AWEU-Net: an attention-aware weight excitation U-Net for lung nodule segmentation.

Banu, Syeda Furruka; Sarker, Md. Mostafa Kamal; Abdel-Nasser, Mohamed; Puig, Domenec; Raswan, Hatem A.

Abstract

Lung cancer is a deadly cancer that causes millions of deaths every year around the world. Accurate lung nodule detection and segmentation in computed tomography (CT) images is a vital step for diagnosing lung cancer early. Most existing systems face several challenges, such as the heterogeneity in CT images and variation in nodule size, shape, and location, which limit their accuracy. In an attempt to handle these challenges, this article proposes a fully automated deep learning framework that consists of lung nodule detection and segmentation models. Our proposed system comprises two cascaded stages: (1) nodule detection based on fine-tuned Faster R-CNN to localize the nodules in CT images, and (2) nodule segmentation based on the U-Net architecture with two effective blocks, namely position attention-aware weight excitation (PAWE) and channel attention-aware weight excitation (CAWE), to enhance the ability to discriminate between nodule and non-nodule feature representations. The experimental results demonstrate that the proposed system yields a Dice score of 89.79% and 90.35%, and an intersection over union (IoU) of 82.34% and 83.21% on the publicly available LUNA16 and LIDC-IDRI datasets, respectively.

Citation

BANU, S.F., SARKER, M.M.K., ABDEL-NASSER, M., PUIG, D. and RASWAN, H.A. 2021. AWEU-Net: an attention-aware weight excitation U-Net for lung nodule segmentation. Applied science [online], 11(21), article 10132. Available from: https://doi.org/10.3390/app112110132

• Journal Article Type: Article
• Acceptance Date: Oct 22, 2021
• Online Publication Date: Oct 28, 2021
• Publication Date: Nov 1, 2021
• Deposit Date: Nov 18, 2021
• Publicly Available Date: Nov 18, 2021
• Journal: Applied Sciences
• Electronic ISSN: 2076-3417
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 11
• Issue: 21
• Article Number: 10132
• DOI: https://doi.org/10.3390/app112110132
• Keywords: Artificial intelligence; Computer-aided diagnosis; Computed tomography; Lung cancer; Deep learning; Lung nodule detection; Lung nodule segmentation
• Public URL: https://rgu-repository.worktribe.com/output/1530022