K
Kenji Shinozaki
Publications - 9
Citations - 151
Kenji Shinozaki is an academic researcher. The author has contributed to research in topics: Segmentation & Scale-space segmentation. The author has an hindex of 5, co-authored 9 publications receiving 144 citations.
Papers
More filters
Journal ArticleDOI
Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography.
TL;DR: This study verified the effectiveness of two-stage segmentation with spatial standardization of pancreas in delineating the Pancreas region, patient-specific probabilistic atlas guided segmentation in reducing false negatives, and a classifier ensemble in boosting segmentation performance.
Book ChapterDOI
Automated segmentation of 3D CT images based on statistical atlas and graph cuts
Akinobu Shimizu,Keita Nakagomi,Takuya Narihira,Hidefumi Kobatake,Shigeru Nawano,Kenji Shinozaki,Koich Ishizu,Kaori Togashi +7 more
TL;DR: An effective combination of a statistical atlasbased approach and a graph cuts algorithm for fully automated robust and accurate segmentation is presented and two new submodular energies for graph cuts are proposed.
Proceedings ArticleDOI
Segmentation of liver region with tumorous tissues
Xuejun Zhang,Xuejun Zhang,Gobert N. Lee,Tetsuji Tajima,Teruhiko Kitagawa,Masayuki Kanematsu,Xiangrong Zhou,Takeshi Hara,Hiroshi Fujita,Ryujiro Yokoyama,Hiroshi Kondo,Hiroaki Hoshi,Shigeru Nawano,Kenji Shinozaki +13 more
TL;DR: Wang et al. as mentioned in this paper proposed a non-density based method for extracting the liver region containing tumor tissues by edge detection processing, and the final liver region integrates the tumor region with the liver tissue.
Proceedings ArticleDOI
Computer-aided detection (CAD) of hepatocellular carcinoma on multiphase CT images
Tetsuji Tajima,Xuejun Zhang,Teruhiko Kitagawa,Masayuki Kanematsu,Xiangrong Zhou,Takeshi Hara,Hiroshi Fujita,Ryujiro Yokoyama,Hiroshi Kondo,Hiroaki Hoshi,Shigeru Nawano,Kenji Shinozaki +11 more
TL;DR: The result demonstrates that the edge-detection-based method is effective in locating the cancer region by using the information obtained from different phase images.
Book ChapterDOI
Medical Image Processing Competition in Japan
TL;DR: This paper describes a medical image processing competition held annually in Japan from 2002 to 2008 to evaluate existing segmentation algorithms and boost this type of research in Japan.