Related Experiment Video
Updated: Aug 8, 2026
08:59
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
Published on: October 28, 2018
Simulation of tissue atrophy using a topology preserving transformation model
Bilge Karaçali1, Christos Davatzikos
1School of Biomedical Engineering, Science, and Health Systems, Drexel University, 3120-24 Market Street, Philadelphia, PA 19104, USA. bilge@drexel.edu
IEEE Transactions on Medical Imaging
|May 13, 2006
Summary
This study introduces a new method to simulate tissue loss, like brain atrophy, in medical images. The technique accurately models volumetric changes, aiding in the evaluation of medical image analysis tools.
Area of Science:
- Medical Imaging
- Computational Anatomy
- Image Processing
Background:
- Volumetric changes, such as atrophy, are critical indicators in diagnosing and monitoring neurological conditions.
- Accurate simulation of these changes is essential for developing and validating medical image analysis techniques.
Purpose of the Study:
- To develop a novel method for simulating realistic volumetric changes, specifically atrophy, in medical images.
- To provide a framework for generating images with controlled levels of tissue loss.
Main Methods:
- An energy minimization strategy is employed to find a dense warping deformation.
- This deformation precisely controls the volumetric loss in labeled tissues to match a desired atrophy level.
Main Results:
- Simulations on a real brain image successfully generated realistic depictions of tissue loss.
- The method establishes exact correspondences between pre- and post-atrophy images.
Conclusions:
- The proposed method offers a robust framework for simulating atrophy without making assumptions about tissue mechanics.
- The generated image correspondences are valuable for assessing image registration and atrophy quantification algorithms.
