A Deep Learning-Based Approach for the Detection and Localization of Prostate Cancer in T2 Magnetic Resonance Images

被引:81
作者
Alkadi, Ruba [1 ]
Taher, Fatma [1 ]
El-baz, Ayman [2 ]
Werghi, Naoufel [1 ]
机构
[1] Khalifa Univ Sci & Technol, POB 127788, Abu Dhabi, U Arab Emirates
[2] Univ Louisville, Louisville, KY 40292 USA
关键词
Magnetic resonance imaging; Prostate cancer; Deep convolutional encoder-decoder; COMPUTER-AIDED DETECTION; MRI; SPECTROSCOPY; SMOTE;
D O I
10.1007/s10278-018-0160-1
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
We address the problem of prostate lesion detection, localization, and segmentation in T2W magnetic resonance (MR) images. We train a deep convolutional encoder-decoder architecture to simultaneously segment the prostate, its anatomical structure, and the malignant lesions. To incorporate the 3D contextual spatial information provided by the MRI series, we propose a novel 3D sliding window approach, which preserves the 2D domain complexity while exploiting 3D information. Experiments on data from 19 patients provided for the public by the Initiative for Collaborative Computer Vision Benchmarking (I2CVB) show that our approach outperforms traditional pattern recognition and machine learning approaches by a significant margin. Particularly, for the task of cancer detection and localization, the system achieves an average AUC of 0.995, an accuracy of 0.894, and a recall of 0.928. The proposed mono-modal deep learning-based system performs comparably to other multi-modal MR-based systems. It could improve the performance of a radiologist in prostate cancer diagnosis and treatment planning.
引用
收藏
页码:793 / 807
页数:15
相关论文
共 51 条
[1]  
Alkadi R, PROSTATE CANC IMAGIN
[2]  
[Anonymous], 2018, ARXIV180208717
[3]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[4]   Detection of prostate cancer by integration of line-scan diffusion, T2-mapping and T2-weighted magnetic resonance imaging; a multichannel statistical classifier [J].
Chan, I ;
Wells, W ;
Mulkern, RV ;
Haker, S ;
Zhang, JQ ;
Zou, KH ;
Maier, SE ;
Tempany, CMC .
MEDICAL PHYSICS, 2003, 30 (09) :2390-2398
[5]   SMOTE: Synthetic minority over-sampling technique [J].
Chawla, Nitesh V. ;
Bowyer, Kevin W. ;
Hall, Lawrence O. ;
Kegelmeyer, W. Philip .
2002, American Association for Artificial Intelligence (16)
[6]   What is a good evaluation measure for semantic segmentation? [J].
Csurka, Gabriela ;
Larlus, Diane ;
Perronnin, Florent .
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2013, 2013,
[7]   Learning normalized inputs for iterative estimation in medical image segmentation [J].
Drozdzal, Michal ;
Chartrand, Gabriel ;
Vorontsov, Eugene ;
Shakeri, Mahsa ;
Di Jorio, Lisa ;
Tang, An ;
Romero, Adriana ;
Bengio, Yoshua ;
Pal, Chris ;
Kadoury, Samuel .
MEDICAL IMAGE ANALYSIS, 2018, 44 :1-13
[8]   Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture [J].
Eigen, David ;
Fergus, Rob .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :2650-2658
[9]   Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012 [J].
Ferlay, Jacques ;
Soerjomataram, Isabelle ;
Dikshit, Rajesh ;
Eser, Sultan ;
Mathers, Colin ;
Rebelo, Marise ;
Parkin, Donald Maxwell ;
Forman, David ;
Bray, Freddie .
INTERNATIONAL JOURNAL OF CANCER, 2015, 136 (05) :E359-E386
[10]   Multiparametric MRI in the Detection of Clinically Significant Prostate Cancer [J].
Futterer, Jurgen J. .
KOREAN JOURNAL OF RADIOLOGY, 2017, 18 (04) :597-606