A lightweight neural network with multiscale feature enhancement for liver CT segmentation

Citations Over TimeTop 1% of 2022 papers

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.

Related Papers

• → Adaptive t-vMF dice loss: An effective expansion of dice loss for medical image segmentation(2023)46 cited
• → Medical Image Segmentation with Stochastic Aggregated Loss in a Unified U-Net(2019)11 cited
• → [Automatic segmentation of head and neck organs at risk based on three-dimensional U-NET deep convolutional neural network].(2020)4 cited
• → Adaptive t-vMF Dice Loss for Multi-class Medical Image Segmentation(2022)1 cited