Multislice input for 2D and 3D residual convolutional neural network noise reduction in CT

Abstract

Purpose: Deep convolutional neural network (CNN)-based methods are increasingly used for reducing image noise in computed tomography (CT). Current attempts at CNN denoising are based on 2D or 3D CNN models with a single-or multiple-slice input. Our work aims to investigate if the multiple-slice input improves the denoising performance compared with the singleslice input and if a 3D network architecture is better than a 2D version at utilizing the multislice input.Approach: Two categories of network architectures can be used for the multislice input. First, multislice images can be stacked channel-wise as the multichannel input to a 2D CNN model. Second, multislice images can be employed as the 3D volumetric input to a 3D CNN model, in which the 3D convolution layers are adopted. We make performance comparisons among 2D CNN models with one, three, and seven input slices and two versions of 3D CNN models with seven input slices and one or three output slices. Evaluation was performed on liver CT images using three quantitative metrics with full-dose images as reference. Visual assessment was made by an experienced radiologist.Results: When the input channels of the 2D CNN model increases from one to three to seven, a trend of improved performance was observed. Comparing the three models with the seven-slice input, the 3D CNN model with a one-slice output outperforms the other models in terms of noise texture and homogeneity in liver parenchyma as well as subjective visualization of vessels. Conclusions:We conclude the that multislice input is an effective strategy for improving performance for 2D deep CNN denoising models. The pure 3D CNN model tends to have a better performance than the other models in terms of continuity across axial slices, but the difference was not significant compared with the 2D CNN model with the same number of slices as the input.

Self-trained deep convolutional neural network for noise reduction in CT

“…The CNN model can be based on many of the popular network architectures. Here, we employed a 2D residual-based CNN denoiser 5 for both ST_CNN and conventional deep CNN methods. An identical network architecture (Fig.…”

“…4) was used for both methods so that any performance difference can be attributed to the different training methods. To optimize the performance of the CNN model, we used seven adjacent CT slices as the channel input of the 2D residual CNN model 5 . The CNN inputs were first standardized by subtracting the mean value and dividing by the standard deviation (SD) and then were subjected to the initial 2D convolutional layer (Conv2D) to generate 128 feature maps.…”

“…To optimize the performance of the CNN model, we used seven adjacent CT slices as the channel input of the 2D residual CNN model. 5 The CNN inputs were first standardized by subtracting the mean value and dividing by the standard deviation (SD) and then were subjected to the initial 2D convolutional layer (Conv2D) to generate 128 feature maps. The feature maps were further processed by a series of 2D residual blocks, each of which consisted of repeated Conv2Ds, batch normalization, and rectified linear unit (ReLU) activation.…”

“…Deep convolutional neural networks (CNNs) have been one of the main driving forces for computed tomography (CT) image noise reduction in recent years 1 – 9 It has been shown that the CNN-based noise reduction methods can reduce image noise while preserving natural noise texture, which was one of the major limitations of iterative reconstruction 10 – 12 The majority of existing CNN-based denoising methods are supervised, in which they learn the mapping function between the low-quality image (e.g., lower dose) and its high-quality (e.g., higher dose) counterpart 1 …”

“… – 12 The majority of existing CNN-based denoising methods are supervised, in which they learn the mapping function between the low-quality image (e.g., lower dose) and its high-quality (e.g., higher dose) counterpart 1 – 5 The low-quality images are typically created by inserting noise into the high-quality projection data such that the low- and high-quality images are perfectly registered. When the projection data were inaccessible due to the protection of the intellectual properties of the CT manufacturers, unsupervised CNN-based noise reduction methods were developed to utilize a large amount of unpaired data for training 6 …”