Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT

Abstract

Objective This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans. Methods Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively. Results The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT. Conclusion There is substantial room for improvement in image registration for abdominal CT. Significance All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.

TernaryNet: faster deep model inference without GPUs for medical 3D segmentation using sparse and binary convolutions

“…Comparison to State-of-the-Art: Several approaches have been evaluated in the last few years on the NIH dataset and a similar corpus of abdominal CT scans (the BCV challenge data described in [29]). Accuracies for pancreas segmentation without CNNs are often relatively low, e.g.…”

Automatic Multiorgan Segmentation via Multiscale Registration and Graph Cut

“…The reason is that the relatively low inter-subject variation in overall brain shape and structure locations allows good alignment. In contrast, abdominal structures exhibit high location and shape variability and are challenging for registration [20].…”

Liver Segmentation in CT Images Using Three Dimensional to Two Dimensional Fully Convolutional Network

“…µ� , � = � ≠ �. In (4), p indicates position and shows gray-scale value. The bilateral kernel motivates nearby pixels with similar intensity to be in the same class while unilateral is used for smoothness and elimination of isolated regions.…”