Deep convolutional neural network for reduction of contrast-enhanced region on CT images
Deep convolutional neural network for reduction of contrast-enhanced region on CT images
复制标题
DOI：
10.1093/jrr/rrz030
复制
发表时间：
2019-09-01
影响因子：
2
通讯作者：
Ogawa, Kazuhiko
中科院分区：
文献类型：
--
作者：
Sumida, Iori;Magome, Taiki;Ogawa, Kazuhiko
本研究旨在使用深度卷积神经网络(CNN)生成非对比CT图像以进行成像。入选患者29例。CT图像是在没有和有对比增强介质的情况下获得的。将横断面图像划分为×像素。这导致非对比度和对比度增强的CT图像对总共有14 723个斑块。所提出的CNN模型包括五个具有一条捷径的二维(2D)卷积层。为了进行比较，使用了U-Net模型，该模型包括五个交错的2D卷积层以及合并和非合并的层。对24名患者进行了训练，另有5名患者用于测试训练后的模型。为了定量评估，在测试数据的参考对比增强图像上选择了50个感兴趣区域(ROI)，并计算了ROI的平均像素值。计算参考非对比度图像和预测非对比度图像上同一位置的感兴趣区的平均像素值，并将其进行比较。在定量分析方面，两种模型的参考对比增强图像和预测的非对比图像之间的平均像素值差异显著(P<；0.0001)。使用U-Net模型发现像素有显著差异(P<；0.0001)；相反，当比较参考非对比度图像和预测非对比度图像时，使用所提出的CNN模型没有显著差异。使用所提出的CNN模型，对比增强区域被满意地减少。
This study aims to produce non-contrast computed tomography (CT) images using a deep convolutional neural network (CNN) for imaging. Twenty-nine patients were selected. CT images were acquired without and with a contrast enhancement medium. The transverse images were divided into 64 x 64 pixels. This resulted in 14 723 patches in total for both non-contrast and contrast-enhanced CT image pairs. The proposed CNN model comprises five two-dimensional (2D) convolution layers with one shortcut path. For comparison, the U-net model, which comprises five 2D convolution layers interleaved with pooling and unpooling layers, was used. Training was performed in 24 patients and, for testing of trained models, another 5 patients were used. For quantitative evaluation, 50 regions of interest (ROIs) were selected on the reference contrast-enhanced image of the test data, and the mean pixel value of the ROIs was calculated. The mean pixel values of the ROIs at the same location on the reference non-contrast image and the predicted non-contrast image were calculated and those values were compared. Regarding the quantitative analysis, the difference in mean pixel value between the reference contrast-enhanced image and the predicted non-contrast image was significant (P < 0.0001) for both models. Significant differences in pixels (P < 0.0001) were found using the U-net model; in contrast, there was no significant difference using the proposed CNN model when comparing the reference non-contrast images and the predicted non-contrast images. Using the proposed CNN model, the contrast-enhanced region was satisfactorily reduced.