东南大学学报（自然科学版）2012，Vol.42Issue(3)：419-423,5.DOI:10.3969/j.issn.1001-0505.2012.03.005
基于曲线波的超声图像分割
Ultrasound image segmentation based on curvelet
摘要
Abstract
In order to improve the accuracy of prostate ultrasound image segmentation, a semi-supervised automatic segmentation method based on curvelet transform is proposed. First, the Riemann-Liouville (RL) fractional differential operator which is sensitive to the tiny fluctuations is used to enhance the fuzzy boundary and image texture. Secondly, the image is transformed into curvelet domain and different subbands are obtained to represent the ultrasound image characteristics. Thirdly, the Adaboost algorithm is applied to identify the lesion and non-lesion regions in the ultrasound image. Finally, the median filter and the erosion operator are used to smooth the lesion regions' edge. Experiments show that the proposed method outperforms the approaches based on co-occurrence matrix and dyadic wavelet in terms of accuracy.关键词
Riemann-Liouville分数阶微分/曲线波变换/Adaboost/超声图像/分割Key words
Riemann-Liouville fractional differential/ curvelet transform/ Adaboost/ ultrasound image/ segmentation分类
信息技术与安全科学引用本文复制引用
曹琳,云挺,舒华忠..基于曲线波的超声图像分割[J].东南大学学报（自然科学版）,2012,42(3):419-423,5.基金项目
国家重点基础研究发展计划(973计划)资助项目(2011CB707904)、国家自然科学基金资助项目(60911130370)、教育部博士点基金资助项目(20110092110023). （973计划）
