Computerized classification scheme for distinguishing between benign and malignant masses by analyzing multiple MRI sequences with convolutional neural network
Computerized classification scheme for distinguishing between benign and malignant masses by analyzing multiple MRI sequences with convolutional neural network
复制标题
通过使用卷积神经网络分析多个 MRI 序列来区分良性和恶性肿块的计算机分类方案
DOI：
10.1117/12.2564061
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ryohei Nakayama
中科院分区：
文献类型：
--
作者：
Yuichi Mima;Akiyoshi Hizukuri;Ryohei Nakayama
乳腺磁共振成像（MRI）对早期乳腺癌的敏感性高于钼靶摄影，但特异性较低。在临床MRI检查中，通常采集多个MRI序列以实现高诊断准确性。本研究的目的是开发一种计算机化的分类方案，通过卷积神经网络（CNN）集成分析多个MRI序列来区分良性和恶性肿块。我们的数据库包括43例肿块患者的4个MRI序列。包括T1加权图像、T2加权图像、动态对比剂增强磁共振成像（DCE-MRI）图像以及DCE-MRI图像的差异图像。在训练CNN时，CNN首先针对每个MRI序列进行独立训练。然后将从四个MRI序列中提取的CNN特征与训练的CNN输入到支持向量机（SVM）中，用于区分良性和恶性肿块。使用k倍交叉验证方法（k=3）来训练和测试CNN和SVM。该方法的分类准确率、敏感性、特异性、阳性预测值和阴性预测值分别为88.4%（38/43）、90.0%（27/30）、84.6%（11/13）、78.6%（11/14）和93.1%（27/29）。所提出的方法分析多个MRI序列的分类性能大大高于CNN分析一个MRI序列的分类性能。所提出的方法取得了很高的分类性能，将是有用的鉴别诊断的肿块作为诊断辅助。
Breast magnetic resonance imaging (MRI) has a higher sensitivity of early breast cancer than mammography, but the specificity is lower. In MRI examination at clinical practice, multiple MRI sequences are usually acquired to achieve high diagnostic accuracy. The purpose of this study was to develop a computerized classification scheme for distinguishing between benign and malignant masses by integrally analyzing multiple MRI sequences with convolutional neural networks (CNNs). Our database consisted of four MRI sequences for 43 patients with masses. It included T1-weighted images, T2- weighted images, dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) images, and the difference images of the DCE-MRI images for each patient. In training the CNNs, the CNNs were first trained independently for each MRI sequence. The CNN features extracted from four MRI sequences with the trained CNNs were then inputted to a support vector machine (SVM) for distinguishing between benign and malignant masses. A k-fold cross validation method (k=3) was used for training and testing the CNNs and the SVM. With the proposed method, the classification accuracy, the sensitivity, the specificity, the positive predictive value, and the negative predictive value were 88.4% (38/43), 90.0% (27/30), 84.6% (11/13), 78.6% (11/14), and 93.1% (27/29), respectively. The classification performance with the proposed method analyzing multiple MRI sequences was substantially greater than those with CNNs analyzing one MRI sequence. The proposed method achieved high classification performance and would be useful in differential diagnoses of masses as diagnostic aid.