Skip to main content

Medical-image Analysis and Statistical Interpretation Lab

Evaluation of Five Image Registration Tools for Abdominal CT: Pitfalls and Opportunities with Soft Anatomy.

Posted by on Thursday, February 12, 2015 in Abdomen Imaging, Image Segmentation, Registration.

Christopher P. Lee, Zhoubing Xu, Ryan P. Burke, Rebeccah B. Baucom, Benjamin K. Poulose, Richard G. Abramson, Bennett A. Landman. “Evaluation of Five Image Registration Tools for Abdominal CT: Pitfalls and Opportunities with Soft Anatomy.” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2015. †

Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4405654/

Abstract

Image registration has become an essential image processing technique to compare data across time and individuals. With the successes in volumetric brain registration, general-purpose software tools are beginning to be applied to abdominal computed tomography (CT) scans. Herein, we evaluate five current tools for registering clinically acquired abdominal CT scans. Twelve abdominal organs were labeled on a set of 20 atlases to enable assessment of correspondence. The 20 atlases were pairwise registered based on only intensity information with five registration tools (affine IRTK, FNIRT, Non-Rigid IRTK, NiftyReg, and ANTs). Following the brain literature, the Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. However, interpretation was confounded due to a significant proportion of outliers. Examining the retrospectively selected top 1 and 5 atlases for each target revealed that there was a substantive performance difference between methods. To further our understanding, we constructed majority vote segmentation with the top 5 DSC values for each organ and target. The results illustrated a median improvement of 85% in DSC between the raw results and majority vote. These experiments show that some images may be well registered to some targets using the available software tools, but there is significant room for improvement and reveals the need for innovation and research in the field of registration in abdominal CTs. If image registration is to be used for local interpretation of abdominal CT, great care must be taken to account for outliers (e.g., atlas selection in statistical fusion).

The proposed general pipeline for conducting registrations and followed by metric analyses. Initially, each of 20 CT scans were pairwise linear registered using affine IRTK. Using the linear registration as a baseline, the registrations went through four non-rigid registrations. The output non-rigid registrations are evaluated against the manual segmentation via the DSC overlap, mean surface distance, and Hausdorff distance for each organ of interest. The comparison of the four non-rigid registrations was first based on all pairs of inter-subject registrations for all organs. Then another round of comparison was applied to the top 1 and top 5 registrations selected retrospectively for each target CT scan.
The proposed general pipeline for conducting registrations and followed by metric analyses. Initially, each of 20 CT scans were pairwise linear registered using affine IRTK. Using the linear registration as a baseline, the registrations went through four non-rigid registrations. The output non-rigid registrations are evaluated against the manual segmentation via the DSC overlap, mean surface distance, and Hausdorff distance for each organ of interest. The comparison of the four non-rigid registrations was first based on all pairs of inter-subject registrations for all organs. Then another round of comparison was applied to the top 1 and top 5 registrations selected retrospectively for each target CT scan.