Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks
Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks
复制标题
DOI：
10.3390/app8010027
复制
发表时间：
2018-01-01
影响因子：
2.7
通讯作者：
Alkhawaldeh, Rami S.
中科院分区：
文献类型：
--
作者：
Khawaldeh, Saed;Pervaiz, Usama;Alkhawaldeh, Rami S.
近年来，卷积神经网络（ConvNets）作为一种广泛的机器学习技术迅速出现在许多应用中，特别是在医学图像分类和分割领域。在本文中，我们提出了一种新的方法，使用ConvNet将大脑医学图像分类为健康和不健康的大脑图像。脑肿瘤的不健康图像也分为低等级和高等级。特别是，我们在磁共振图像上使用Alex Krizhevsky网络（AlexNet）深度学习架构的修改版本作为潜在的肿瘤分类技术。对整个图像执行分类，其中训练集中的标签处于图像级别而不是像素级别。实验结果表明，该方法对脑医学图像的特征提取具有较好的效果，准确率为91.16%。
In recent years, Convolutional Neural Networks (ConvNets) have rapidly emerged as a widespread machine learning technique in a number of applications especially in the area of medical image classification and segmentation. In this paper, we propose a novel approach that uses ConvNet for classifying brain medical images into healthy and unhealthy brain images. The unhealthy images of brain tumors are categorized also into low grades and high grades. In particular, we use the modified version of the Alex Krizhevsky network (AlexNet) deep learning architecture on magnetic resonance images as a potential tumor classification technique. The classification is performed on the whole image where the labels in the training set are at the image level rather than the pixel level. The results showed a reasonable performance in characterizing the brain medical images with an accuracy of 91.16%.