be inaccurate
Solution Approach 1:
The patent replaces the manual mechanical delineation process performed by oncologists with an automated computer-based system. The system uses image processing algorithms to automatically segment and delineate the clinical target volume from medical images, substituting human manual operations with automated computational methods. This resolves the contradiction by achieving both high accuracy through consistent algorithmic application and high efficiency through automation, eliminating the trade-off between manual precision and automated speed.
2Productivity
If automated delineation is implemented, then the delineation efficiency is improved, but the automatic delineation of CTV cannot be realized with high accuracy
Solution Approach 1:
The patent applies segmentation by dividing the automated delineation process into distinct functional modules: image preprocessing, feature extraction, boundary detection, and result generation. Each module handles specific aspects of the delineation task, allowing the system to achieve both high efficiency through automation and high accuracy through specialized processing at each stage. This modular segmentation enables the automated system to overcome the accuracy limitations of previous automated methods.
Solution Approach 2:
The patent introduces intermediary processing steps between raw image input and final delineation output, including image enhancement, noise filtering, and feature detection algorithms. These intermediary processes refine the input data and extract critical information that improves the accuracy of the automated delineation, resolving the contradiction by adding intermediate processing layers that enhance precision without compromising automation efficiency.
3Reliability
If manual delineation is used, then the process can be completed, but it is a huge burden for oncologists and time-consuming
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform the complete delineation task without requiring oncologist intervention for each case. The automated system independently processes medical images, applies delineation algorithms, and generates results, making the system self-sufficient. This resolves the contradiction by maintaining reliable delineation completion while eliminating the time burden on oncologists, as the system operates autonomously without requiring their time investment.
Data Source
AI summary
The present disclosure provides a clinical target volume delineation method and an electronic device. The method includes: receiving a radiotherapy computed tomography (RTCT) image; and obtaining a plurality of binary images by delineating a gross tumor volume (GTV), lymph nodes (LNs), and organs at risk (OARs) in the RTCT image. A SDMs for each of the binary images is calculated. The RTCT image and all the SDM are finally input into a clinical target volume (CTV) delineation model; and a CTV in the RTCT image is delineated by the CTV delineation model. An automatic delineation of the CTV of esophageal cancer are realized, a delineation efficiency is high and a delineation effect is good.