双路学习提升医学图像去噪，兼顾噪声与上下文信息
Dual Path Learning -- learning from noise and context for medical image denoising
- 设计双路径结构，同时利用噪声特征和图像上下文信息
- 跨模态训练下相比UNet提升3.35%的PSNR
- 适用于多种成像模态和噪声类型，通用性强
医学影像在现代医疗中至关重要，但成像设备引入的噪声会降低图像质量，导致误判和临床后果受损。现有去噪方法通常仅依赖噪声特性或图像上下文信息，且多针对单一模态和噪声类型。受Geng等人的CNCL启发，本文提出双路径学习（DPL）模型架构，通过融合噪声与上下文信息实现高效去噪。DPL在多种成像模态和噪声类型上进行评估，展现出强鲁棒性与泛化能力。在高斯噪声下，跨模态训练时相比基线UNet提升3.35% PSNR。代码已公开于10.5281/zenodo.15836053。
原文摘要 · Abstract (English)
Medical imaging plays a critical role in modern healthcare, enabling clinicians to accurately diagnose diseases and develop effective treatment plans. However, noise, often introduced by imaging devices, can degrade image quality, leading to misinterpretation and compromised clinical outcomes. Existing denoising approaches typically rely either on noise characteristics or on contextual information from the image. Moreover, they are commonly developed and evaluated for a single imaging modality and noise type. Motivated by Geng et.al CNCL, which integrates both noise and context, this study introduces a Dual-Pathway Learning (DPL) model architecture that effectively denoises medical images by leveraging both sources of information and fusing them to generate the final output. DPL is evaluated across multiple imaging modalities and various types of noise, demonstrating its robustness and generalizability. DPL improves PSNR by 3.35% compared to the baseline UNet when evaluated on Gaussian noise and trained across all modalities. The code is available at 10.5281/zenodo.15836053.
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。