A lightweight neural network with multiscale feature enhancement for liver CT segmentation. Academic Article uri icon

Overview

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.

publication date

  • August 19, 2022

Research

keywords

  • Image Processing, Computer-Assisted
  • Liver Neoplasms

Identity

PubMed Central ID

  • PMC9391485

Scopus Document Identifier

  • 85136923717

Digital Object Identifier (DOI)

  • 10.1016/j.compbiomed.2021.105089

PubMed ID

  • 35986015

Additional Document Info

volume

  • 12

issue

  • 1