Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review

被引:241
作者
Bernal, Jose [1 ]
Kushibar, Kaisar [1 ]
Asfaw, Daniel S. [1 ]
Valverde, Sergi [1 ]
Oliver, Arnau [1 ]
Marti, Robert [1 ]
Llado, Xavier [1 ]
机构
[1] Univ Girona, Comp Vis & Robot Inst, Dept Comp Architecture & Technol, Ed P-4,Ave Lluis Santald S-N, Girona 17003, Spain
关键词
Deep convolutional neural network; Brain MRI; Segmentation; Review; SCLEROSIS LESION SEGMENTATION; INTENSITY NONUNIFORMITY; TUMOR SEGMENTATION; MRI; CLASSIFICATION; EXTRACTION; ALGORITHMS; CANCER; MATTER; TISSUE;
D O I
10.1016/j.artmed.2018.08.008
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre-processing, data-preparation and post-processing strategies available in these works. The aim of this study is three-fold. Our primary goal is to report how different CNN architectures have evolved, discuss state-of-the-art strategies, condense their results obtained using public datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in deep CNN for brain MRI analysis. Finally, we present a perspective on the future of CNNs in which we hint some of the research directions in subsequent years.
引用
收藏
页码:64 / 81
页数:18
相关论文
共 166 条
[81]  
HASEGAWA A, 1994, PROC SPIE, V2167, P654
[82]   Brain tumor segmentation with Deep Neural Networks [J].
Havaei, Mohammad ;
Davy, Axel ;
Warde-Farley, David ;
Biard, Antoine ;
Courville, Aaron ;
Bengio, Yoshua ;
Pal, Chris ;
Jodoin, Pierre-Marc ;
Larochelle, Hugo .
MEDICAL IMAGE ANALYSIS, 2017, 35 :18-31
[83]  
He KM, 2014, LECT NOTES COMPUT SC, V8691, P346, DOI [arXiv:1406.4729, 10.1007/978-3-319-10578-9_23]
[84]   A fast learning algorithm for deep belief nets [J].
Hinton, Geoffrey E. ;
Osindero, Simon ;
Teh, Yee-Whye .
NEURAL COMPUTATION, 2006, 18 (07) :1527-1554
[85]   Robust Brain Extraction Across Datasets and Comparison With Publicly Available Methods [J].
Iglesias, Juan Eugenio ;
Liu, Cheng-Yi ;
Thompson, Paul M. ;
Tu, Zhuowen .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2011, 30 (09) :1617-1634
[86]   Evaluation of automatic neonatal brain segmentation algorithms: The NeoBrainS12 challenge [J].
Isgum, Ivana ;
Benders, Manon J. N. L. ;
Avants, Brian ;
Cardoso, M. Jorge ;
Counsell, Serena J. ;
Gomez, Elda Fischi ;
Gui, Laura ;
Huppi, Petra S. ;
Kersbergen, Karina J. ;
Makropoulos, Antonios ;
Melbourne, Andrew ;
Moeskops, Pim ;
Mol, Christian P. ;
Kuklisova-Murgasova, Maria ;
Rueckert, Daniel ;
Schnabel, Julia A. ;
Srhoj-Egekher, Vedran ;
Wu, Jue ;
Wang, Siying ;
de Vries, Linda S. ;
Viergever, Max A. .
MEDICAL IMAGE ANALYSIS, 2015, 20 (01) :135-151
[87]  
Jenkinson M., 11 ANN M ORG HUM BRA
[88]  
Jin X., 2016, 30 AAAI C ART INT
[89]  
Juntu J, 2005, ADV SOFT COMP, P543
[90]   Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1026-1034