Academic Journal
MGA-UNet: A Frequency-Aware Multi-Scale Mamba U-Net for Medical Image Segmentation.
| Title: | MGA-UNet: A Frequency-Aware Multi-Scale Mamba U-Net for Medical Image Segmentation. |
|---|---|
| Authors: | Qiu S; School of Computer and Control Engineering, Yantai University, Yantai 264005, China., Wang X; School of Computer and Control Engineering, Yantai University, Yantai 264005, China., Su K; School of Computer and Control Engineering, Yantai University, Yantai 264005, China., Song Y; School of Computer and Control Engineering, Yantai University, Yantai 264005, China., Zheng Q; School of Computer and Control Engineering, Yantai University, Yantai 264005, China., Cao Z; School of Computer and Control Engineering, Yantai University, Yantai 264005, China. |
| Source: | Sensors (Basel, Switzerland) [Sensors (Basel)] 2026 Aug 27; Vol. 26 (17). Date of Electronic Publication: 2026 Aug 27. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Basel, Switzerland : MDPI, c2000- |
| MeSH Terms: | Image Processing, Computer-Assisted*/methods, Image Interpretation, Computer-Assisted/methods ; Algorithms ; Humans ; Convolutional Neural Networks ; Wavelet Analysis |
| Abstract: | Medical image segmentation is a critical task in computer-assisted diagnosis, but accurate delineation remains challenging in sensor-captured dermoscopic and endoscopic images because of low contrast, blurred boundaries, acquisition artifacts, and large appearance variations. Although CNN-based methods are effective in capturing local texture and boundary cues, they often struggle to explicitly model long-range dependencies and global structural relationships. Transformer-based architectures can capture global context, but their self-attention mechanism may become computationally costly when processing high-resolution feature maps. To address these challenges, we propose MGA-UNet, a frequency-aware multi-scale encoder-decoder segmentation framework that integrates wavelet-based frequency decomposition with Mamba-based long-range dependency modelling. Specifically, the Wavelet-Mamba feature extraction backbone (WMB) decomposes features into low- and high-frequency components to enhance boundary-aware representation, the Gated Multi-scale Aggregation Module (GMAM) aggregates parallel multi-scale encoder features and applies a content-dependent gate to the fused response, and the Adaptive Sparse Attention Module (ASAM) refines bottleneck representations with sparse attention for global semantic modelling. Across three independent runs with random seeds 42, 123, and 2026, MGA-UNet achieves mean Dice Similarity Coefficients of 88.92±0.04%, 88.01±0.07%, and 85.91±0.04% on ISIC2018, ISIC2017, and Kvasir-SEG, respectively. These results demonstrate competitive segmentation performance among the compared representative CNN-based, Transformer-based, and Mamba-based methods, including the recent H-VMUNet baseline. These results indicate that frequency-domain decomposition and state-space modelling can complement each other for accurate medical image segmentation, particularly in images with ambiguous boundaries and complex background interference. |
| References: | Front Bioeng Biotechnol. 2020 Dec 23;8:605132. (PMID: 33425871) Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018). 2018 Sep;11045:3-11. (PMID: 32613207) IEEE Trans Pattern Anal Mach Intell. 2023 Jan;45(1):87-110. (PMID: 35180075) Comput Biol Med. 2023 Sep;164:107268. (PMID: 37494821) IEEE Trans Med Imaging. 2023 May;42(5):1484-1494. (PMID: 37015444) IEEE Trans Med Imaging. 2020 Oct;39(10):3008-3018. (PMID: 32224453) Comput Biol Med. 2024 Feb;169:107919. (PMID: 38176212) Bioengineering (Basel). 2026 Jul 08;13(7):. (PMID: 42510450) |
| Contributed Indexing: | Keywords: Mamba; medical image segmentation; sparse attention; wavelet transform |
| Entry Date(s): | Date Created: 20260915 Date Completed: 20260915 Latest Revision: 20260916 |
| Update Code: | 20260916 |
| PubMed Central ID: | PMC13568299 |
| DOI: | 10.3390/s26175416 |
| PMID: | 42740035 |
| Database: | MEDLINE |
| ISSN: | 1424-8220 |
|---|---|
| DOI: | 10.3390/s26175416 |