A Feature Tracking-based Approach for Local Deformation Fields Measurement of Biological Tissue from MR Volumes

While a variety of different deformable model al- gorithms have been reported for the deformation measurement of biological tissue, few attempts in feature tracking areas have been reported. In this paper, we investigated the feature point automatic extraction and tracking technique to measure local deformation fields from 3D MR volumetric images. To track the precisely homologous position in the deformed MR volumetric image for the given feature point in the initial MR volumetric image, a least squares-based 3D image matching method was introduced. To test the validity of our approach, we applied the proposed method to MR volumetric images of a volunteer's calf. Our preliminary experimental results indicate that the proposed approach is feasible .