频域U-net提升医学图像少样本分割效果
FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation
- 在频域构建U型网络，用小波下采样提取多尺度频谱特征
- 设计自适应多分支上采样，重建精细空间细节，提升小类分割精度
- 适合处理标注不均的医学图像分割任务，尤其对少数类别有效
医学图像分割因类别严重失衡及解剖结构频率分布特性而面临挑战。传统基于CNN的方法在空间域操作，难以捕捉少数类信号，易受频率混叠影响且频谱选择性弱；基于Transformer的模型虽能建模全局依赖，却常忽略细粒度局部细节。为此，我们提出频域感知的U型分割架构FreqU-FNet。其采用频域编码器，结合低通频域卷积与Daubechies小波下采样以提取多尺度频谱特征；为恢复精细空间细节，引入可学习空间解码器（SLD），配备自适应多分支上采样策略；同时设计频域感知损失函数（FAL）以增强少数类学习。在多个医学分割基准上的大量实验表明，FreqU-FNet持续优于CNN与Transformer基线模型，尤其在处理未充分代表类别时表现突出，有效利用了判别性频带。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。