点击次数：

论文类型：期刊论文

发表时间：2016-05-01

发表刊物：MEDICAL PHYSICS

收录刊物：SCIE、PubMed

卷号：43

期号：5

页面范围：2229

ISSN号：0094-2405

关键字：SIFT-flow; label transfer; registration; multiatlas; segmentation

摘要：Purpose: In this paper, the authors proposed a new 3D registration algorithm, 3D-scale invariant feature transform (SIFT)-Flow, for multiatlas-based liver segmentation in computed tomography (CT) images.
   Methods: In the registration work, the authors developed a new registration method that takes advantage of dense correspondence using the informative and robust SIFT feature. The authors computed the dense SIFT features for the source image and the target image and designed an objective function to obtain the correspondence between these two images. Labeling of the source image was then mapped to the target image according to the former correspondence, resulting in accurate segmentation. In the fusion work, the 2D-based nonparametric label transfer method was extended to 3D for fusing the registered 3D atlases.
   Results: Compared with existing registration algorithms, 3D-SIFT-Flow has its particular advantage in matching anatomical structures (such as the liver) that observe large variation/deformation. The authors observed consistent improvement over widely adopted state-of-the-art registration methods such as ELASTIX, ANTS, and multiatlas fusion methods such as joint label fusion. Experimental results of liver segmentation on the MICCAI 2007 Grand Challenge are encouraging, e.g., Dice overlap ratio 96.27%+/- 0.96% by our method compared with the previous state-of-the-art result of 94.90%+/- 2.86%.
   Conclusions: Experimental results show that 3D-SIFT-Flow is robust for segmenting the liver from CT images, which has large tissue deformation and blurry boundary, and 3D label transfer is effective and efficient for improving the registration accuracy. (C) 2016 American Association of Physicists in Medicine.