Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study
Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study
复制标题
DOI：
10.1148/radiol.2017170706
复制
发表时间：
2018-03-01
期刊：
影响因子：
19.7
通讯作者：
Kiryu, Shigeru
中科院分区：
文献类型：
--
作者：
Yasaka, Koichiro;Akai, Hiroyuki;Kiryu, Shigeru
目的：通过使用深度学习方法和卷积神经网络（CNN）来研究诊断性能，以在动态造影剂增强计算机断层扫描（CT）中区分肝脏肿块。材料和方法：这项临床回顾性研究使用了三个阶段（非造影剂增强、动脉和延迟）的肝脏肿块CT图像集。根据5个类别诊断肿块（A类，典型肝细胞癌[HCC]; B类，除典型和早期HCC外的恶性肝脏肿瘤; C类，不确定肿块或肿块样病变[包括早期HCC和发育不良结节]和除血管瘤和囊肿外的罕见良性肝脏肿块; D类，血管瘤; E类，囊肿）。通过使用2013年获得的55536个图像集进行监督训练（从460名患者中获得1068个集，并将其增强52倍[从原始图像生成旋转、平行移位、强烈放大和添加噪声的图像]）。CNN由六个卷积层、三个最大池化层和三个全连接层组成。CNN使用2016年获得的100个肝脏肿块图像集进行了测试（74名男性和26名女性;平均年龄，66.4岁+/- 10.6 [标准差];平均肿块大小，26.9 mm +/- 25.9; A、B、C、D和E类分别有21、9、35、20和15个肝脏肿块）。培训和测试进行了五次。计算CNN模型对肝脏肿块分类的准确性和区分A-B类与C-E类的受试者工作特征曲线下面积。区分A-B类和C-E类的受试者工作特征曲线下面积中位数为0.92。结论：CNN深度学习在动态CT肝脏肿块鉴别诊断中具有较高的诊断性能。(C)RSNA，2017
Purpose: To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent-enhanced computed tomography (CT).Materials and Methods: This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallelshifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years +/- 10.6 [standard deviation]; mean mass size, 26.9 mm +/- 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A-B versus categories C-E were calculated.Results: Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A-B from C-E was 0.92.Conclusion: Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. (C) RSNA, 2017