AUTHOR=Wu Zezhi , Li Xiaoshu , Zuo Jianhui 

TITLE=RAD-UNet: Research on an improved lung nodule semantic segmentation algorithm based on deep learning

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1084096

DOI=10.3389/fonc.2023.1084096

ISSN=2234-943X

ABSTRACT=Objective: Due to the small proportion of target pixels in computed tomography (CT) images and the high similarity with the environment, convolutional neural network semantic segmentation models are difficult to develop using deep learning. Extracting feature information often leads to under- or over-segmentation of lesions in CT images. In this paper, an improved convolutional neural network segmentation model known as RAD-UNet, which is based on the U-Net encoder-decoder architecture, is proposed and applied to lung nodular segmentation in CT images. Method: The proposed RAD-UNet segmentation model includes several improved components: the U-Net encoder is replaced by a ResNet residual network module; an atrous spatial pyramid pooling module is added after the U-Net encoder; and the U-Net decoder is improved by introducing a cross-fusion feature module with channel and spatial attention. Results: The segmentation model was applied to the LIDC dataset and a CT dataset collected by the Affiliated Hospital of Anhui Medical University. The experimental results show that compared with the existing SegNet and U-Net methods, the proposed model demonstrates better lung lesion segmentation performance. On the above two datasets, the mIoU reached 87.76% and 88.13%, and the F1-score reached 93.56% and 93.71%, respectively. Conclusion: The experimental results show that the improved RAD-UNet segmentation method achieves more accurate pixel-level segmentation in CT images of lung tumours and identifies lung nodules better than the SegNet and U-Net models. The problems of under- and over-segmentation that occur during segmentation are solved, effectively improving the image segmentation performance.