3D multimodal MRI brain glioma tumor and edema segmentation: A graph cut distribution matching approach

被引:47
|
作者
Njeh, Ines [1 ]
Sallemi, Lamia [1 ]
Ben Ayed, Ismail [4 ]
Chtourou, Khalil [1 ,5 ]
Lehericy, Stephane [2 ,3 ]
Galanaud, Damien [2 ,3 ]
Ben Hamid, Ahmed [1 ]
机构
[1] Sfax Univ, ENIS, Adv Technol Med & Signals, Sfax, Tunisia
[2] Hop La Pitie Salpetriere, CENIRICM, Neuroimaging Res Ctr, Paris, France
[3] Pitie Salpetriere, Dept Neuroradiol, Paris, France
[4] GE Healthcare, London, ON, Canada
[5] CHU Habib Bourguiba, Dept Nucl Med, Sfax, Tunisia
关键词
Graph cut distribution matching; Segmentation; MRI; Brain tumor; Edema; BraTS2012;
D O I
10.1016/j.compmedimag.2014.10.009
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
This study investigates a fast distribution-matching, data-driven algorithm for 3D multimodal MRI brain glioma tumor and edema segmentation in different modalities. We learn non-parametric model distributions which characterize the normal regions in the current data. Then, we state our segmentation problems as the optimization of several cost functions of the same form, each containing two terms: (i) a distribution matching prior, which evaluates a global similarity between distributions, and (ii) a smoothness prior to avoid the occurrence of small, isolated regions in the solution. Obtained following recent bound-relaxation results, the optima of the cost functions yield the complement of the tumor region or edema region in nearly real-time. Based on global rather than pixel wise information, the proposed algorithm does not require an external learning from a large, manually-segmented training set, as is the case of the existing methods. Therefore, the ensuing results are independent of the choice of a training set. Quantitative evaluations over the publicly available training and testing data set from the MICCAI multimodal brain tumor segmentation challenge (BraTS 2012) demonstrated that our algorithm yields a highly competitive performance for complete edema and tumor segmentation, among nine existing competing methods, with an interesting computing execution time (less than 0.5 s per image). (C) 2014 Elsevier Ltd. All rights reserved.
引用
收藏
页码:108 / 119
页数:12
相关论文
共 50 条
  • [31] SAM-Guided Graph Cut for 3D Instance Segmentation
    Guo, Haoyu
    Zhu, He
    Peng, Sida
    Wang, Yuang
    Shen, Yujun
    Hu, Ruizhen
    Zhou, Xiaowei
    COMPUTER VISION - ECCV 2024, PT XLVIII, 2025, 15106 : 234 - 251
  • [32] Graph cut based multiple view segmentation for 3D reconstruction
    Sormann, Mario
    Zach, Christopher
    Kamer, Konrad
    THIRD INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, 2007, : 1085 - 1092
  • [33] Multiscale Graph-Cut for 3D Segmentation of Compact Objects
    Jirik, Miroslav
    Lukes, Vladimir
    Zelezny, Milos
    Liska, Vaclav
    COMBINATORIAL IMAGE ANALYSIS, IWCIA 2018, 2018, 11255 : 227 - 236
  • [34] Region-related focal loss for 3D brain tumor MRI segmentation
    Li, Bo
    You, Xinge
    Peng, Qinmu
    Wang, Jing
    Yang, Chuanwu
    MEDICAL PHYSICS, 2023, 50 (07) : 4325 - 4339
  • [35] 3D VISUALIZATION AND SEGMENTATION OF BRAIN MRI DATA
    Levinski, Konstantin
    Sourin, Alexei
    Zagorodnov, Vitali
    GRAPP 2009: PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON COMPUTER GRAPHICS THEORY AND APPLICATIONS, 2009, : 111 - +
  • [36] Recurrent Multi-Fiber Network for 3D MRI Brain Tumor Segmentation
    Zhao, Yue
    Ren, Xiaoqiang
    Hou, Kun
    Li, Wentao
    SYMMETRY-BASEL, 2021, 13 (02): : 1 - 12
  • [37] Fast and accurate semiautomatic haptic segmentation of brain tumor in 3D MRI images
    Latifi-Navid, Masoud
    Bilen, Murat
    Konukseven, Erhan Ilhan
    Dogan, Mustafa
    Altun, Adnan
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2016, 24 (03) : 1397 - U4358
  • [38] 3D brain tumor segmentation in MRI images based on a modified PSO technique
    Gtifa, Wafa
    Hamdaoui, Faycal
    Sakly, Anis
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2019, 29 (04) : 501 - 509
  • [39] dResU-Net: 3D deep residual U-Net based brain tumor segmentation from multimodal MRI
    Raza, Rehan
    Bajwa, Usama Ijaz
    Mehmood, Yasar
    Anwar, Muhammad Waqas
    Jamal, M. Hassan
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 79
  • [40] A Discriminative Model-Constrained Graph Cuts Approach to Fully Automated Pediatric Brain Tumor Segmentation in 3-D MRI
    Wels, Michael
    Carneiro, Gustavo
    Aplas, Alexander
    Huber, Martin
    Hornegger, Joachim
    Comanicin, Dorin
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2008, PT I, PROCEEDINGS, 2008, 5241 : 67 - +