학술논문
A lightweight neural network with multiscale feature enhancement for liver CT segmentation.
Document Type
Article
Author
Ansari, Mohammed Yusuf; Yang, Yin; Balakrishnan, Shidin; Abinahed, Julien; Al-Ansari, Abdulla; Warfa, Mohamed; Almokdad, Omran; Barah, Ali; Omer, Ahmed; Singh, Ajay Vikram; Meher, Pramod Kumar; Bhadra, Jolly; Halabi, Osama; Azampour, Mohammad Farid; Navab, Nassir; Wendler, Thomas; Dakua, Sarada Prasad
Source
Subject
*COMPUTED tomography
*LIVER
*HEPATOCELLULAR carcinoma
*NEURAL circuitry
*
*
*
Language
ISSN
2045-2322
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. [ABSTRACT FROM AUTHOR]