首页 > 论文 > 激光与光电子学进展 > 55卷 > 11期(pp:111011--1)

改进的连续型最大流算法脑肿瘤磁核共振成像三维分割

Three-Dimensional Segmentation of Brain Tumors in Magnetic Resonance Imaging Based on Improved Continuous Max-Flow

任璐   李锵   关欣   马杰  
  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对脑肿瘤磁核共振成像(MRI)中噪声、低对比度、脑肿瘤边界模糊等原因造成脑肿瘤分割不足的问题,提出一种改进的连续型最大流算法脑肿瘤MRI三维分割方法。针对Flair、T1C和T2三种模态MRI图像使用中值滤波和快速模糊C均值聚类进行预处理得到预处理图像;按照大量实验统计确定的融合比例5∶1∶4(Flair、T1C和T2三种模态),对各预处理图像进行线性融合得到三维融合图像;采用快速模糊C均值算法对三维融合图像进行聚类得到三维欠分割图像;使用本文提出的算法对三维欠分割图像进行精准分割,即通过分析三维欠分割图像的结构特征和统计特征,提取参数实现改进的连续型最大流算法,去除散点后得到最终分割结果。实验表明,相对金标准的相似系数为0.90,正确率为0.94,召回率为0.86。使用本文提出算法进行脑肿瘤MRI三维分割能够自动、准确地分割出三维脑肿瘤区域,可以满足医学临床需要。

Abstract

In order to solve the problem of insufficient segmentation of brain tumors in magnetic resonance imaging (MRI) caused by noise, poor contrast, and diffused boundaries of tumors, a three-dimensional (3D) segmentation algorithm for brain tumor MRI images based on the improved continuous max-flow is proposed in this paper. Firstly, three types of MIR images, Flair, T1C and T2, are pre-processed with median filtering and fast fuzzy C means clustering. Then, the pre-processed images are linearly fused in the ratio of 5∶1∶4 (Flair, T1C, and T2) which is statistically observed from a large amount of experiments. Next, the 3D fused image is clustered by the fast fuzzy C-means algorithm to obtain the 3D under-segmented image. Finally, the proposed improved continuous max-flow algorithm acts on the 3D under-segmented image to obtain the final segmentation result with scattering points removed according to the analysis of the structural features and statistical characteristics of the 3D under-segmented image. The experimental results show that the average Dice coefficient, precision, and recall of the proposed method relative to the gold standard is up to 0.90, 0.94, and 0.86, respectively. The proposed algorithm can realize the 3D segmentation of the target regions precisely and automatically to meet the clinical medicine requirement.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.111011

所属栏目:图像处理

基金项目:国家自然科学基金(61471263)、天津市自然科学基金(16JCZDJC31100)

收稿日期:2018-05-04

修改稿日期:2018-06-06

网络出版日期:2018-06-08

作者单位    点击查看

任璐:天津大学微电子学院, 天津 300072
李锵:天津大学微电子学院, 天津 300072
关欣:天津大学微电子学院, 天津 300072
马杰:天津微深科技有限公司, 天津 300384

联系人作者:李锵(liqiang@tju.edu.cn)

【1】Siegel R, Naishadham D, Jemal A. Cancer statistics, 2013[J]. CA: A Cancer Journal for Clinicians, 2013, 63(1): 11-30.

【2】Erdt M, Steger S, Sakas G. Regmentation: a new view of image segmentation and registration[J]. Journal of Radiation Oncology Informatics, 2012, 4(1): 1-23.

【3】Mo S W, Deng X P, Wang S, et al. Moving object detection algorithm based on improved visual background extractor[J]. Acta Optica Sinica, 2016, 36(6): 0615001.
莫邵文, 邓新蒲, 王帅, 等. 基于改进视觉背景提取的运动目标检测算法[J]. 光学学报, 2016, 36(6): 0615001.

【4】Akter M K, Khan S M, Azad S, et al. Automated brain tumor segmentation from MRI data based on exploration of histogram characteristics of the cancerous hemisphere[C]∥IEEE Region 10 Humanitarian Technology Conference, IEEE, 2017: 815-818.

【5】Cabral J E, White K S, Kim Y, et al. Interactive segmentation of brain tumors in MR images using 3D region growing[C]∥Medical Imaging 1993: Image Processing, International Society for Optics and Photonics, 1993: 171-181.

【6】Li R Z, Liu Y Y, Yang M, et al. Three-dimensional point cloud segmentation algorithm based on improved region growing[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051502.
李仁忠, 刘阳阳, 杨曼, 等. 基于改进的区域生长三维点云分割[J]. 激光与光电子学进展, 2018, 55(5): 051502.

【7】Vrji K S A, Jayakumari J. Automatic detection of brain tumor based on magnetic resonance image using CAD system with watershed segmentation[C]∥International Conference on Signal Processing, Communication, Computing and Networking Technologies, IEEE, 2011: 145-150.

【8】Luo M, Huang J, Yang F, et al. 3D brain tumour segmentation based on adaptive weighted combined-kernel function[J]. Computer Applications and Software, 2015, 32(9): 210-213.
罗蔓, 黄靖, 杨丰, 等. 基于自适应加权混合核函数的3D脑肿瘤分割[J]. 计算机应用与软件, 2015, 32(9): 210-213.

【9】Zhao X, Wu Y, Song G, et al. 3D brain tumor segmentation through integrating multiple 2D FCNNs[C]∥International MICCAI Brainlesion Workshop, Springer, 2017: 191-203.

【10】Pereira S, Pinto A, Alves V, et al. Brain tumor segmentation using convolutional neural networks in MRI images[J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1240-1251.

【11】Tong Y F, Li Q, Guan X. An improved multi-modal brain tumor segmentation hybrid algorithm[J]. Journal of Signal Processing, 2018, 34(3): 340-346.
童云飞, 李锵, 关欣. 改进的多模式脑肿瘤图像混合分割算法[J]. 信号处理, 2018, 34(3): 340-346.

【12】Xie Z N, Zheng D, Chen J Y, et al. A tumor segmentation method of improved Chan-Vese model for liver cancer ablation computed tomography image[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021702.
谢志南, 郑东, 陈嘉耀, 等. 改进Chan-Vese模型的肝癌消融CT图像肿块分割方法[J]. 激光与光电子学进展, 2017, 54(2): 021702.

【13】Chen Z B, Qiu T S, Su R. FCM and level set based segmentation method for brain MR images[J]. Acta Electronica Sinica, 2008, 36(9): 1733-1736.
陈志彬, 邱天爽, Su R.一种基于FCM和Level Set的MRI医学图像分割方法[J]. 电子学报, 2008, 36(9): 1733-1736.

【14】Abdel-Maksoud E, Elmogy M, Al-Awadi R. Brain tumor segmentation based on a hybrid clustering technique[J]. Egyptian Informatics Journal, 2015, 16(1): 71-81.

【15】Adhikari S K, Sing J K, Basu D K, et al. Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images[J]. Applied Soft Computing, 2015, 34: 758-769.

【16】Wang M, Song Z F, Wang Z H. Remote sensing image segmentation based on fractal net evolution approach and improved fuzzy C-means[J]. Laser & Optoelectronics Progress, 2016, 53(11): 112801.
王民, 宋正付, 王稚慧. 基于分形网络演化方法和改进模糊聚类遥感影像分割[J]. 激光与光电子学进展, 2016, 53(11): 112801.

【17】Tian J, Huang Y, Tian J. Histogram constraint based fast FCM cluster image segmentation[C]∥IEEE International Symposium on Industrial Electronics, IEEE, 2007: 1623-1627.

【18】Strang G. Maximal flow through adomain[J]. Mathematical Programming, 1983, 26(2): 123-143.

【19】Appleton B, Talbot H. Globally minimal surfaces by continuous maximal flows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(1): 106-118.

【20】Yuan J, Bae E, Tai X C. A study on continuous max-flow and min-cut approaches[C]∥Computer Vision and Pattern Recognition, IEEE, 2010: 2217-2224.

【21】Havaei M, Davy A, Warde-Farley D, et al. Brain tumor segmentation with deep neural networks[J]. Medical Image Analysis, 2017, 35: 18-31.

引用该论文

Ren Lu,Li Qiang,Guan Xin,Ma Jie. Three-Dimensional Segmentation of Brain Tumors in Magnetic Resonance Imaging Based on Improved Continuous Max-Flow[J]. Laser & Optoelectronics Progress, 2018, 55(11): 111011

任璐,李锵,关欣,马杰. 改进的连续型最大流算法脑肿瘤磁核共振成像三维分割[J]. 激光与光电子学进展, 2018, 55(11): 111011

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF