基于改进K-Means的腹内脂肪自动定量检测算法.pdfVIP

第29 卷 第4 期 计算机辅助设计与图形学学报 Vol. 29 No.4 2017 年4 月 Journal of Computer-Aided Design Computer Graphics Apr. 2017 基于改进K-Means 的腹内脂肪自动定量检测算法 1) 1,2)* 3) 2,3) 曹鸿吉 , 盛 斌 , 吴 雯 , 吴恩华 1) (上海交通大学计算机科学与工程系 上海 200240) 2) ( 中国科学院软件研究所计算机科学国家重点实验室 北京 100080) 3) (澳门大学科技学院电脑及资讯科学系 澳门) (shengbin@sjtu.edu.cn) : 检测肥胖病人腹部脂肪的分布及含量情况, 判定腹型肥胖的种类, 对评估和治疗糖尿病和心血管代谢等相关疾 病有重要的临床价值. 通过分析人体腹部磁共振(MR)图像中脂肪成像的特点, 提出一种无监督的腹部脂肪自动检测算法. 该算法运用 SLIC 算法对腹部磁共振图像进行预处理, 生成超像素; 然后用泛洪填充算法进行背景剔除, 再将改进的 K-means 算法用于脂肪区域与非脂肪区域以及皮下脂肪与内脏脂肪的自动分割; 最后基于分割结果实现对腹部脂肪的定量 分析. 实验结果表明, 文中算法能精确地检测出腹部脂肪的含量, 并能够区分脂肪的类别, 相比以往的半自动或全自动算 法, 其准确率得到了有效的提高. ：脂肪检测; 磁共振图像; 图像处理; 图像分割; SLIC 算法; K-means 算法 ：TP391.41 Automatic Quantitative Detection Algorithm of Abdominal Fat Based on Improved K-Means Algorithm Cao Hongji1), Sheng Bin1,2)*, Wu Wen3) , and Wu Enhua2,3) 1) (Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240) 2) (The State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Science, Beijing 100080) 3) (Department of Computer and Information Science, Faculty of Science and Technology, University of Macau, Macau) Abstract: As many important diseases of human body are closely related to the abdominal obesity, such as dia- betes and cardiovascular disease, detecting distribution and quantity of abdominal fat in human body is of great significance to determine the type of abdominal obesity in the medical research and clinical applications. By ana- lyzing the abdominal Magnetic Resonance (MR) images of human body, we propose an unsupervised automatic detection algorithm of abdominal fat. First, the abdominal MR image was preprocessed to be represented by su- per-pixels using SLIC algorithm;