论文标题
自我监督的低剂量计算机断层扫描图像使用可逆网络剥削夹层间一致性
Self Supervised Low Dose Computed Tomography Image Denoising Using Invertible Network Exploiting Inter Slice Congruence
论文作者
论文摘要
深度神经网络的复兴通过学习低剂量CT（LDCT）和正常剂量CT（NDCT）图像对之间的非线性转化函数，为低剂量计算机断层扫描降解创造了替代途径。但是，这些配对的LDCT和NDCT图像在临床环境中很少可用，从而使深度神经网络部署变得不可行。这项研究提出了一种新型的方法，用于自我监管的低剂量CT deno，以减轻配对的LDCT和NDCT图像的需求。具体而言，我们已经训练了一个可逆的神经网络，以最大程度地减少基于像素的均方根距离噪声切片和其两个即时相邻嘈杂片的平均值。我们已经表明，上述内容类似于训练神经网络，以最大程度地减少清洁NDCT和嘈杂的LDCT图像对之间的距离。同样，在可逆网络的反向映射期间，输出图像映射到原始输入图像，类似于循环一致性损失。最后，训练有素的可逆网络的正向映射用于降低LDCT图像。在两个公开数据集上进行的广泛实验表明，我们的方法对其他现有的无监督方法有利。
The resurgence of deep neural networks has created an alternative pathway for low-dose computed tomography denoising by learning a nonlinear transformation function between low-dose CT (LDCT) and normal-dose CT (NDCT) image pairs. However, those paired LDCT and NDCT images are rarely available in the clinical environment, making deep neural network deployment infeasible. This study proposes a novel method for self-supervised low-dose CT denoising to alleviate the requirement of paired LDCT and NDCT images. Specifically, we have trained an invertible neural network to minimize the pixel-based mean square distance between a noisy slice and the average of its two immediate adjacent noisy slices. We have shown the aforementioned is similar to training a neural network to minimize the distance between clean NDCT and noisy LDCT image pairs. Again, during the reverse mapping of the invertible network, the output image is mapped to the original input image, similar to cycle consistency loss. Finally, the trained invertible network's forward mapping is used for denoising LDCT images. Extensive experiments on two publicly available datasets showed that our method performs favourably against other existing unsupervised methods.
