基于级联Dense-UNet和图割的肝脏肿瘤自动分割  

Automatic Liver Tumor Segmentation Based on Cascaded Dense-UNet and Graph Cuts

作　　者：杨振[1,2] 邸拴虎[1] 赵于前 廖苗[1,4] 曾业战 YANG Zhen;DI Shuanhu;ZHAO Yuqian;LIAO Miao;ZENG Yezhan(School of Automation,Central South University,Changsha 410083,China;Department of Oncology,Xiangya Hospital,Central South University,Changsha 410083,China;Hunan Xiangjiang Artificial Intelligence Academy,Changsha,410083,China;School of Computer Science and Engineering,Hunan University of Science and Technology,Xiangtan 411100,China;School of Electrical and Information Engineering,Hunan University of Technology,Zhuzhou 412007,China)

机构地区：[1]中南大学自动化学院,长沙410083 [2]中南大学湘雅医院肿瘤科,长沙410083 [3]湖南湘江人工智能学院,长沙410083 [4]湖南科技大学计算机科学与工程学院,湘潭411100 [5]湖南工业大学电气与信息工程学院,株洲412007

出　　处：《电子与信息学报》2022年第5期1683-1693,共11页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(62076256,61772555,61702179);湖南省教育厅资助科研项目(20B239,18C0497);湖南省研究生科研创新项目(CX20200129);湖南省自然科学基金(2021JJ30275)。

摘　　要：腹部CT图像肝脏肿瘤分割是进行肝脏疾病诊断、手术规划和放射治疗的重要前提。针对肝脏肿瘤灰度异质、纹理丰富、边界模糊等因素引起的分割困难,该文提出基于级联Dense-Unet和图割的自动精确鲁棒分割方法。首先运用级联的Dense-UNet获取肝脏肿瘤初始分割结果及感兴趣区域,然后利用图像像素级和区域级特征,分别构建可有效区分肿瘤与非肿瘤的灰度模型和概率模型,并将其融入图割能量函数,进一步精确分割感兴趣区域中的肿瘤组织。最后分别采用LiTS和3Dircadb公共数据库作为训练集与测试集进行实验,并与现有多种自动分割方法进行了比较。结果表明,提出方法可有效分割CT图像中灰度、形状、大小、位置各异的肝脏肿瘤,能提取更精确的肿瘤边界,尤其对于对比度低、边界模糊的肿瘤具有明显优势。Liver tumor segmentation from abdominal CT image is an important prerequisite for liver disease diagnosis,surgical planning,and radiation therapy.However,the segmentation remains a challenging problem since the tumors in CT images generally have heterogeneous intensities,complicated textures,and ambiguous boundaries.To address this,an automatic,accurate,and robust segmentation method is proposed based on cascaded Dense-Unet and graph cuts.Firstly,the cascaded Dense-UNet is used to obtain liver tumor initial segmentation results as well as the tumor Regions Of Interest(ROIs).Then,an intensity model and a probability model are established respectively by utilizing pixel-wise and patch-wise features in order to distinguish between tumor and non-tumor,and these models are further integrated into the graph cuts energy function to segment the tumor from ROIs accurately.Finally,experiments are carried out on LiTS and 3Dircadb datasets,which are respectively used as training set and testing set,and this method is compared with many other existing automatic segmentation methods.Results demonstrate that the proposed method can segment liver tumors in CT images with different intensity,texture,shape and size more effectively and can extract the tumor boundaries more accurately than other methods,especially for the tumors with low contrasts and ambiguous boundaries.

关 键 词：CT图像 肿瘤分割 Dense-UNet 图割 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]