MetaFormer-driven Encoding Network for Robust Medical Semantic Segmentation

TL;DR

This paper introduces MFEnNet, an efficient medical image segmentation framework that leverages MetaFormer and pooling transformer blocks to achieve high accuracy with reduced computational cost, suitable for resource-limited clinical environments.

Contribution

The paper presents a novel MetaFormer-based encoding network with pooling transformer blocks, improving efficiency and accuracy in medical segmentation tasks.

Findings

Achieves competitive accuracy on medical benchmarks.

Reduces computational complexity compared to state-of-the-art models.

Incorporates multi-scale feature extraction with spatial pyramid pooling.

Abstract

Semantic segmentation is crucial for medical image analysis, enabling precise disease diagnosis and treatment planning. However, many advanced models employ complex architectures, limiting their use in resource-constrained clinical settings. This paper proposes MFEnNet, an efficient medical image segmentation framework that incorporates MetaFormer in the encoding phase of the U-Net backbone. MetaFormer, an architectural abstraction of vision transformers, provides a versatile alternative to convolutional neural networks by transforming tokenized image patches into sequences for global context modeling. To mitigate the substantial computational cost associated with self-attention, the proposed framework replaces conventional transformer modules with pooling transformer blocks, thereby achieving effective global feature aggregation at reduced complexity. In addition, Swish activation is used to achieve smoother gradients and faster convergence, while spatial pyramid pooling is incorporated at the bottleneck to improve multi-scale feature extraction. Comprehensive experiments on different medical segmentation benchmarks demonstrate that the proposed MFEnNet approach attains competitive accuracy while significantly lowering computational cost compared to state-of-the-art models. The source code for this work is available at https://github.com/tranleanh/mfennet.