用频谱分解提升医学图像分割，减少下采样信息丢失。
Spectral U-Net: Enhancing Medical Image Segmentation via Spectral Decomposition
- 用双树复小波变换实现下采样，保留高频细节
- 通过逆变换重建高分辨率特征，增强细节恢复
- 在视网膜、脑肿瘤等数据集上优于基准模型
本文提出Spectral U-Net，一种基于频谱分解的新型深度学习网络，利用双树复小波变换（DTCWT）进行下采样，逆双树复小波变换（iDTCWT）进行上采样。设计了Wave-Block与iWave-Block模块，嵌入U-Net架构中，旨在缓解下采样过程中的信息损失，并提升上采样阶段的细节重建能力。编码器中，先通过DTCWT将特征图分解为高低频成分，实现下采样同时保留关键信息；解码器中，利用iDTCWT从下采样特征重建高分辨率特征图。在Retina Fluid、Brain Tumor和Liver Tumor三个医学图像分割数据集上，基于nnU-Net框架的实验表明，所提方法显著优于现有基准模型。
原文摘要 · Abstract (English)
This paper introduces Spectral U-Net, a novel deep learning network based on spectral decomposition, by exploiting Dual Tree Complex Wavelet Transform (DTCWT) for down-sampling and inverse Dual Tree Complex Wavelet Transform (iDTCWT) for up-sampling. We devise the corresponding Wave-Block and iWave-Block, integrated into the U-Net architecture, aiming at mitigating information loss during down-sampling and enhancing detail reconstruction during up-sampling. In the encoder, we first decompose the feature map into high and low-frequency components using DTCWT, enabling down-sampling while mitigating information loss. In the decoder, we utilize iDTCWT to reconstruct higher-resolution feature maps from down-sampled features. Evaluations on the Retina Fluid, Brain Tumor, and Liver Tumor segmentation datasets with the nnU-Net framework demonstrate the superiority of the proposed Spectral U-Net.
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。