Texture‐aware dual domain mapping model for low‐dose CT reconstruction

Abstract

Background Remarkable progress has been made for low‐dose computed tomography (CT) reconstruction tasks by applying deep learning techniques. However, establishing an intrinsic link between deep learning techniques and CT texture preservation is still one of the significant challenges for researchers to further improve the effect of low‐dose CT (LDCT) reconstruction. Purpose Most of the existing deep learning‐based LDCT reconstruction methods are derived from popular frameworks, and most models focus on the image domain. Even few existing methods start with dual domains (sinogram and image) by considering the processing of the data itself, the final performances are limited due to the lack of perception of textures. With this in mind, we propose a method for texture perception on dual domains, so that the reconstruction process can be uniformly driven by visual effects. Methods The proposed method involves the processing of two domains: the sinogram domain and the image domain. For the sinogram domain, we have designed a novel dilated residual network (S‐DRN) which aims to increase the receptive field to obtain multiscale information. For the image domain, we propose a self‐attention (SA) residual encoder & decoder network (SRED‐Net) as the denoising network for obtaining much acceptable edges and textures. In addition, the composite loss function composed of the feature loss constructed by the proposed boundary and texture feature‐aware network (BTFAN) and the mean square error (MSE) can obtain a higher image quality while retaining more details and fewer artifacts, thereby obtaining better visual image quality. Results The proposed method was validated using both the American association of physicists in medicine (AAPM)‐Mayo clinic LDCT data sets and a real clinic data. Experimental results demonstrated that the new method has achieved the state‐of‐the‐art performance on objective indicators and visual metrics in terms of denoising and texture restoration. Conclusions Compared with single‐domain or existing dual‐domain processing strategies, the proposed texture‐aware dual domain mapping network (TADDM‐Net) can much better improve the visual effect of reconstructed CT images. Meantime, we also provide much intuitive evidence in terms of model interpretability.

CT image denoising methods for image quality improvement and radiation dose reduction

“…The predominant DL models for CT denoising are GANs and CNNs. As shown in Figure 2a, out of 99 publications examined, 61 studies use the models based on CNN, 59–119 while 30 studies are based on GAN 120–149 . Additionally, two studies adopt Transformer‐based approaches 150,151 .…”

“…The predominant DL models for CT denoising are GANs and CNNs. As shown in Figure 2a , out of 99 publications examined, 61 studies use the models based on CNN, 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , …”

“… 150 , 151 with the remaining approaches including filter‐based methods as well as hybrid methods. 152 , 153 , 154 , 155 , 156 , 157 To be noted that some models are originally developed, 61 , 62 , 65 , 66 , 68 , 70 , 72 , 73 , 77 , 122 , 153 while some are developed by modifying original models through modifying loss functions, or layers, or extending original models to different domains. 60 , 63 , 64 , 69 , 71 , 72 , 74 , 75 , 76 , 78 , 82 , 84 , 102 , 121 , 123 , 124 , 125 , 147 , 150 , 151 , 152 , 155 , 158 …”

“…Supervised DL‐based methods have been shown to produce high‐quality denoised CT images, and they are effective at removing various types of noise patterns. Out of 99 studies reviewed, 64 studies 42,59–68,71,72,74,76,77,79,80,83,84,86,88–93,97–104 , 106–109,111–119,123–126,132,134,137–139,142,147,153,159,161–163 apply supervised training method. CNNs are a common type of supervised DL‐based model used for CT image denoising.…”

“…Supervised DL‐based methods have been shown to produce high‐quality denoised CT images, and they are effective at removing various types of noise patterns. Out of 99 studies reviewed, 64 studies 42 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 71 , 72 , 74 , 76 , 77 , 79 , 80 , 83 , 84 , 86 , 88 , 89 , 90 , 91 , 92 , 93 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 106 , 107 , 108 , 109 , 111 , 112 , 113 , 114 , 115 , 116 , 117 , 118 , 119 , 123 , 124 , 125 , ...…”