X-ray computed tomography (CT) is a non-invasive medical diagnostic tool that has raised public concerns due to the associated health risks of radiation dose to patients. Reducing the radiation dose leads to noise artifacts, making the low-dose CT images unreliable for diagnosis. Hence, low-dose CT (LDCT) image reconstruction techniques have offered a new research area. In this study, a deep neural network is proposed, specifically a residual network (ResNet) using dilated convolution, batch normalization, and rectified linear unit (ReLU) layers with fused spatial- and channel-attention modules to enhance the quality of LDCT images. The network is optimized using the integration of per-pixel loss, perceptual loss via VGG16-net, and dissimilarity index loss. Through an ablation experiment, these functions show that they could effectively prevent edge oversmoothing, improve image texture, and preserve the structural details. Finally, comparative experiments showed that the qualitative and quantitative results of the proposed network outperform state-of-the-art denoising models such as block-matching 3D filtering (BM3D), Markovian-based patch generative adversarial network (patch-GAN), and dilated residual network with edge detection (DRL-E-MP).

Computer-aided diagnosis (CAD) has become a major research interest in diagnostic radiology and medical imaging. The basic goal of CAD is to provide a computer output as a second opinion to assist medical image interpretation by improving accuracy, consistency of diagnosis, and image interpretation time. Since a CAD system is only interested in analyzing a specific organ, segmentation of computer tomography (CT) images is a precursor to most image analysis applications. A fully automated method is presented to segment lung in pulmonary CT images based on detected lung edges by wavelet analysis. Due to wavelet transformation characteristics, the proposed method is not only computational inexpensive compared to other existing methods such as snakes or watershed, but also is robust and accurate in detecting lung borders. A set of 330 low dose (50 mA) CT images were processed demonstrating accuracy and satisfactory performance of the algorithm.