FBDA ‐Net: Medical Image Segmentation via Foreground–Background Decoupled Attention Aggregation
- 8 October 2026
- journal article
- research article
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 36 (6) , e70454
Abstract
Medical image segmentation is a fundamental task in computer‐aided diagnosis, playing an important role in organ measurement, lesion delineation, and surgical planning. However, due to the limitations of imaging conditions and the complexity of tissue characteristics, foreground targets and the background often exhibit a “soft boundary,” and the two are easily confused in ambiguous transition regions, which limits further improvement of segmentation accuracy. To address this, we propose FBDA‐Net, a segmentation network based on foreground–background decoupled attention (FBDA). Its core module, the FBDA, decouples the input features into foreground and background at the feature level using prior masks, computes attention with a shared Query and three independent sets of Key/Value, and employs a joint Softmax so that the foreground, background, and global branches competitively allocate weights within the same probability space. Building upon this, we construct a top‐down progressive decoupling decoder that converts the prediction at each level into prior masks and passes them downward layer by layer, driving the decoupled priors to be progressively reconstructed and refined along the decoding process, and we adopt a combinatorial supervision loss to strengthen the cross‐level consistency of multi‐level predictions. Experiments on three benchmark datasets—Synapse multi‐organ CT, ACDC cardiac MRI, and ISIC 2016 dermoscopy—demonstrate competitive overall segmentation performance. Zero‐shot external evaluation on PH2 without fine‐tuning further supports the cross‐dataset generalization of FBDA‐Net. The source code is publicly available at https://github.com/TongLiuLDU/FBDANet.git .Keywords
Funding Information
- National Natural Science Foundation of China (61702249)
- National Natural Science Foundation of China (61741311)
- Natural Science Foundation of Shandong Province (ZR2020MF134)
This publication has 28 references indexed in Scilit:
- Adaptive modality-channel-search Hadamard multimodal fusion network for multi-phase liver tumor segmentationBiomedical Signal Processing and Control, 2026
- Lifting wavelet transform-guided network with histogram attention for liver segmentation in CT scansInformation Fusion, 2026
- Contrastive coarse-to-fine medical segmentation with prototype guidance and dual-granularity fusionNeurocomputing, 2026
- Medical image segmentation model for complex boundary features: Large kernel deformable convolution and gated feature preservationExpert Systems with Applications, 2025
- Human visual perception-inspired medical image segmentation network with multi-feature compressionArtificial Intelligence in Medicine, 2025
- A Medical image segmentation model with auto-dynamic convolution and location attention mechanismComputer Methods and Programs in Biomedicine, 2025
- CSWin-UNet: Transformer UNet with cross-shaped windows for medical image segmentationInformation Fusion, 2024
- Label-aware Attention Network with Multi-scale Boosting for Medical Image SegmentationExpert Systems with Applications, 2024
- PVT v2: Improved baselines with pyramid vision transformerComputational Visual Media, 2022
- A survey on deep learning in medical image analysisMedical Image Analysis, 2017