MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentation

TL;DR

MobileUtr is a novel lightweight medical image segmentation model that effectively combines CNNs and Transformers, leveraging their strengths to achieve superior performance with lower computational costs across multiple datasets.

Contribution

This work introduces a new hybrid network architecture, MobileUtr, integrating CNN and Transformer components for efficient medical image segmentation, emphasizing lightweight design and improved global context understanding.

Findings

Outperforms state-of-the-art methods on five medical datasets

Achieves lighter weights and lower computational costs

Demonstrates effective local-to-global information exchange

Abstract

Due to the scarcity and specific imaging characteristics in medical images, light-weighting Vision Transformers (ViTs) for efficient medical image segmentation is a significant challenge, and current studies have not yet paid attention to this issue. This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level. In order to leverage the inductive bias inherent in CNNs, we abstract a Transformer-like lightweight CNNs block (ConvUtr) as the patch embeddings of ViTs, feeding Transformer with denoised, non-redundant and highly condensed semantic information. Moreover, an adaptive Local-Global-Local (LGL) block is introduced to facilitate efficient local-to-global information flow exchange, maximizing Transformer's global context information extraction capabilities. Finally, we build an efficient medical image segmentation model (MobileUtr) based on CNN and Transformer. Extensive experiments on five public medical image datasets with three different modalities demonstrate the superiority of MobileUtr over the state-of-the-art methods, while boasting lighter weights and lower computational cost. Code is available at https://github.com/FengheTan9/MobileUtr.