A Novel MRI Diagnosis Method for Brain Tumor Classification Based on CNN and Bayesian Optimization.
A Novel MRI Diagnosis Method for Brain Tumor Classification Based on CNN and Bayesian Optimization.
复制标题
DOI：
10.3390/healthcare10030494
复制
发表时间：
2022-03-08
期刊：
影响因子：
--
通讯作者：
Mouhafid M
中科院分区：
文献类型：
--
作者：
Ait Amou M;Xia K;Kamhi S;Mouhafid M
脑肿瘤是当今最具侵略性的疾病之一，如果在晚期被诊断出来，会导致非常短的寿命。因此，治疗计划阶段对于提高患者的生活质量至关重要。磁共振成像（MRI）在脑肿瘤诊断中的应用非常广泛，但人工解读大量图像需要相当大的努力，并且容易出现人为错误。因此，需要一种自动化的方法来识别最常见的脑肿瘤。卷积神经网络（CNN）架构在图像分类中是成功的，因为它们的层数很高，这使它们能够自己有效地构思特征。CNN超参数的调整在每个数据集中都是至关重要的，因为它对训练模型的效率有重大影响。考虑到数据的高维性和复杂性，手动调整超参数将花费过多的时间，并且可能无法识别最佳超参数。在本文中，我们提出了一种基于贝叶斯优化的CNN高效超参数优化技术。通过将3064个T1加权CE-MRI图像分类为三种类型的脑肿瘤（胶质瘤、脑膜瘤和脑胶质瘤）来评估该方法。基于迁移学习，将五个公认的深度预训练模型的性能与优化的CNN的性能进行了比较。在使用贝叶斯优化后，我们的CNN在没有数据增强或裁剪病变技术的情况下最多能够达到98.70%的验证准确率，而VGG 16，VGG 19，ResNet 50，InceptionV 3和DenseNet 201分别达到97.08%，96.43%，89.29%，92.86%和94.81%的验证准确率。此外，该模型在CE-MRI数据集上的性能优于最先进的方法，证明了自动化超参数优化的可行性。
Brain tumor is one of the most aggressive diseases nowadays, resulting in a very short life span if it is diagnosed at an advanced stage. The treatment planning phase is thus essential for enhancing the quality of life for patients. The use of Magnetic Resonance Imaging (MRI) in the diagnosis of brain tumors is extremely widespread, but the manual interpretation of large amounts of images requires considerable effort and is prone to human errors. Hence, an automated method is necessary to identify the most common brain tumors. Convolutional Neural Network (CNN) architectures are successful in image classification due to their high layer count, which enables them to conceive the features effectively on their own. The tuning of CNN hyperparameters is critical in every dataset since it has a significant impact on the efficiency of the training model. Given the high dimensionality and complexity of the data, manual hyperparameter tuning would take an inordinate amount of time, with the possibility of failing to identify the optimal hyperparameters. In this paper, we proposed a Bayesian Optimization-based efficient hyperparameter optimization technique for CNN. This method was evaluated by classifying 3064 T-1-weighted CE-MRI images into three types of brain tumors (Glioma, Meningioma, and Pituitary). Based on Transfer Learning, the performance of five well-recognized deep pre-trained models is compared with that of the optimized CNN. After using Bayesian Optimization, our CNN was able to attain 98.70% validation accuracy at best without data augmentation or cropping lesion techniques, while VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved 97.08%, 96.43%, 89.29%, 92.86%, and 94.81% validation accuracy, respectively. Moreover, the proposed model outperforms state-of-the-art methods on the CE-MRI dataset, demonstrating the feasibility of automating hyperparameter optimization.
登录
查看更多内容
影响因子：
8.7
作者：
Budak, Umit;Comert, Zafer;Cibuk, Musa
通讯作者：
Cibuk, Musa
影响因子：
5.6
作者：
Jain, Rachna;Nagrath, Preeti;Hemanth, D. Jude
通讯作者：
Hemanth, D. Jude
影响因子：
7.8
作者：
Ciresan, Dan;Meier, Ueli;Schmidhuber, Juergen
通讯作者：
Schmidhuber, Juergen
影响因子：
2.7
作者：
Khawaldeh, Saed;Pervaiz, Usama;Alkhawaldeh, Rami S.
通讯作者：
Alkhawaldeh, Rami S.
DOI：
10.1109/jbhi.2013.2263533
发表时间：
2013-11-01
影响因子：
7.7
作者：
Coatrieux, Gouenou;Huang, Hui;Roux, Christian
通讯作者：
Roux, Christian