Year: 2025
Type: conference-paper
Abstract: Magnetic Resonance Imaging (MRI) is an essential diagnostic tool in clinical settings, but its utility is often hin-dered by noise artifacts introduced during the imaging process. Effective denoising is critical for enhancing image quality while preserving anatomical structures. However, traditional denoising methods, which often assume uni-form noise distributions, struggle to handle the non-uniform noise commonly present in MRI images. In this paper, we introduce a novel approach leveraging a sparse mixture-of-experts framework for MRI image denoising. Each expert is a specialized denoising convolutional neural network fine-tuned to target specific noise characteristics associated with different image regions. Our method demonstrates superior performance over state-of-the-art denoising techniques on both synthetic and real-world brain MRI datasets. Fur-thermore, we show that it generalizes effectively to unseen datasets, highlighting its robustness and adaptability.
Authors: Zeyun Deng, Joseph Campbell
Institution: Purdue University West Lafayette
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409917476