使用卷积神经网络进行支气管内超声图像的计算机辅助诊断。

Computer-aided diagnosis of endobronchial ultrasound images using convolutional neural network.

机构信息

Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, China Medical University Hospital, Taiwan; School of Medicine, China Medical University, Taiwan; Graduate Institute of Clinical Medical Science, China Medical University, Taiwan.

Department of Computer Science and Information Engineering, National Taiwan University, Taiwan.

出版信息

Comput Methods Programs Biomed. 2019 Aug;177:175-182. doi: 10.1016/j.cmpb.2019.05.020. Epub 2019 May 22.

DOI:10.1016/j.cmpb.2019.05.020

PMID:31319946

Abstract

BACKGROUND AND OBJECTIVE

In the United States, lung cancer is the leading cause of cancer death. The survival rate could increase by early detection. In recent years, the endobronchial ultrasonography (EBUS) images have been utilized to differentiate between benign and malignant lesions and guide transbronchial needle aspiration because it is real-time, radiation-free and has better performance. However, the diagnosis depends on the subjective judgment from doctors. In some previous studies, which using the grayscale image textures of the EBUS images to classify the lung lesions but it belonged to semi-automated system which still need the experts to select a part of the lesion first. Therefore, the main purpose of this study was to achieve full automation assistance by using convolution neural network.

METHODS

First of all, the EBUS images resized to the input size of convolution neural network (CNN). And then, the training data were rotated and flipped. The parameters of the model trained with ImageNet previously were transferred to the CaffeNet used to classify the lung lesions. And then, the parameter of the CaffeNet was optimized by the EBUS training data. The features with 4096 dimension were extracted from the 7th fully connected layer and the support vector machine (SVM) was utilized to differentiate benign and malignant. This study was validated with 164 cases including 56 benign and 108 malignant.

RESULTS

According to the experiment results, applying the classification by the features from the CNN with transfer learning had better performance than the conventional method with gray level co-occurrence matrix (GLCM) features. The accuracy, sensitivity, specificity, and the area under ROC achieved 85.4% (140/164), 87.0% (94/108), 82.1% (46/56), and 0.8705, respectively.

CONCLUSIONS

From the experiment results, it has potential ability to diagnose EBUS images with CNN.

摘要

背景与目的

在美国，肺癌是癌症死亡的主要原因。通过早期发现，生存率可以提高。近年来，支气管内超声（EBUS）图像已被用于区分良性和恶性病变，并指导经支气管针吸活检，因为它是实时的、无辐射的，并且具有更好的性能。然而，诊断取决于医生的主观判断。在之前的一些研究中，使用 EBUS 图像的灰度图像纹理对肺病变进行分类，但这属于半自动系统，仍然需要专家首先选择病变的一部分。因此，本研究的主要目的是通过使用卷积神经网络实现完全自动化辅助。

方法

首先，将 EBUS 图像调整为卷积神经网络（CNN）的输入大小。然后，对训练数据进行旋转和翻转。将之前在 ImageNet 上训练的模型参数转移到用于分类肺病变的 CaffeNet。然后，使用 EBUS 训练数据优化 CaffeNet 的参数。从第 7 个全连接层提取具有 4096 维的特征，并使用支持向量机（SVM）对良性和恶性进行区分。本研究用包括 56 例良性和 108 例恶性在内的 164 例病例进行验证。