Lung Segmentation for Chest Radiograph by Using Adaptive Active Shape Models

摘要：

In this paper, we proposed an automatic lung segmentation method. We designed a ROI based method to estimate a proper initial lung boundary for ASM deformation by deriving the translation and the scaling parameters from the lung ROI. An adaptive ASM, using k-means clustering and silhouette-based cluster validation technique, was proposed to adapt to the lung shape change so that the lung shape variation among people can be overwhelmed. The experiments indicated that the segmentation performance of the adaptive ASM is superior to the traditional ASM approaches.

关键词： Lung segmentation chest radiograph adaptive ASM

作者: Jiann-Shu Lee Hsing-Hsien Wu Ming-Zheng Yuan

作者单位: Department of Computer Science and Information Engineering,National University of Tainan,Taiwan Division of Thoracic Surgery,Tainan Municipal Hospital,Taiwan Institute of System Engineering,National University of Tainan,Taiwan

会议类型: 国际会议

会议名称: The Fifth International Conference on Information Assurance and Security(第五届信息保障与安全国际会议)

会议地点: 西安

会议语种:英文

页码: 383-386

在线出版日期: 2009-08-18（万方平台首次上网日期，不代表论文的发表时间）