MetaFormer-driven Encoding Network for Robust Medical Semantic Segmentation

2026-01-01

AI Summary

This work proposes MFEnNet, an efficient medical image segmentation framework designed for deployment in resource-constrained clinical settings where existing high-performance models are often impractical due to excessive computational demands. By integrating a MetaFormer architecture into the U-Net encoder, MFEnNet replaces conventional self-attention mechanisms with pooling-based Transformer blocks to model global context while significantly reducing computational overhead. The framework further enhances multi-scale feature representation through the incorporation of Swish activation functions and spatial pyramid pooling. Experimental results demonstrate that MFEnNet achieves segmentation accuracy comparable to state-of-the-art methods across multiple medical imaging benchmarks, while substantially improving inference efficiency.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• medical semantic segmentation
• computational efficiency
• resource-constrained settings
• model complexity

Innovation

• MetaFormer
• Pooling Transformer
• Medical Semantic Segmentation
• Efficient Architecture
• Spatial Pyramid Pooling