Deformable Registration Techniques for Thoracic CT Images by Ali Imam Abidi & S. K. Singh

Author:Ali Imam Abidi & S. K. Singh
Language: eng
Format: epub
ISBN: 9789811058370
Publisher: Springer Singapore

4.3.2 Proposed Methodology

The procedure acquired is as such that a temporal thoracic image sequence from time t = 0.1 to 0.6 s is taken such that first frame of the sequence is the full inhale frame and the last frame is full exhale frame. This paper uses the Speeded up Robust Feature detector (SURF) (Bay et al. 2006, 2008) to obtain a feature set comprising of common feature points throughout the image sequence. It detects and describes the feature set irrespective of any scaling and/or rotation in the corresponding images. SURF provides better approximations in comparison to previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster than any other state-of-the-art feature detector. These feature sets are then fed into the OFM estimation algorithm to identify the deformation path throughout the temporal sequence, be it peripheral or local.

Optical flow has been successfully applied to motion estimation of points/point clouds and other point set surface definitions over a temporal sequence (Sun et al. 2014). It performs better than its contemporaries while tracing deformations that are realistic and guides the user in manipulation of real-world objects. It also allows the user to specify the deformations using either sets of points or line segments, the later useful for controlling curves and profiles present in the image. For each of these techniques, it provides simple closed-form solutions that yield fast deformations, which can be performed in real-time. The proposed methodology aims to track and estimate the deformations by tracking the transition of the interest points through the sequence from full inhale to full exhale frame. The overall process can be referred to in Fig. 4.1.

Fig. 4.1The proposed framework structure

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.