Automated delineation of lung tumors from CT images using a single click ensemble segmentation approach

PATTERN RECOGNITION

卷:46

Article

Gu, Yuhua¹  Kumar, Virendra¹  Hall, Lawrence O.²  Goldgof, Dmitry B.²  Li, Ching-Yen²  Korn, Rene³  Bendtsen, Claus⁴  Velazquez, Emmanuel Rios⁵  Dekker, Andre⁵  Aerts, Hugo⁵  Lambin, Philippe⁵  Li, Xiuli⁶  Tian, Jie⁶  Gatenby, Robert A.¹  Gillies, Robert J.¹ 

[1] H Lee Moffitt Canc Ctr & Res Inst, Dept Imaging, Tampa, FL 33612 USA

[2] Univ S Florida, Dept Comp Sci & Engn, Tampa, FL 33620 USA

[3] Definiens AG, D-80339 Munich, Germany

[4] AstraZeneca, Discovery Sci, Macclesfield SK10 4TG, Cheshire, England

[5] Univ Hosp Maastricht, Dept Radiat Oncol, Maastricht, Netherlands

[6] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Med Image Proc Grp, Beijing 100190, Peoples R China

关键词: Image features;    Delineation;    Lung tumor;    Lesion;    CT;    Region growing;    Ensemble segmentation;   

DOI  :  10.1016/j.patcog.2012.10.005

来源: Elsevier

【 摘 要 】

A single click ensemble segmentation (SCES) approach based on an existing Click & Grow algorithm is presented. The SCES approach requires only one operator selected seed point as compared with multiple operator inputs, which are typically needed. This facilitates processing large numbers of cases. Evaluation on a set of 129 CT lung tumor images using a similarity index (SI) was done. The average SI is above 93% using 20 different start seeds, showing stability. The average SI for 2 different readers was 79.53%. We then compared the SCES algorithm with the two readers, the level set algorithm and the skeleton graph cut algorithm obtaining an average SI of 78.29%, 77.72%, 63.77% and 63.76%, respectively. We can conclude that the newly developed automatic lung lesion segmentation algorithm is stable, accurate and automated. (C) 2012 Elsevier Ltd. All rights reserved.

【 授权许可】

Free