EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices

TL;DR

EViT-UNet is a novel efficient Vision Transformer-based U-Net architecture designed for medical image segmentation on resource-limited devices, balancing high accuracy with reduced computational demands.

Contribution

This paper introduces EViT-UNet, a U-shaped network combining convolution and self-attention, optimized for low-resource medical image segmentation tasks.

Findings

Achieves high segmentation accuracy

Reduces computational complexity significantly

Suitable for mobile and edge medical devices

Abstract

With the rapid development of deep learning, CNN-based U-shaped networks have succeeded in medical image segmentation and are widely applied for various tasks. However, their limitations in capturing global features hinder their performance in complex segmentation tasks. The rise of Vision Transformer (ViT) has effectively compensated for this deficiency of CNNs and promoted the application of ViT-based U-networks in medical image segmentation. However, the high computational demands of ViT make it unsuitable for many medical devices and mobile platforms with limited resources, restricting its deployment on resource-constrained and edge devices. To address this, we propose EViT-UNet, an efficient ViT-based segmentation network that reduces computational complexity while maintaining accuracy, making it ideal for resource-constrained medical devices. EViT-UNet is built on a U-shaped architecture, comprising an encoder, decoder, bottleneck layer, and skip connections, combining convolutional operations with self-attention mechanisms to optimize efficiency. Experimental results demonstrate that EViT-UNet achieves high accuracy in medical image segmentation while significantly reducing computational complexity.