A novel hierarchical K-means clustering for white blood cells segmentation(International Forum on Medical Imaging in Asia 2009 (IFMIA 2009))

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents a hierarchical K-means clustering scheme for white blood cells (WBCs) segmentation in blood cell images. The proposed scheme solves the problem of WBCs segmentation by manual manner traditionally. In the proposed hierarchical K-means clustering, there are three processing levels. The first level removes the background of the blood cell image, then large amount of red blood cells and a little of cytoplasm are discriminated in the second level. The last level obtains the nucleus of each white blood cell automatically. After clustering, this scheme recognizes cytoplasm of white blood cells by calculating the difference of pixel values between red band and green band in RGB color space. Experimental results show that the proposed method can segment nuclei and cytoplasm of white blood cells efficiently and accurately.

• 2009-01-12

著者

• Liu Kuo-ching

  Department Of Medical Laboratory Science And Biotechnology China Medical University

• Wu Hsien-chu

  Graduate School Of Computer Science And Information Technology National Taichung Institute Of Techno

• Shiu Jen-Yun

  Graduate School of Computer Science and Information Technology, National Taichung Institute of Techn

• Shiu Jen-yun

  Graduate School Of Computer Science And Information Technology National Taichung Institute Of Techno

関連論文

• A novel hierarchical K-means clustering for white blood cells segmentation(International Forum on Medical Imaging in Asia 2009 (IFMIA 2009))

スポンサーリンク