Chinese Journal of Magnetic Resonance >

2020 , Vol. 37 >Issue 3: 300 - 310

DOI: https://doi.org/10.11938/cjmr20192753

Articles

A Deep Learning Algorithm for Classifying Meningioma and Auditory Neuroma in the Cerebellopontine Angle from Magnetic Resonance Images

  • LOU Yun-zhong ,
  • LIU Ying ,
  • JIANG Hua ,
  • ZHANG Hao-wei
Expand
  • Institute of Medical Imaging Engineering, School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received date: 2019-05-28

  Online published: 2019-07-30

Fold

Abstract

Meningioma and auditory neuroma are two types of brain tumors frequently found in the cerebellopontine angle. Misdiagnosis of the two is common due to their similarity in clinical manifestations and imaging manifestations. In this work, the deep learning algorithm was developed to classify the meningioma and auditory neuroma from the magnetic resonance images, assisting the timely and accurate diagnosis to the two brain tumors. T1-weighted spin-echo (T1W-SE) images were collected from 307 patients with brain tumors. Contrast limited adaptive histogram equalization (CLAHE) pre-processing was used to improve the quality of the dataset. The image features were learnt in the deep learning framework of 3-dimensional convolutional neural network (3D CNN). By optimizing the image enhancement parameters and the network structure parameters, the accuracy of the meningioma/acoustic neuroma classification model reached 0.918 0, and the area under curve (AUC) was found to be 0.913 4.

Key words： meningioma; auditory neuroma; 3-dimensional convolutional neural network (3D CNN); magnetic resonance imaging (MRI)

Cite this article

LOU Yun-zhong , LIU Ying , JIANG Hua , ZHANG Hao-wei . A Deep Learning Algorithm for Classifying Meningioma and Auditory Neuroma in the Cerebellopontine Angle from Magnetic Resonance Images[J]. Chinese Journal of Magnetic Resonance, 2020 , 37(3) : 300 -310 . DOI: 10.11938/cjmr20192753

References

[1] CHANG D S, XU C, CUI C P. MRI diagnosis of cerebellopontine angle tumors[J]. Chinese J PMI, 2014, 15(3):190-193. 常东胜, 徐成, 崔翠萍. 桥小脑角区肿瘤的磁共振成像诊断[J]. 实用医学影像杂志, 2014, 15(3):190-193.
[2] NIU L, ZHOU X M, DUAN C F, et al. Differentiation researches on the meningioma subtypes by radiomics from contrast enhanced MRI, A preliminary study[J]. World Neurosurgery, 2019, 126:646-652.
[3] LIU Z Y, SUN Z G, ZHANG X F. MRI diagnosis and differential diagnosis of meningioma, auditory neuroma and trigeminal nerve tumors in cerebellopontine angle area[J]. Chinese J Misdiagn, 2010, 10(30):7390.刘智勇, 孙志刚, 张秀芳. 桥小脑角区脑膜瘤、听神经瘤和三叉神经瘤的MRI诊断与鉴别诊断[J]. 中国误诊学杂志, 2010, 10(30):7390.
[4] YE D Q, XU S H, HUANG Y C, et al. MRI diagnosis value of cerebellopontine angle tumor[J]. Chinese and Foreign Medical Research, 2017, 15(1):50-51.叶德湫, 许淑惠, 黄永础, 等. 桥小脑角区肿瘤的MRI诊断价值[J]. 中外医学研究, 2017, 15(1):50-51.
[5] SHEN J H, ZHANG T, FANG L J, et al. Conventional MRI, DWI characteristics and immunocytochemistry of fibrous meningioma[J]. Chinese J Medical Image, 2016, 26(12):2164-2167. 沈金花, 张涛, 方龙江, 等. 纤维型脑膜瘤的常规MRI、DWI及免疫组化分析[J]. 医学影像学杂志, 2016, 26(12):2164-2167.
[6] MENZE B H, JAKAB A, BAUER S, et al. The multimodal brain tumor image segmentation benchmark (BRATS)[J]. IEEE Trans Med Imaging, 2015, 34(10):1993-2024.
[7] MA Y, GUO H, WANG Q S, et al. Correlations between morphological characteristics and expression levels of specific molecular biomarkers in glioblastoma[J]. Chinese J Magn Reson, 2018, 35(1):22-30. 马芸, 郭虹, 王秋实, 等. 基于影像的形态学特征与胶质母细胞瘤特征分子表达的相关性研究[J]. 波谱学杂志, 2018, 35(1):22-30.
[8] 黄唯. 脑肿瘤MRI图像分类与肝病理图像分级方法研究[D]. 广州:南方医科大学, 2016.
[9] TANG X M. CT differential diagnosis of meningioma involving the internal auditory canal and acoustic neuroma[J]. Guide of China Medicine, 2014, 12(27):218-219.唐宪明. 桥小脑角区脑膜瘤累及内听道与听神经瘤的CT鉴别诊断[J]. 中国医药指南, 2014, 12(27):218-219.
[10] CHEN L, ZHANG C, TONG M L, et al. Analysis of the differential diagnosis of meningioma and auditory neuroma in the cerebellar horn area by MRI[J]. Contemporary Medicine Forum, 2016, 14(22):134-136.陈玲, 张超, 童梦玲, 等. 用MRI检查对桥小脑角区脑膜瘤和听神经瘤进行鉴别诊断的效果分析[J]. 当代医药论丛, 2016, 14(22):134-136.
[11] PING X X, MENG Q, TIAN X, et al. MRI findings of lesions in the cerebellopontine angle[J]. Chinese J Medical Image, 2014, 24(1):12-15, 20. 平小夏, 孟倩, 田霞, 等. 桥小脑角区病变的MRI表现[J]. 医学影像学杂志, 2014, 24(1):12-15, 20.
[12] ZHANG M, ZHANG H Q. Application of MRI in diagnosis of cerebellopontine angle tumor and its clinical value[J]. Medical Innovation of China, 2018, 15(34):25-29. 张敏, 张海青. MRI在桥小脑角区肿瘤患者病情诊断中的应用及其临床价值分析[J]. 中国医学创新, 2018, 15(34):25-29.
[13] SONG I, KIM H J, JEON P B. Deep learning for real-time robust facial expression recognition on a smartphone[C]. Las Vegas:2014 IEEE International Conference on Consumer Electronics (ICCE), 2014.
[14] PAYAN A, MONTANA G. Predicting Alzheimer's disease:a neuroimaging study with 3D convolutional neural networks[J]. Computer Science, 2015:arXiv:1502.02506.
[15] GUPTA A, MAIDA A S, AYHAN M S. Natural image bases to represent neuroimaging data[C]. Atlanta:Proceedings of the 30th international conference on machine learning, 2013:987-994.
[16] SOOMRO M H, DE COLA G, CONFORTO S, et al. Automatic segmentation of colorectal cancer in 3D MRI by combining deep learning and 3D level-set algorithm-a preliminary study[C]. Tunis:2018 IEEE 4th Middle East Conference on Biomedical Engineering (MECBME), 2018.
[17] LIANG C X, LI M Q, BIAN Z Y, et al. Establishment of a deep feature-based classification model for distinguishing benign and malignant[J]. J Southern Medical University, 2019, 39(1):88-92. 梁翠霞, 李明强, 边兆英, 等. 基于深度学习特征的乳腺肿瘤分类模型评估[J]. 南方医科大学学报, 2019, 39(1):88-92.
[18] LING Z G, LIANG Y, WANG Y N, et al. Adaptive extended piecewise histogram equalisation for dark image enhancement[J]. IET Image Processing, 2015, 9(11):1012-1019.
[19] KHAN R, TALHA M, KHATTAK A S, et al. Realization of balanced contrast limited adaptive histogram equalization (B-CLAHE) for adaptive dynamic range compression of real time medical images[C]. Islamabad:Proceedings of 201310th International Bhurban Conference on Applied Sciences & Technology (IBCAST), 2013.
[20] MAGUDEESWARAN V, FENSHIA SINGH J. Contrast limited fuzzy adaptive histogram equalization for enhancement of brain images[J]. Int J Imag Syst Tech, 2017, 27(1):98-103.
[21] PENG S L, JIANG H Y, WANG H X, et al. Modulation classification using convolutional neural network based deep learning model[C]. Newark:201726th Wireless and Optical Communication Conference (WOCC), 2017.
[22] CHUMERIN N. Convolutional neural network[M]//KIM P. MATLAB deep learning. Apress, Berkeley, CA. 2017:121-147.
[23] CS231n. Convolutional Neural Networks for Visual Recognition[OL]. 2019. http://cs231n.github.io/.
[24] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]. Lille:ICML'15 Proceedings of the 32nd International Conference on International Conference on Machine Learning, 2015, 37:448-456.
[25] KRIZHEVSKY A, SUTSKEVER I, HINTON G E, et al. ImageNet classification with deep convolutional neural networks[C]. Lake Tahoe:NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems, 2012, 1:1097-1105.
[26] GOLD S, RANGARAJAN A. Softmax to softassign:neural network algorithms for combinatorial optimization[J]. Journal of Artificial Neural Network, 1995, 2(4):381-399.
[27] EL-SAWY, EL-BAKRY H, LOEY M. CNN for handwritten arabic digits recognition based on LeNet-5[C]. International Conference on Advanced Intelligent Systems and Informatics AISI 2016:Proceedings of the International Conference on Advanced Intelligent Systems and Informatics, 2016:566-575.
[28] ALOM M Z, TAHA T M, YAKOPCIC C, et al. The history began from AlexNet:A comprehensive survey on deep learning approaches[J]. 2018:arXiv:1803.01164
[29] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014:arXiv:1409.1556.
[30] BALLESTER P, ARAUJO R M. On the performance of GoogLeNet and AlexNet applied to sketches[C]. Phoenix:AAAI'16 Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016:1124-1128.
[31] QIN F, YANG B, CHENG Z K. Research on measure criteria in evaluating classification performance[J]. Computer Technology and Development, 2006, 16(10):85-88.秦锋, 杨波, 程泽凯. 分类器性能评价标准研究[J]. 计算机技术与发展, 2006, 16(10):85-88.
[32] WANG H Z, ZHAO D, YANG L Q, et al. An approach for training data enrichment and batch labeling in AI+MRI aided diagnosis[J]. Chinese J Magn Reson, 2018, 35(4):50-59. 汪红志, 赵地, 杨丽琴, 等. 基于AI+MRI的影像诊断的样本增广与批量标注方法[J]. 波谱学杂志, 2018, 35(4):50-59.
Options
Outlines

/

〈 〉

Copyright © 2017 Editorial Board of Chinese Journal of Magnetic Resonance
Powered by Beijing Magtech Co. Ltd