Soft Tissue Tracking via DRR-Xray Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for tracking the position of moving soft tissue in medical procedures, such as radiosurgery or radiotherapy, are inefficient and prone to errors due to the difficulty in visually inspecting and automatically fusing digitally rendered radiographs with X-ray images, especially when dealing with vital movements like breathing or heartbeats, which can lead to inaccurate irradiation of target regions.
Innovation Solution
A data processing method that uses a computer to track anatomical body parts by associating them with specific movement phases through infrared-reflecting markers and navigation systems, allowing for the fusion of pre-acquired CT images with real-time X-ray images to accurately highlight and follow the movement of tissues like the diaphragm or tumors during medical procedures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple DRRs are compared with a single X-ray image to track soft tissue position, then the tracking coverage is improved, but the measurement precision deteriorates due to outdated information and erroneous results
Solution Approach 1:
The patent applies preliminary action by pre-acquiring a planning CT image and generating DRRs from it before the actual treatment. This allows the system to have a reference framework ready in advance, which is then matched with real-time X-ray images during treatment, ensuring that the reference data is current and accurate for tracking soft tissue position.
Solution Approach 2:
The patent uses copying by creating digitally rendered radiographs (DRRs) from the planning CT image. These DRRs are synthetic copies that simulate what the X-ray images would look like from the same angles, allowing for direct comparison and accurate tracking of soft tissue position without needing to acquire multiple actual X-ray images.
2Productivity
If automated multi-modal fusion is applied to fuse DRRs with X-ray images, then the productivity is improved by reducing manual inspection time, but the reliability deteriorates due to lack of robustness
Solution Approach 1:
The patent implements feedback by using the matched X-ray image and its corresponding DRR as a reference pair, then comparing this reference against other X-ray images taken at different angles. The system provides feedback on the matching quality and uses this information to accurately determine soft tissue position, ensuring both efficiency and reliability in the automated tracking process.
3Measurement precision
If visual inspection of fusion between DRR and X-ray image is performed, then the measurement precision can be maintained through human judgment, but the productivity deteriorates due to difficulty and time-consuming nature
Solution Approach 1:
The patent introduces an intermediary by using the planning CT image as a bridge between the actual X-ray images and the soft tissue position tracking. The CT image serves as a common reference that can be rendered into DRRs for comparison with X-rays, facilitating automated matching and position determination without requiring direct visual inspection of complex multi-modal fusions.
4Device complexity
If a single X-ray image is used for comparison with multiple DRRs, then the device complexity is reduced, but the measurement precision deteriorates due to outdated information
Solution Approach 1:
The patent applies dynamics by making the reference X-ray image selection dynamic rather than static. Instead of using a single fixed X-ray image for all comparisons, the system dynamically selects and matches the most appropriate X-ray image that corresponds to each DRR based on imaging parameters and timing, ensuring that the reference data is always current and accurate for the specific tracking moment.
Data Source
AI summary
The present invention relates to a medical data processing method of determining the representation of an anatomical body part (2) of a patient (1) in a sequence of medical images, the anatomical body part (2) being subject to a vital movement of the patient (1), the method being constituted to be executed by a computer and comprising the following steps:a) acquiring advance medical image data comprising a time-related advance medical image comprising a representation of the anatomical body part (2) in a specific movement phase;b) acquiring current medical image data describing a sequence of current medical images, wherein the sequence comprises a specific current medical image comprising a representation of the anatomical body part (2) in the specific movement phase, and a tracking current medical image which is different from the specific current medical image and comprises a representation of the anatomical body part (2) in a tracking movement phase which is different from the specific movement phase;c) determining, based on the advance medical image data and the current medical image data, specific image subset data describing a specific image subset of the specific current medical image, the specific image subset comprising the representation of the anatomical body part (2);d) determining, based on the current medical image data and the image subset data, subset tracking data describing a tracked image subset in the tracking current medical image, the tracked image subset comprising the representation of the anatomical body part (2).