FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation
This addresses segmentation challenges in medical imaging, particularly for minority classes, but is incremental as it builds on existing U-Net and frequency-based approaches.
The paper tackled the problem of medical image segmentation with severe class imbalance and frequency-specific anatomical structures by proposing FreqU-FNet, a U-shaped architecture operating in the frequency domain, which outperformed CNN and Transformer baselines on multiple benchmarks, especially for under-represented classes.
Medical image segmentation faces persistent challenges due to severe class imbalance and the frequency-specific distribution of anatomical structures. Most conventional CNN-based methods operate in the spatial domain and struggle to capture minority class signals, often affected by frequency aliasing and limited spectral selectivity. Transformer-based models, while powerful in modeling global dependencies, tend to overlook critical local details necessary for fine-grained segmentation. To overcome these limitations, we propose FreqU-FNet, a novel U-shaped segmentation architecture operating in the frequency domain. Our framework incorporates a Frequency Encoder that leverages Low-Pass Frequency Convolution and Daubechies wavelet-based downsampling to extract multi-scale spectral features. To reconstruct fine spatial details, we introduce a Spatial Learnable Decoder (SLD) equipped with an adaptive multi-branch upsampling strategy. Furthermore, we design a frequency-aware loss (FAL) function to enhance minority class learning. Extensive experiments on multiple medical segmentation benchmarks demonstrate that FreqU-FNet consistently outperforms both CNN and Transformer baselines, particularly in handling under-represented classes, by effectively exploiting discriminative frequency bands.