MFA-Net: Multiscale Feature Attention Network for Medical Image Segmentation
Open Access
- 12 January 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 330
Abstract
Medical image segmentation acts as a foundational element of medical image analysis. Yet its accuracy is frequently limited by the scale fluctuations of anatomical targets and the intricate contextual traits inherent in medical images—including vaguely defined structural boundaries and irregular shape distributions. To tackle these constraints, we design a multi-scale feature attention network (MFA-Net), customized specifically for thyroid nodule, skin lesion, and breast lesion segmentation tasks. This network framework integrates three core components: a Bidirectional Feature Pyramid Network (Bi-FPN), a Slim-neck structure, and the Convolutional Block Attention Module (CBAM). CBAM steers the model to prioritize boundary regions while filtering out irrelevant information, which in turn enhances segmentation precision. Bi-FPN facilitates more robust fusion of multi-scale features via iterative integration of top-down and bottom-up feature maps, supported by lateral and vertical connection pathways. The Slim-neck design is constructed to simplify the network’s architecture while effectively merging multi-scale representations of both target and background areas, thus enhancing the model’s overall performance. Validation across four public datasets covering thyroid ultrasound (TNUI-2021, TN-SCUI 2020), dermoscopy (ISIC 2016), and breast ultrasound (BUSI) shows that our method outperforms state-of-the-art segmentation approaches, achieving Dice similarity coefficients of 0.955, 0.971, 0.976, and 0.846, respectively. Additionally, the model maintains a compact parameter count of just 3.05 million and delivers an extremely fast inference latency of 1.9 milliseconds—metrics that significantly outperform those of current leading segmentation techniques. In summary, the proposed framework demonstrates strong performance in thyroid, skin, and breast lesion segmentation, delivering an optimal trade-off between high accuracy and computational efficiency.Keywords
Funding Information
- Hebei Normal University (L2023T06)
This publication has 42 references indexed in Scilit:
- CIL-Net: Densely Connected Context Information Learning Network for Boosting Thyroid Nodule Segmentation Using Ultrasound ImagesCognitive Computation, 2024
- Slim-neck by GSConv: a lightweight-design for real-time detector architecturesJournal of Real-Time Image Processing, 2024
- GLFNet: Global-local fusion network for the segmentation in ultrasound imagesComputers in Biology and Medicine, 2024
- CRSANet: Class Representations Self-Attention network for the segmentation of thyroid nodulesBiomedical Signal Processing and Control, 2024
- HAU-Net: Hybrid CNN-transformer for breast ultrasound image segmentationBiomedical Signal Processing and Control, 2023
- BPAT-UNet: Boundary preserving assembled transformer UNet for ultrasound thyroid nodule segmentationComputer Methods and Programs in Biomedicine, 2023
- Dynamically aggregating MLPs and CNNs for skin lesion segmentation with geometry regularizationComputer Methods and Programs in Biomedicine, 2023
- MShNet: Multi-scale feature combined with h-network for medical image segmentationBiomedical Signal Processing and Control, 2022
- SLT-Net: A codec network for skin lesion segmentationComputers in Biology and Medicine, 2022
- Endometrium segmentation on transvaginal ultrasound image using key‐point discriminatorMedical Physics, 2019