[Updated on Apr. 18] Integration of CiNii Articles into CiNii Research


Bibliographic Information

Other Title
  • ゾウキ ソンザイ ユウド アトラス ト グラフカット オ モチイタ フクブ 3ジゲン CTゾウ カラ ノ ゾウキ リョウイキ チュウシュツ
  • Organ segmentation from 3D abdominal CT images using likelihood atlas of organ existence and graph cut

Search this article


In this paper, we propose a multi organ segmentation method from 3D abdominal CT images. In our method, we extract organs using multiple likelihood atlases of the organ existence, instead of single atlas. In our method, first we apply a clustering method to training image datasets based on image similarity. We generate average images and atlases for each cluster. When an input image is given, we select an atlas that has the maximum image similarity between the average image and the input image. We use the selected atlas to extract organs. Then, we extract multi organs roughly by the MAP estimation from the selected atlas and the input image. Finally, we perform precise segmentation by using a multi label graph cut. We apply this method to 100 cases of abdominal CT images. Jaccard indices were 88.6% for liver, 73.9% for spleen, 42.0% for pancreas, and 79.8% for kidney, respectively.

IEICE Technical Report;MI2010-123


Citations (4)*help

See more


See more


Report a problem

Back to top