What question did this study set out to answer?

This research aims to enhance medical image segmentation performance by addressing bottlenecks in U-Net structures.

May 14, 2026CAAI Transactions on Intelligence Technology0 citationsOpen Access

FMTNet: A Fourier‐Mamba–Transformer Enhanced Network for Medical Image Segmentation

SWShaoqiang WangQingdao University of Technology GSGuiling ShiQingdao University of Science and Technology YZYuanyuan ZhangQingdao University of Technology

Key Points

This research aims to enhance medical image segmentation performance by addressing bottlenecks in U-Net structures.
Proposed FMTNet integrates a composite enhancement module into the U-Net architecture.
Module consists of Fourier spatial fusion, hybrid mamba-transformer, and multi-scale context aggregation.
Extensive experiments conducted on multiple public multi-modal datasets.
FMTNet outperforms state-of-the-art methods across all key metrics.
Significantly enhances accuracy and robustness of medical image segmentation.
Demonstrates improved generalization capabilities in various imaging modalities.

Abstract

ABSTRACT Models based on U‐shaped networks have achieved widespread success in the field of medical image segmentation, but their performance is generally limited by structural bottlenecks in the network. At this stage, feature maps experience a sharp decline in spatial resolution due to continuous downsampling, resulting in significant loss of critical boundaries and structural details. Additionally, the local receptive fields of convolutions limit the effective modelling of global context. To address this core issue, we propose a novel enhanced segmentation network called FMTNet. FMTNet fundamentally enhances the expressive power of deep features by integrating an innovative composite enhancement module at the bottleneck of the U‐Net. This module consists of three synergistically working submodules: the Fourier spatial fusion module, which introduces a frequency‐domain perspective to compensate for and reconstruct high‐frequency structural information lost in the spatial domain; the hybrid mamba–transformer module, which efficiently captures cross‐regional long‐range dependencies to establish global context and the multi‐scale context Aggregation module, which fuses features of different scales to adapt to objects of varying sizes. We conducted extensive experiments on multiple public multi‐modal datasets, including colonoscopy polyps, dermatoscopy lesions, breast ultrasound and dental X‐rays. The results demonstrate that FMTNet comprehensively outperforms SOTA methods across all key metrics, showcasing exceptional segmentation accuracy and generalisation capabilities. Our research study demonstrates that by synergistically enhancing deep features across three dimensions—frequency, global, and multi‐scale—FMTNet provides a general and efficient solution to address the bottleneck issues of U‐Net, significantly enhancing the accuracy and robustness of medical image segmentation. The source code and pre‐trained weights are available at https://github.com/shiguiling0‐has/FMTNet .

问 AI

Bookmark

View Full Paper