MID-UNet: Multi-input directional UNet for COVID-19 lung infection segmentation from CT images.
MID-UNet: Multi-input directional UNet for COVID-19 lung infection segmentation from CT images.
复制标题
MID-UNet：用于 CT 图像中的 COVID-19 肺部感染分割的多输入定向 UNet
DOI：
10.1016/j.image.2022.116835
复制
发表时间：
2022-10
影响因子：
3.5
通讯作者：
Yu, Xiaosheng
中科院分区：
文献类型：
--
作者：
Chi, Jianning;Zhang, Shuang;Han, Xiaoying;Wang, Huan;Wu, Chengdong;Yu, Xiaosheng
自2019年12月报告首例病例以来，2019冠状病毒病（COVID-19）已在全球蔓延，成为全球性的生存健康危机，确诊病例总数超过9000万例。通过深度学习方法从计算机断层扫描（CT）扫描中分割肺部感染在辅助COVID-19的诊断和医疗保健方面具有巨大的潜力。然而，目前用于从肺部CT图像分割感染区域的深度学习方法存在三个问题：（1）COVID-19感染区域、其他肺炎区域和正常肺组织之间的语义特征区分度低;（2）不同COVID-19病例或阶段之间的视觉特征变化大;（3）不同的COVID-19病例或阶段之间的视觉特征差异大。（3）限制COVID-19感染区域的不规则边界的难度高。为了解决这些问题，提出了一种多输入方向UNet（MID-UNet）来分割肺部CT图像中的COVID-19感染。对于网络的输入部分，我们首先提出了一个图像模糊描述符来反映感染的纹理特征。然后将原始CT图像、自适应直方图均衡化增强后的图像、非局部均值滤波后的图像和模糊特征图作为网络的输入。对于网络结构，我们提出了由4个方向卷积核组成的方向卷积块（DCB）。DCB应用于快捷连接，以在将提取的特征传输到去卷积部分之前对其进行细化。此外，我们提出了一种基于局部曲率直方图的轮廓损失，然后将其与二进制交叉熵（BCE）损失和交集（IOU）损失相结合，以更好地分割边界约束。在COVID-19-CT-Seg数据集上的实验结果表明，我们提出的MID-UNet在从CT图像中分割COVID-19感染方面提供了优于现有技术的上级性能。
Coronavirus Disease 2019 (COVID-19) has spread globally since the first case was reported in December 2019, becoming a world-wide existential health crisis with over 90 million total confirmed cases. Segmentation of lung infection from computed tomography (CT) scans via deep learning method has a great potential in assisting the diagnosis and healthcare for COVID-19. However, current deep learning methods for segmenting infection regions from lung CT images suffer from three problems: (1) Low differentiation of semantic features between the COVID-19 infection regions, other pneumonia regions and normal lung tissues; (2) High variation of visual characteristics between different COVID-19 cases or stages; (3) High difficulty in constraining the irregular boundaries of the COVID-19 infection regions. To solve these problems, a multi-input directional UNet (MID-UNet) is proposed to segment COVID-19 infections in lung CT images. For the input part of the network, we firstly propose an image blurry descriptor to reflect the texture characteristic of the infections. Then the original CT image, the image enhanced by the adaptive histogram equalization, the image filtered by the non-local means filter and the blurry feature map are adopted together as the input of the proposed network. For the structure of the network, we propose the directional convolution block (DCB) which consist of 4 directional convolution kernels. DCBs are applied on the short-cut connections to refine the extracted features before they are transferred to the de-convolution parts. Furthermore, we propose a contour loss based on local curvature histogram then combine it with the binary cross entropy (BCE) loss and the intersection over union (IOU) loss for better segmentation boundary constraint. Experimental results on the COVID-19-CT-Seg dataset demonstrate that our proposed MID-UNet provides superior performance over the state-of-the-art methods on segmenting COVID-19 infections from CT images.
登录
查看更多内容
影响因子：
4.6
作者：
Gordaliza PM;Muñoz-Barrutia A;Abella M;Desco M;Sharpe S;Vaquero JJ
通讯作者：
Vaquero JJ
DOI：
10.1148/ryct.2020200075
发表时间：
2020-04-01
期刊：
RADIOLOGY-CARDIOTHORACIC IMAGING
影响因子：
--
作者：
Huang, Lu;Han, Rui;Xia, Liming
通讯作者：
Xia, Liming
影响因子：
8.4
作者：
Amzat, Jimoh;Aminu, Kafayat;Danjibo, Maryann C.
通讯作者：
Danjibo, Maryann C.
影响因子：
7.7
作者：
Keshani, Mohsen;Azimifar, Zohreh;Boostani, Reza
通讯作者：
Boostani, Reza
影响因子：
7.6
作者：
Muñoz-Barrutia A;Ceresa M;Artaechevarria X;Montuenga LM;Ortiz-de-Solorzano C
通讯作者：
Ortiz-de-Solorzano C