Tomographic Image Segmentation for Radiotherapy Motion Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for radiotherapy treatment planning struggle to accurately track moving objects, such as tumors, during a patient's respiratory cycle, leading to inaccurate delineation of target regions and normal critical organs.
Innovation Solution
A computer-implemented method that acquires multiple subsets of tomographic images of an object, segments each image to identify regions of interest, and generates a region of interest contour and probability distribution to enhance treatment planning ancillary data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physicians or technicians empirically estimate an outer contour envelope of a motion object to perform dose planning, then the treatment planning can be performed, but the accuracy of determining the irradiation area is insufficient
Solution Approach 1:
The patent segments the tomographic images into multiple subsets corresponding to different axial positions, and further segments each image into regions of interest. This segmentation allows the system to process and analyze motion information at different spatial locations independently, improving the accuracy of irradiation area determination without requiring a monolithic complex system
Solution Approach 2:
The patent introduces an intermediary processing system that automatically generates region of interest contours and probability distributions from the segmented images. This intermediary computational layer bridges the raw image data and the treatment planning requirements, enabling accurate irradiation area determination through automated contour generation and probability calculation
2Reliability
If respiratory gating technology or deviceless 4D scanning is used to track patient motion, then motion status can be acquired, but additional devices or complex scanning procedures are required
Solution Approach 1:
The patent extracts motion information directly from the tomographic images themselves, without requiring additional respiratory gating devices or complex 4D scanning procedures. By segmenting the images and analyzing regions of interest within the standard scanning data, the system extracts reliable motion status information while avoiding the complexity of extra hardware and procedures
Solution Approach 2:
The patent enables the tomographic imaging system to serve itself by automatically processing its own output data to generate motion information and treatment planning ancillary data. The system uses the scanned images to create the analysis contours and probability distributions needed for treatment planning, eliminating the need for separate motion tracking devices
3Measurement precision
If multiple subsets of tomographic images are processed to generate enhanced ancillary data, then treatment planning accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent segments the comprehensive image data into manageable subsets organized by axial position, and further segments each image into regions of interest. This segmentation strategy enables the system to process and analyze motion information at different spatial locations independently, improving treatment planning accuracy while managing computational complexity through structured data organization
Solution Approach 2:
The patent performs preliminary segmentation and region of interest identification during the image acquisition phase, preparing the data structure in advance. By organizing the tomographic images into subsets and identifying regions of interest before final analysis, the system reduces the computational burden during the actual treatment planning calculation phase
Data Source
AI summary
Provided are a method and an apparatus for generating enhanced treatment planning ancillary data. The example method includes acquiring a plurality of subsets of tomographic images of an object, where the plurality of subsets respectively correspond to different positions in a scanning axial direction, and where each of the plurality of subsets includes a plurality of tomographic images, at different time points of a specific scanning time period, obtained by scanning a movable portion of the object at a specific position in the scanning axial direction. The method further includes segmenting each of the plurality of tomographic images in one of the plurality of subsets to separately obtain a region of interest in each tomographic image and generating a region of interest contour of the one subset based on the regions of interest of the plurality of tomographic images in the one subset.