基于softmax回归与图割法的脑肿瘤分割算法

doi:10.3969/j.issn.0372-2112.2017.03.021

电子学报 ›› 2017, Vol. 45 ›› Issue (3): 644-649.DOI: 10.3969/j.issn.0372-2112.2017.03.021

所属专题：机器学习与智慧医疗

基于softmax回归与图割法的脑肿瘤分割算法

葛婷^1,2, 牟宁¹, 李黎¹

1. 南京理工大学电子工程与光电技术学院, 江苏南京 210094;
2. 金陵科技学院公共基础课部, 江苏南京 211169

收稿日期:2015-09-25 修回日期:2016-02-19 出版日期:2017-03-25
- 作者简介:
- 葛婷女,1981年生于江苏南京.现为南京理工大学电子工程与光电技术学院博士研究生,金陵科技学院讲师.主要研究方向为医学图像处理与分析.E-mail:geting@jit.edu.cn;牟宁女,1981年生于江苏南京.现为南京理工大学电子工程与光电技术学院博士研究生.主要研究方向为生物医学成像.E-mail:ning.mu@gmail.com;李黎女,1981年生于安徽蚌埠,现为南京理工大学电子工程与光电技术学院博士研究生.河海大学讲师.主要研究方向为毫米波天线系统.E-mail:lili@hhu.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61275198，No.60978069）

A Brain Tumor Segmentation Method Based on Softmax Regression and Graph Cut

GE Ting^1,2, MU Ning¹, LI Li¹

1. School of Electronic and Optical Engineering, Nanjing University of Science & Technology, Nanjing, Jiangsu 210094, China;
2. Department of Mathematical, Jinling Institute of Technology, Nanjing, Jiangsu 211169, China

Received:2015-09-25 Revised:2016-02-19 Online:2017-03-25 Published:2017-03-25

摘要/Abstract

摘要：

从医学图像中分割脑肿瘤区域可以为脑肿瘤的诊断以及放射治疗提供帮助.但肿瘤区域的变化异常且边界非常模糊，因此自动或半自动地分割脑肿瘤非常困难.针对这一问题，本文结合softmax回归和图割法提出一种脑肿瘤分割算法.首先融合多序列核磁共振图像（MRI）并标记训练样本，再用softmax回归训练模型参数并计算每个点属于各个类别的概率，最后将概率融入到图割法中，用最小切/最大流方法得到最终分割结果.实验表明提出的方法可以更好地得到脑肿瘤的边界，并能较准确地分割出脑肿瘤区域.

关键词: 医学图像, 脑肿瘤, 核磁共振图像, 图像分割, softmax回归, 图割法, 最小切/最大流

Abstract:

Brain tumor segmentation from medical images is a clinical requirement for brain tumor diagnosis and radiotherapy planning.However,automatic or semi-automatic segmentation of the brain tumor is still a challenging task due to the high diversities and the ambiguous boundaries in the appearance of tumor tissue.To solve this problem,we propose a brain tumor segmentation method based on softmax regression and graph model.Firstly,the training samples are labeled from the multi-modality magnetic resonance images(MRI).Then,the softmax regression method is used to train the samples to obtain the parameters of this regression model and calculate the probabilities of each pixel belonging to different labels.At last,the probabilities calculated in the previous step are introduced to a graph-cut based model.This model is minimized with a min-cut/max-flow method to obtain the final tumor segmentation results.The experiment results demonstrate superior performance in brain tumor segmentation.

Key words: medical image, brain tumor, magnetic resonance image, image segmentation, softmax regression, graph-cut, min-cut/max-flow

中图分类号:

TP391.41

葛婷, 牟宁, 李黎. 基于softmax回归与图割法的脑肿瘤分割算法[J]. 电子学报, 2017, 45(3): 644-649.

GE Ting, MU Ning, LI Li. A Brain Tumor Segmentation Method Based on Softmax Regression and Graph Cut[J]. Acta Electronica Sinica, 2017, 45(3): 644-649.

参考文献

[1] Jose A,Ravi S,Sambath M.Brain tumor segmentation using K-means clustering and fuzzy C-means algorithms and its area calculation[J].Brain,2014,2(3):3496-3501.
[2] Dou W,Ruan S,Chen Y,et al.A framework of fuzzy information fusion for the segmentation of brain tumor tissues on MR images[J].Image and Vision Computing,2007,25(2):164-171.
[3] Gooya A,Biros G,Davatzikos C.Deformable registration of glioma images using EM algorithm and diffusion reaction modeling [J].Medical Imaging,IEEE Transactions on,2011,30(2):375-390.
[4] Conson M,Cella L,Pacelli R,et al.Automated delineation of brain structures in patients undergoing radiotherapy for primary brain tumors:From atlas to dose-volume histograms[J].Radiotherapy and Oncology,2014,112(3):326-331.
[5] Thapaliya K,Pyun J Y,Park C S,et al.Level set method with automatic selective local statistics for brain tumor segmentation in MR images[J].Computerized Medical Imaging and Graphics,2013,37(7):522-537.
[6] Rajendran A,Dhanasekaran R.Brain tumor segmentation on MRI brain images with fuzzy clustering and GVF snake model[J].International Journal of Computers Communications & Control,2014,7(3):530-539.
[7] Kanas V G,Zacharaki E I,Davatzikos C,et al.A low cost approach for brain tumor segmentation based on intensity modeling and 3D random walker[J].Biomedical Signal Processing and Control,2015,22:19-30.
[8] Boughattas N,Berar M,Hamrouni K,et al.Brain tumor segmentation from multiple MRI sequences using multiple kernel learning[A].Proceedings of IEEE International Conference on Image Processing 2014[C].Paris,France:IEEE,2014.1887-1891.
[9] Zhang N,Ruan S,Lebonvallet S,et al.Kernel feature selection to fuse multi-spectral MRI images for brain tumor segmentation[J].Computer Vision and Image Understanding,2011,115(2):256-269.
[10] Jiang J,Wu Y,Huang M,et al.3D brain tumor segmentation in multimodal MR images based on learning population-and patient-specific feature sets[J].Computerized Medical Imaging and Graphics,2013,37(7):512-521.
[11] Bishop C M,Nasrabadi N M.Pattern Recognition and Machine Learning[M].New York:Springer,2006.
[12] Boykov Y,Veksler O,Zabih R.Fast approximate energy minimization via graph cuts[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2001,23(11):1222-1239.
[13] Boykov Y,Kolmogorov V.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2004,26(9):1124-1137.
[14] Brindle K.New approaches for imaging tumour responses to treatment[J].Nature Reviews Cancer,2008,8(2):94-107.

[1]	蔡超丽, 李纯纯, 黄琳, 杨铁军. ED-NAS: 基于神经网络架构搜索的陶瓷晶粒SEM图像分割方法[J]. 电子学报, 2022, 50(2): 461-469.
[2]	张淑军, 彭中, 李辉. SAU-Net：基于U-Net和自注意力机制的医学图像分割方法[J]. 电子学报, 2022, 50(10): 2433-2442.
[3]	李居朋, 王颖慧, 李刚. 医学图像关键点检测深度学习方法研究与挑战[J]. 电子学报, 2022, 50(1): 226-237.
[4]	吴绿, 张馨月, 唐茉, 王梓, 王永安. Focus+Context语义表征的场景图像分割[J]. 电子学报, 2021, 49(3): 596-604.
[5]	周涛, 霍兵强, 陆惠玲, 任海玲. 残差神经网络及其在医学图像处理中的应用研究[J]. 电子学报, 2020, 48(7): 1436-1447.
[6]	朱占龙, 刘永军. 融合混沌优化和改进模糊聚类的图像分割算法[J]. 电子学报, 2020, 48(5): 975-984.
[7]	梁新宇, 林洗坤, 权冀川, 肖铠鸿. 基于深度学习的图像实例分割技术研究进展[J]. 电子学报, 2020, 48(12): 2476-2486.
[8]	石雪, 李玉, 赵泉华. 自适应类别的层次高斯混合模型遥感影像分割[J]. 电子学报, 2020, 48(1): 131-136.
[9]	雷涛, 张肖, 加小红, 刘侍刚, 张艳宁. 基于模糊聚类的图像分割研究进展[J]. 电子学报, 2019, 47(8): 1776-1791.
[10]	侯小刚, 赵海英, 马严. 基于超像素多特征融合的快速图像分割算法[J]. 电子学报, 2019, 47(10): 2126-2133.
[11]	范虹, 张程程, 侯存存, 朱艳春, 姚若侠. 结合双树复小波变换和改进密度峰值快速搜索聚类的乳腺MR图像分割[J]. 电子学报, 2019, 47(10): 2149-2157.
[12]	张峰, 钟宝江. 基于兴趣目标的图像检索[J]. 电子学报, 2018, 46(8): 1915-1923.
[13]	袁绍锋, 杨丰, 刘树杰, 季飞, 黄靖. 基于局部形状结构分类的心血管内超声图像中-外膜边界检测[J]. 电子学报, 2018, 46(7): 1601-1608.
[14]	李亚峰. 一种基于多字典学习的图像分割模糊方法[J]. 电子学报, 2018, 46(7): 1700-1709.
[15]	李磊, 董卓莉, 张德贤. 基于自适应区域限制FCM的图像分割方法[J]. 电子学报, 2018, 46(6): 1312-1318.

基于softmax回归与图割法的脑肿瘤分割算法

A Brain Tumor Segmentation Method Based on Softmax Regression and Graph Cut

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics