Multi-scale conv-attention U-Net for medical image segmentation DOI Creative Commons
Linqiang Pan, Chengxue Zhang, Jingbo Sun

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 8, 2025

U-Net-based network structures are widely used in medical image segmentation. However, effectively capturing multi-scale features and spatial context information of complex organizational remains a challenge. To address this, we propose novel structure based on the U-Net backbone. This model integrates Adaptive Convolution (AC) module, Multi-Scale Learning (MSL) Conv-Attention module to enhance feature expression ability segmentation performance. The AC dynamically adjusts convolutional kernel through an adaptive layer. enables extract different shapes scales adaptively, further improving its performance scenarios. MSL is designed for fusion. It aggregates fine-grained high-level semantic from resolutions, creating rich connections between encoding decoding processes. On other hand, incorporates efficient attention mechanism into skip connections. captures global using low-dimensional proxy high-dimensional data. approach reduces computational complexity while maintaining effective channel extraction. Experimental validation CVC-ClinicDB, MICCAI 2023 Tooth, ISIC2017 datasets demonstrates that our proposed MSCA-UNet significantly improves accuracy robustness. At same time, it lightweight outperforms existing methods.

Language: Английский

ELA-Net: An Efficient Lightweight Attention Network for Skin Lesion Segmentation DOI Creative Commons
Tianyu Nie, Yishi Zhao,

Shihong Yao

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(13), P. 4302 - 4302

Published: July 2, 2024

In clinical conditions limited by equipment, attaining lightweight skin lesion segmentation is pivotal as it facilitates the integration of model into diverse medical devices, thereby enhancing operational efficiency. However, design may face accuracy degradation, especially when dealing with complex images such irregular regions, blurred boundaries, and oversized boundaries. To address these challenges, we propose an efficient attention network (ELANet) for task. ELANet, two different mechanisms bilateral residual module (BRM) can achieve complementary information, which enhances sensitivity to features in spatial channel dimensions, respectively, then multiple BRMs are stacked feature extraction input information. addition, acquires global information improves putting maps scales through multi-scale fusion (MAF) operations. Finally, evaluate performance ELANet on three publicly available datasets, ISIC2016, ISIC2017, ISIC2018, experimental results show that our algorithm 89.87%, 81.85%, 82.87% mIoU datasets a parametric 0.459 M, excellent balance between lightness superior many existing methods.

Language: Английский

Citations

4
Learning multi-axis representation in frequency domain for medical image segmentation DOI
Jiacheng Ruan, Jingsheng Gao, Mingye Xie

et al.

Machine Learning, Journal Year: 2025, Volume and Issue: 114(1)

Published: Jan. 1, 2025

Language: Английский

Citations

0
Miniunet: An Efficient Mobile-Ready Approach for Online Yarn Quality Detection DOI

Yao Huang,

Shangjie Li,

Haipeng Pan

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Neural Memory Self-Supervised State Space Models With Learnable Gates DOI
Zhihua Wang, Yuxin He, Yi Zhang

et al.

IEEE Signal Processing Letters, Journal Year: 2025, Volume and Issue: 32, P. 926 - 930

Published: Jan. 1, 2025

Language: Английский

Citations

0
UCM-NetV2: an Efficient and Accurate Deep Learning Model for Skin Lesion Segmentation DOI Creative Commons
Chunyu Yuan, Dongfang Zhao, Sos С. Agaian

et al.

Journal of Economy and Technology, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

0
U-MGA: A Multi-Module Unet Optimized with Multi-Scale Global Attention Mechanisms for Fine-Grained Segmentation of Cultivated Areas DOI Creative Commons
Yun Chen, Yiheng Xie, Weiyuan Yao

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(5), P. 760 - 760

Published: Feb. 22, 2025

Arable land is fundamental to agricultural production and a crucial component of ecosystems. However, its complex texture distribution in remote sensing images make it susceptible interference from other cover types, such as water bodies, roads, buildings, complicating accurate identification. Building on previous research, this study proposes an efficient lightweight CNN-based network, U-MGA, address the challenges feature similarity between arable non-arable areas, insufficient fine-grained extraction, underutilization multi-scale information. Specifically, Multi-Scale Adaptive Segmentation (MSAS) designed during extraction phase provide multi-feature information, supporting model’s reconstruction stage. In phase, introduction Contextual Module (MCM) Group Aggregation Bridge (GAB) significantly enhances efficiency accuracy utilization. The experiments conducted dataset based GF-2 imagery publicly available show that U-MGA outperforms mainstream networks (Unet, A2FPN, Segformer, FTUnetformer, DCSwin, TransUnet) across six evaluation metrics (Overall Accuracy (OA), Precision, Recall, F1-score, Intersection-over-Union (IoU), Kappa coefficient). Thus, provides precise solution for recognition task, which significant importance resource monitoring ecological environmental protection.

Language: Английский

Citations

0
A Novel U-Shaped Hybrid Segmentation Approach to Imbalanced Medical Image Using Receptive Field Enhancement and Adaptive Weighted Loss Function DOI
Mahdi Zarrin, Haniyeh Nikkhah,

Mohammad Nourian

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Automatic brain MRI tumors segmentation based on deep fusion of weak edge and context features DOI Creative Commons

Leyi Xiao,

Baoxian Zhou, Chaodong Fan

et al.

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(5)

Published: March 3, 2025

Language: Английский

Citations

0
A damage detection network for ancient murals via multi-scale boundary and region feature fusion DOI Creative Commons

Xiuhui Wu,

Yingyan Yu, Ying Li

et al.

Published: March 18, 2025

Language: Английский

Citations

0
Dual branch segment anything model‐transformer fusion network for accurate breast ultrasound image segmentation DOI Open Access
Yu Li, Jin Huang, Yimin Zhang

et al.

Medical Physics, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

Abstract Background Precise and rapid ultrasound‐based breast cancer diagnosis is essential for effective treatment. However, existing ultrasound image segmentation methods often fail to capture both global contextual features fine‐grained boundary details. Purpose This study proposes a dual‐branch network architecture that combines the Swin Transformer Segment Anything Model (SAM) enhance (BUSI) accuracy reliability. Methods Our integrates attention mechanism of with detection from SAM through multi‐stage feature fusion module. We evaluated our method against state‐of‐the‐art on two datasets: Breast Ultrasound Images dataset Wuhan University (BUSI‐WHU), which contains 927 images (560 benign 367 malignant) ground truth masks annotated by radiologists, public BUSI dataset. Performance was using mean Intersection‐over‐Union (mIoU), 95th percentile Hausdorff Distance (HD95) Dice Similarity coefficients, statistical significance assessed two‐tailed independent t ‐tests Holm–Bonferroni correction (). Results On proposed dataset, achieved mIoU 90.82% HD95 23.50 pixels, demonstrating significant improvements over current effect sizes ranging 0.38 0.61 ( p 0.05). 82.83% 71.13 comparable 0.45 0.58 Conclusions leverages complementary strengths mechanism, superior performance. code publicly available at https://github.com/Skylanding/DSATNet .

Language: Английский

Citations

0