FAN-Net: Fourier-Based Adaptive Normalization For Cross-Domain Stroke Lesion Segmentation
arXiv:2304.11557 · doi:10.1109/ICASSP49357.2023.10096381
Abstract
Since stroke is the main cause of various cerebrovascular diseases, deep learning-based stroke lesion segmentation on magnetic resonance (MR) images has attracted considerable attention. However, the existing methods often neglect the domain shift among MR images collected from different sites, which has limited performance improvement. To address this problem, we intend to change style information without affecting high-level semantics via adaptively changing the low-frequency amplitude components of the Fourier transform so as to enhance model robustness to varying domains. Thus, we propose a novel FAN-Net, a U-Net--based segmentation network incorporated with a Fourier-based adaptive normalization (FAN) and a domain classifier with a gradient reversal layer. The FAN module is tailored for learning adaptive affine parameters for the amplitude components of different domains, which can dynamically normalize the style information of source images. Then, the domain classifier provides domain-agnostic knowledge to endow FAN with strong domain generalizability. The experimental results on the ATLAS dataset, which consists of MR images from 9 sites, show the superior performance of the proposed FAN-Net compared with baseline methods.
arXiv commentAccepted by IEEE ICASSP 2023
References in corpus (7)
- Automated Design of Deep Learning Methods for Biomedical Image Segmentation
- Unsupervised Domain Adaptation by Backpropagation
- X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
- Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge
- SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization
- DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation
- A multi-path 2.5 dimensional convolutional neural network system for segmenting stroke lesions in brain MRI images