Related Experiment Video
Updated: Jul 10, 2026
Quantitative Assessment Protocol for Facial Soft Tissue Volumetric Changes with Stereophotogrammetry
Published on: December 9, 2025
Simultaneous registration and landmark detection
1Wolfson Med. Vision Lab., Oxford Univ., UK. sarah@robots.ox.ac.uk
Abstract:
We are developing a system for patient management in colorectal cancer, in which a difficult case of non-rigid registration, namely of pre- and post-therapy images, arises. Numerous non-rigid registration algorithms have been proposed in medical image analysis, and we have applied several leading algorithms to our non-rigid registration problem; but with unpromising results. The fundamental reason appears to be that they lack with knowledge of the particular application. We propose a graphical representation of anatomical knowledge relevant for colorectal cancer, and of the ways in which this anatomy may be predicted to change as a result of chemo and radiotherapy. We show how we interleave this representation with an adaptive registration algorithm to make the non-rigid registration result both robust and accurate.
Insights
This study introduces a novel method for accurate medical image registration in colorectal cancer patient management. By incorporating anatomical knowledge, the system improves the precision of pre- and post-therapy image alignment.
Area of Science:
- Medical image analysis
- Computational anatomy
- Oncology
Background:
- Accurate patient management in colorectal cancer requires precise image registration.
- Standard non-rigid registration algorithms struggle with pre- and post-therapy image alignment due to a lack of application-specific knowledge.
Purpose of the Study:
- To develop an improved non-rigid image registration system for colorectal cancer patient management.
- To enhance registration accuracy and robustness by integrating anatomical knowledge.
Main Methods:
- Proposed a graphical representation of anatomical knowledge specific to colorectal cancer.
- Modeled predicted anatomical changes from chemo and radiotherapy.
- Interleaved this anatomical knowledge with an adaptive registration algorithm.
Main Results:
- Standard registration algorithms yielded unpromising results for pre- and post-therapy colorectal cancer images.
- The proposed method, incorporating anatomical knowledge, achieved robust and accurate non-rigid registration.
Conclusions:
- Integrating application-specific anatomical knowledge is crucial for effective medical image registration in complex cases like colorectal cancer.
- The developed system offers a more robust and accurate solution for aligning pre- and post-therapy images, aiding patient management.
