基于3D CNN的脑胶质瘤分类算法

赵尚义; 王远军

光学技术, 2019, 45 (6): 749, 网络出版: 2020-01-08

基于3D CNN的脑胶质瘤分类算法

Brain glioma classification algorithm based on 3D CNN

论文大纲

赵尚义 ^*王远军

作者单位

上海理工大学医疗器械与食品学院, 上海 200093

脑胶质瘤分类特征提取磁共振成像 glioma classification 3D CNN 3D CNN feature extraction magnetic resonance imaging

摘要

基于目前脑胶质瘤在低分级胶质瘤和高分级胶质瘤上分类不准确的问题, 提出了基于3D CNN特征提取的磁共振成像脑胶质瘤分类方法。在3D CNN模型中加入Batch Normalizing层和Dropout层, 降低了过度拟合并加速了网络收敛速度; 使用N4ITK和数据增强后的数据进行训练, 进一步降低了过度拟合, 提升了模型分类效果; 构建特征融合层, 实现自动分类。实验结果表明, 算法在BraTS 2018数据集中的分类效果具有明显优势, 分类准确率高达91.67%, 明显高于AlexNet、VGG和ResNet三大主流网络模型, 算法具有较好的鲁棒性和泛化性, 对脑胶质瘤的分类和诊断具有临床应用潜力。

Abstract

Based on the inaccurate classification of gliomas in low-grade gliomas and high-grade gliomas at present, this thesis proposed the classification of gliomas by Magnetic Resonance Imaging in the basis of 3D CNN. Firstly, the Batch Normalizing layer and the Dropout layer are added to the 3D CNN model, which reduces the over-fitting and accelerates the convergence speed of the network. Then, the model has trained with N4ITK and the data that were augmented, which further reduces the over-fitting and improves the effect of model classification. Finally, the feature fusion layer is constructed to realize automatic classification. The experiment results show that the algorithm has obvious advantages in the classification of BraTS 2018 dataset, and the classification accuracy is as high as 91.67 percent, which is significantly higher than the three mainstream network models-AlexNet, VGG and ResNet. The algorithm has better robustness and generalization as well as has the clinical potential of the classification and diagnosis of glioma.

参考文献

[1] Sridhar D, Krishna I V M. Brain tumor classification using discrete cosine transform and probabilistic neural network［C］∥ International Conference on Signal Processing Image Processing & Pattern Recognition.Andhrapradesh,India:IEEE,2013:92-96.

[2] Wen P Y, Kesari S. Malignant gliomas in adults［J］. New England Journal of Medicine,2008,359(5):492-507.

[3] Bauer S, Wiest R, Nolte L P, et al. A survey of MRI-based medical image analysis for brain tumor studies［J］. Physics in Medicine & Biology,2013,58(13):R97.

[4] Stylli S S, Luwor R B, Ware T M B, et al. Mouse models of glioma［J］. Journal of Clinical Neuroscience,2015,22(4):619-626.

[5] Arevalo-Perez J, Peck K K, Young R J, et al. Dynamic contrast-enhanced perfusion MRI and diffusion-weighted imaging in grading of gliomas［J］. Journal of Neuroimaging,2015,25(5):792-798.

[6] Menze B H, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS) ［J］. IEEE Transactions on Medical Imaging,2015,34(10):1993-2024.

[7] Bakas S, Akbari H, Sotiras A, et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features［J］. Nature Scientific Data,2017,4(1):170117.

[8] 刘利雄, 马忠梅, 赵恒博, 等. 一种基于主动轮廓模型的心脏核磁共振图像分割方法［J］. 计算机学报,2012,35(1):146-153.

Liu Lixiong, Ma Zhongmei, Zhao Hengbo, et al. A method for segmenting cardiac magnetic resonance images using active contours［J］. Chinese Journal Of Computers,2012,35(1):146-153.

[9] Zacharaki E I, Wang S, Chawla S, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme［J］. Magnetic Resonance in Medicine,2010,62(6):1609-1618.

[10] Zulpe N S, Pawar V P. GLCM textural features for Brain Tumor Classification［J］. International Journal of Computer Science Issues,2012,9(3):354.

[11] Khawaldeh S, Pervaiz U, Rafiq A, et al. Noninvasive grading of glioma tumor using magnetic resonance imaging with convolutional neural networks［J］. Applied Sciences,2017,8(1):27.

[12] Hazlett H C, Gu H, Munsell B C, et al. Early brain development in infants at high risk for autism spectrum disorder［J］. Nature,2017,542(7641):348-351.

[13] Esteva A, Kuprel B, Novoa R A, et al. Dermatologist-level classification of skin cancer with deep neural networks［J］. Nature,2017,542(7639):115.

[14] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks［J］. Science,2006,313(5786):504-507.

[15] Ji S, Xu W, Yang M, et al. 3D convolutional neural networks for human action recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):221-231.

[16] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation［J］. Medical Image Computing and Computer-Assisted Intervention,2015,1(1):234-241.

[17] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift［C］∥ International Conference on International Conference on Machine Learning. Lille,France:IEEE,2015:448-456.

[18] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting［J］. Journal of Machine Learning Research,2014,15(1):1929-1958.

[19] Tustison N J, Avants B B, Cook P A, et al. N4ITK: improved N3 bias correction［J］. IEEE Transactions on Medical Imaging,2010,29(6):1310.

[20] Masko D, Hensman P. The impact of imbalanced training data for convolutional neural networks［J］. Degree Project in Computer Science, KTH Royal Institute of Technology,2015,1(10):82-110.

[21] Bloice M D, Stocker C, Holzinger A. Augmentor: an image augmentation library for machine learning［J］. Journal of Open Source Software,2017,2(19):1708-1713.

[22] Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks［J］. Advances in Neural Information Processing Systems,2012,25(2):1097-1105.

[23] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition［C］∥ International Conference on Learning Representations. Banff,Canada:IEEE,2014:1409-1416.

[24] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition［C］∥ Conference on Computer Vision & Pattern Recognition. Las Vegas,USA:IEEE,2016:770-778.

[25] Cho H, Lee S, Kim J, et al. Classification of the glioma grading using radiomics analysis［J］. PeerJ,2018,6(1):e5982.

[26] Saito T, Rehmsmeier M. Precrec: fast and accurate precision-recall and ROC curve calculations in R［J］. Bioinformatics,2017,33(1):145-147.

赵尚义, 王远军. 基于3D CNN的脑胶质瘤分类算法[J]. 光学技术, 2019, 45(6): 749. ZHAO Shangyi, WANG Yuanjun. Brain glioma classification algorithm based on 3D CNN[J]. Optical Technique, 2019, 45(6): 749.

基于3D CNN的脑胶质瘤分类算法

关于本站 Cookie 的使用提示

全站搜索

基于3D CNN的脑胶质瘤分类算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索