不同指标下几个loss正好是相反的,但一开始loss都是下降所用应该是正相关,在MSE下,网络loss递增方向是:CNN-MSE<WGAN-MSE<WGAN-VGG<CNN-VGG,在VGG下,网络loss递增方向正好相反。在定量测量下,PSNR和SSIM结果如下表: 实验的CT重建结果如下:
Low-dose CTImage denoisingGANConfidence mapArtifactUtilization of lower dose to generate CT images (LDCT) can reduce X-ray radiation damage to human body, but the resulting noise and artifacts will hinder its applications for clinical diagnosis. In order to solve the difficulty in separating the ...
[5] Ma J H,Huang J,Feng Q,et a1.Low—dose computed tomography image restoration using previous normal—dose SCan [J].Medical Physics,201 1,38(10):5713-5731. [6] Chen Y,Yin X,Shi L,et a1.Improving abdomen ttlnlor low-dose CT images using a fast dictionary learning based processi...
Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss In this paper, we introduce a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is...
Medical image reconstructionSemanticsTunable filtersLow-Dose CT (LDCT) scanning can greatly reduce the radiation damage to patients but would introduce serious noise and artifacts to CT images. The traditional deep learning based LDCT denoising methods are fundamentally based on the convolution operations,...
Low-dose CT has become a commonly used means of CT examination in clinical practice because of its relatively small amount of radiation and less radiation damage to the human body. However, its noise and image quality are lower than that of conventional CT and high-resolution CT, which directl...
模拟数据是通过来自NBIA的 7,015 normal-dose CT images of 256× 256 pixels per image来生成的low-dose数据,使用poisson噪声模型来模拟的使正常剂量CT发生降质的过程。而且不出意外的是,限于图像尺寸和数据量,patch-based的训练集在这里依然被采纳。真实数据来源于the 2016 NIH-AAPM-Mayo Clinic Low Dose CT ...
Although commercial iterative reconstruction methods have helped to lower radiation dose in CT studies, they can also alter image appearance and add artefacts. To see if deep learning could yield improvements, the researchers tested the MAP-NN model on 60 low-dose CT scans performed at MGH. The...
Low-dose CT is an effective solution to alleviate radiation risk to patients, it also introduces additional noise and streak artifacts. In order to maintain a high image quality for low-dose scanned CT data, we propose a post-processing method based on deep learning and using 2-D and 3-D...
文章提出了NNC(neural network convolution),不同于CNN,NNC从目标图像出发,学习LDCT和标准HDCT之间的区别。基本模型如下图所示,输入LDCT和HDCT经过滤波反投影变换,得到原始图像。 滤波反投影变换(FBP),是CT重建最常用的算法,原理是中心切片定理:原数据投影的一维傅立叶变换等于原数据的二维傅立叶变换。所以FBP的流程...