DISGAN：小波感知判别器引导GAN实现带噪声清除的MRI超分辨率
DISGAN: Wavelet-informed Discriminator Guides GAN to MRI Super-resolution with Noise Cleaning
AI总结：
本研究提出DISGAN模型，通过嵌入3D DWT+卷积单元的频率感知3D Unet判别器引导残差结构3D生成器，仅用超分辨率任务训练即可同时实现MRI超分辨率与去噪，在HCP数据及脑疾病数据上表现优异。
摘要：
MRI超分辨率（SR）与去噪任务是深度学习领域的基础性挑战，传统上二者被视为独立任务，需使用各自的配对训练数据。本文提出一种创新方法，仅用单个深度学习模型即可同时解决这两项任务，训练过程无需显式的含噪与清晰图像配对数据。我们提出的模型主要针对超分辨率任务训练，但在生成的超分辨率图像中展现出卓越的噪声清除能力。与在生成过程中引入频率相关操作的传统方法不同，我们的全新思路采用由频率感知判别器引导的GAN模型。为此，我们在面向MRI数据超分辨率任务的GAN框架中，利用3D离散小波变换（DWT）操作作为频率约束。具体而言，我们的贡献包括：1）基于残差中残差连接块的3D生成器；2）将3D DWT与1×1卷积整合为DWT+卷积单元，嵌入判别器所用的3D Unet中；3）训练后的模型可实现高质量图像超分辨率，同时自带内在去噪过程。鉴于该模型兼具生成超分辨率图像和同步去噪的双重效果，我们将其命名为“去噪诱导超分辨率GAN（DISGAN）”。与将超分辨率和去噪任务作为独立模型训练的传统方法不同，我们提出的DISGAN仅针对超分辨率任务训练，却在去噪方面也取得了优异性能。该模型在来自人类连接组计划（HCP）的数十名受试者的3D MRI数据上训练，并进一步在来自脑肿瘤和癫痫患者的未见过的MRI数据上评估，以验证其去噪和超分辨率性能。
英文摘要：
MRI super-resolution (SR) and denoising tasks are fundamental challenges in the field of deep learning, which have traditionally been treated as distinct tasks with separate paired training data. In this paper, we propose an innovative method that addresses both tasks simultaneously using a single deep learning model, eliminating the need for explicitly paired noisy and clean images during training. Our proposed model is primarily trained for SR, but also exhibits remarkable noise-cleaning capabilities in the super-resolved images. Instead of conventional approaches that introduce frequency-related operations into the generative process, our novel approach involves the use of a GAN model guided by a frequency-informed discriminator. To achieve this, we harness the power of the 3D Discrete Wavelet Transform (DWT) operation as a frequency constraint within the GAN framework for the SR task on magnetic resonance imaging (MRI) data. Specifically, our contributions include: 1) a 3D generator based on residual-in-residual connected blocks; 2) the integration of the 3D DWT with $1\times 1$ convolution into a DWT+conv unit within a 3D Unet for the discriminator; 3) the use of the trained model for high-quality image SR, accompanied by an intrinsic denoising process. We dub the model "Denoising Induced Super-resolution GAN (DISGAN)" due to its dual effects of SR image generation and simultaneous denoising. Departing from the traditional approach of training SR and denoising tasks as separate models, our proposed DISGAN is trained only on the SR task, but also achieves exceptional performance in denoising. The model is trained on 3D MRI data from dozens of subjects from the Human Connectome Project (HCP) and further evaluated on previously unseen MRI data from subjects with brain tumours and epilepsy to assess its denoising and SR performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
