Improving Low-Dose CT Image Using Residual Convolutional Network

Yang, Wei; Zhang, Huijuan; Yang, Jian; Wu, Jiasong; Yin, Xiangrui; Chen, Yang; Hu, Shu; Luo, Limin; Coatrieux, Gouenou; Gui, Zhiguo; Feng, Qianjin

doi:10.1109/access.2017.2766438

Cited by 93 publications

(67 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The structure of residual CNN model. Learning the differences between input data and ground truth, which is commonly called residual, has faster convergence speed when training CNN [15,23]. This is because it is difficult to map the downsampled image data to ground truth with conventional CNN structure (eg.…”

Section: Figmentioning

confidence: 99%

Temporally downsampled cerebral CT perfusion image restoration using deep residual learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose Acute ischemic stroke is one of the most causes of death all over the world. Onset to treatment time is critical in stroke diagnosis and treatment. Considering the time consumption and high price of MR imaging, CT perfusion (CTP) imaging is strongly recommended for acute stroke. However, too much CT radiation during CTP imaging may increase the risk of health problems. How to reduce CT radiation dose in CT perfusion imaging has drawn our great attention. Method In this study, the original 30-pass CTP images are downsampled to 15 passes in time sequence, which equals to 50% radiation dose reduction. Then, a residual deep convolutional neural network (CNN) model is proposed to restore the downsampled 15-pass CTP images to 30 passes to calculate the parameters such as CBF (Cerebral Blood Flow), CBV (Cerebral Blood Volume), MTT (Mean Transit Time), TTP (Time To Peak) for stroke diagnosis and treatment. The deep restoration CNN network is implemented simply and effectively with 16 successive convolutional layers which form a wide enough receptive field for input image data. 18 patients' CTP images are employed as training set and the other 6 patients' CTP images are treated as test dataset in this study. Results Experiments demonstrate that our CNN network can restore high-quality CTP images in terms of structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). The average SSIM and PSNR for test images are 0.981 and 56.25, and the SSIM and PSNR of regions of interest (ROI) are 0.915 and 42.44 respectively, showing promising quantitative level. In addition, we compare the perfusion maps calculated from the restored images and from the original images, and the average perfusion results of them are extremely close. Areas of hypoperfusion of 6 test cases could be detected with comparable accuracy by radiologists. Conclusion The trained model can restore the temporally downsampled 15-pass CTP to 30 passes very well. According to the contrast test, sufficient information cannot be restored with e.g., simple interpolation method and Deep Convolutional Generative Adversarial Network (DCGAN), but can be restored with the proposed CNN model. This method can be an optional way to reduce radiation dose during CTP imaging.

show abstract

Section: Figmentioning

confidence: 99%

Temporally downsampled cerebral CT perfusion image restoration using deep residual learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning methods have been widely conducted in LDCT problems and achieved significant breakthrough. Various types of convolutional neural networks (CNN) such as residual net [17][18][19], encoder-decoder [17,18,20], U-Net [21] were adopted in image domain for LDCT image denoising after reconstruction. The networks were trained with simulated LDCT and NDCT image pairs using L2-norm loss function.…”

Section: Introductionmentioning

confidence: 99%

A Model-Based Unsupervised Deep Learning Method for Low-Dose CT Reconstruction

et al. 2020

View full text Add to dashboard Cite

Low-dose CT (LDCT) is of great significance due to the concern about the potential radiation risk. With the fast development of deep learning, neural networks have become powerful tools in LDCT enhancement. Current deep neural networks for LDCT reconstruction are often trained with paired LDCT dataset and normal-dose CT (NDCT) dataset. However, high quality NDCT dataset paired with LDCT dataset is expensive to acquire or even not available sometimes in reality. In this work, we proposed an unsupervised model-based deep learning (MBDL) for LDCT reconstruction. The network is trained based on group-wise maximum a posterior (G-MAP) loss function with LDCT dataset only. The MBDL is a general framework. It also allows us to combine with supervised training if a small number of paired NDCT dataset accessible to help optimizing the network parameters, i.e. works in a semi-supervised mode. During inference, LDCT images are reconstructed end-to-end by the trained network. We verified the proposed method with simulated projection data from clinical CT images. The proposed method restrained noise well while restoring anatomical structures and it achieved better results than model-based iterative reconstruction (MBIR) with significantly less computational cost. The performances of MBDL were further enhanced by integrating a small paired NDCT dataset for semi-supervised training. The results suggested that MBDL is an efficient and flexible method for LDCT deep learning based reconstruction in the situations lacking of enough high quality NDCT data.

show abstract

“…In recent years, some researchers have introduced the idea of deep learning to limited-angle CT problems as well as low does problem [17]- [20]. According to the differences in the processing steps, it can be classified into three categories: image post-processing, projection pre-processing and reconstruction processing.…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Dilated Convolution Neural Network for Image Artifact Correction of Limited-Angle Tomography

et al. 2020

View full text Add to dashboard Cite

Limited-angle computed tomography (CT) has arisen in some medical and industrial applications. It is also a challenging problem since some scan views are missing and the directly reconstructed images often suffer from severe distortions. For such kind of problems, we analyze the features of limitedangle CT images and propose a multi-scale dilated convolution neural network (MSD-CNN) to correct the artifacts and to restore the image. In this network, the dilated convolution layer and multi-scale pooling layer are combined to form a group and exited in the whole encoder-decoder process. Since the dilated convolutions support an exponential expansion of the receptive field without losing resolution and coverage, the obtained artifact features possess the multi-scale characteristic. Furthermore, to improve the effectiveness and accuracy of the training step, we employ a preprocessing method, which extracts image patches. Numerical experiments verify the out-performance of the proposed method compared with some conventional methods, such as Unet based deep learning,TV-and L 0-based optimization methods. INDEX TERMS Limited-angle tomography, artifact correction, multi-scale, dilated convolution.

show abstract

Improving Low-Dose CT Image Using Residual Convolutional Network

Cited by 93 publications

References 12 publications

Temporally downsampled cerebral CT perfusion image restoration using deep residual learning

Temporally downsampled cerebral CT perfusion image restoration using deep residual learning

A Model-Based Unsupervised Deep Learning Method for Low-Dose CT Reconstruction

Multi-Scale Dilated Convolution Neural Network for Image Artifact Correction of Limited-Angle Tomography

Contact Info

Product

Resources

About