Zhou Xiangrong, Hayashi Tatsuro, Hara Takeshi, Fujita Hiroshi, Yokoyama Ryujiro, Kiryu Takuji, Hoshi Hiroaki
Department of Intelligent Image Information, Division of Regeneration and Advanced Medical Sciences, Graduate School of Medicine, Gifu University, Yanagito 1-1, Gifu 501-1194, Japan.
Comput Med Imaging Graph. 2006 Jul;30(5):299-313. doi: 10.1016/j.compmedimag.2006.06.002. Epub 2006 Aug 22.
This paper describes a fully automated segmentation and recognition scheme, which is designed to recognize lung anatomical structures in the human chest by segmenting the different chest internal organ and tissue regions sequentially from high-resolution chest CT images. A sequential region-splitting process is used to segment lungs, airway of bronchus, lung lobes and fissures based on the anatomical structures and statistical intensity distributions in CT images. The performance of our scheme is evaluated by segmenting lung structures from high-resolution multi-slice chest CT images from 44 patients; the validity of our method was proved by preliminary experimental results.
