肝脏及肿瘤图像分割方法综述  

Review of liver and tumor image segmentation methods

作　　者：陈英[1] 郑铖 易珍[2] 胡菲 徐国辉[3] Chen Ying;Zheng Cheng;Yi Zhen;Hu Fei;Xu Guohui(School of Software,Nanchang Hangkong University,Nanchang 330063,China;Radiology,Jiangxi Provincial Cancer Hospital,Nanchang 330029,China;Hepatobiliary Surgery,Jiangxi Provincial Cancer Hospital,Nanchang 330029,China)

机构地区：[1]南昌航空大学软件学院,南昌330063 [2]江西省肿瘤医院放射科,南昌330029 [3]江西省肿瘤医院肝胆外科,南昌330029

出　　处：《计算机应用研究》2022年第3期641-650,共10页Application Research of Computers

基　　金：江西省自然科学基金资助项目(20202BABL202029);国家自然科学基金资助项目(61762067)。

摘　　要：肝脏肿瘤是一种发病率高且恶化概率高的疾病,为了快速地诊断肝脏疾病,需要从计算机断层扫描(CT)中准确地分割出肝脏及肿瘤。为了分析肝脏及肿瘤图像分割领域的现状及发展趋势,针对肝脏及肿瘤图像的分割方法进行了研究,总结了近些年肝脏及肿瘤图像的分割方法。肝脏及肿瘤图像分割方法包括传统方法以及深度学习方法。传统方法需要较多的人工参与,不能实现完全自动化。深度学习方法从分割网络的维度可分为2D、2.5D以及3D方法,这些方法分割精度高,硬件需求高。在考虑深度学习与传统方法优缺点的同时,它们的结合也被不断探索,图割法和条件随机场等传统方法经常被用于细化深度学习方法的分割结果。The liver tumor is a disease with a high incidence and probability of deterioration,and the rapid diagnosis of liver disease requires accurate segmentation of liver and tumor from computed tomography(CT)scan.To analyze the status and the trend of the liver and tumor image segmentation field,this paper investigated the segmentation methods for liver and tumor images and summarized the segmentation methods for liver and tumor images in recent years.Liver and tumor image segmentation methods included conventional methods and deep learning methods.The conventional methods required more manual involvement and could not be fully automated.Deep learning methods could be divided into 2 D,2.5 D and 3 D methods from the dimension of segmentation network.These methods had high segmentation accuracy and high hardware requirements.While considering the advantages and disadvantages of deep learning and conventional methods,their combination was constantly explored,and conventional methods such as graph cuts and conditional random fields often used to refine the segmentation results of deep learning methods.

关 键 词：肝脏分割 肿瘤分割 传统方法 深度学习方法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]