1. A lightweight neural network with multiscale feature enhancement for liver CT segmentation
- Author
-
Mohammed Yusuf Ansari, Yin Yang, Shidin Balakrishnan, Julien Abinahed, Abdulla Al-Ansari, Mohamed Warfa, Omran Almokdad, Ali Barah, Ahmed Omer, Ajay Vikram Singh, Pramod Kumar Meher, Jolly Bhadra, Osama Halabi, Mohammad Farid Azampour, Nassir Navab, Thomas Wendler, and Sarada Prasad Dakua
- Subjects
Medicine ,Science - Abstract
Abstract Segmentation of abdominal Computed Tomography (CT) scan is essential for analyzing, diagnosing, and treating visceral organ diseases (e.g., hepatocellular carcinoma). This paper proposes a novel neural network (Res-PAC-UNet) that employs a fixed-width residual UNet backbone and Pyramid Atrous Convolutions, providing a low disk utilization method for precise liver CT segmentation. The proposed network is trained on medical segmentation decathlon dataset using a modified surface loss function. Additionally, we evaluate its quantitative and qualitative performance; the Res16-PAC-UNet achieves a Dice coefficient of 0.950 ± 0.019 with less than half a million parameters. Alternatively, the Res32-PAC-UNet obtains a Dice coefficient of 0.958 ± 0.015 with an acceptable parameter count of approximately 1.2 million.
- Published
- 2022
- Full Text
- View/download PDF