Preprint
Spectral U-Net: Enhancing Medical Image Segmentation via Spectral Decomposition
ArXiv.org
Cornell University
09/13/2024
DOI: 10.48550/arxiv.2409.09216
Abstract
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.
Details
- Title: Subtitle
- Spectral U-Net: Enhancing Medical Image Segmentation via Spectral Decomposition
- Creators
- Yaopeng PengMilan SonkaDanny Z Chen
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- DOI
- 10.48550/arxiv.2409.09216
- ISSN
- 2331-8422
- Publisher
- Cornell University; Ithaca, New York
- Language
- English
- Date posted
- 09/13/2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984702903102771
Metrics
69 Record Views