LSU-Net: Lightweight Automatic Organs Segmentation Network For Medical Images

TL;DR

LSU-Net is a lightweight, efficient neural network designed for medical image segmentation, combining novel blocks and dynamic loss weighting to outperform existing models while being suitable for resource-limited clinical environments.

Contribution

The paper introduces LSU-Net, a lightweight segmentation network that integrates Light Conv and Tokenized Shift Blocks with dynamic loss weighting for improved efficiency and accuracy.

Findings

Outperforms most state-of-the-art segmentation architectures.

Reduces model complexity with fewer parameters.

Demonstrates effectiveness on UWMGI and MSD Colon datasets.

Abstract

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures.