M<sub>3</sub>NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising

Lu, Zexin; Xia, Wenjun; Huang, Yongqiang; Hou, Mingzheng; Chen, Hu; Zhou, Jiliu; Shan, Hongming; Zhang, Yi

doi:10.1109/tmi.2022.3219286

Cited by 16 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the iteration unrolling models are larger than post-processing models, they have better performance and interpretability benefitting from the hybrid data-and model-driven manner. In addition, we expect network architecture search will be a potential solution to lessen the model scale [61].…”

Section: Discussionmentioning

confidence: 99%

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

Zhang

Chen

Xia

et al. 2023

IEEE Trans. Radiat. Plasma Med. Sci.

Self Cite

View full text Add to dashboard Cite

Compressed sensing (CS) computed tomography (CT) has been proven to be important for several clinical applications, such as sparse-view CT, digital tomosynthesis, and interior tomography. Traditional CS focuses on the design of handcrafted prior regularizers, which are usually image-dependent and timeconsuming. Inspired by recently proposed deep learning-based CT reconstruction models, we extend the state-of-the-art LEARN model to a dual-domain version, dubbed LEARN++. Different from existing iteration unrolling methods, which only involve projection data in the data consistency layer, the proposed LEARN++ model integrates two parallel and interactive subnetworks to perform image restoration and sinogram inpainting operations on both the image and projection domains simultaneously, which can fully explore the latent relations between projection data and reconstructed images. The experimental results demonstrate that the proposed LEARN++ model achieves competitive qualitative and quantitative results compared to several state-of-the-art methods in terms of both artifact reduction and detail preservation.

show abstract

Section: Discussionmentioning

confidence: 99%

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

Zhang

Chen

Xia

et al. 2023

IEEE Trans. Radiat. Plasma Med. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…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 .…”

Section: Dl‐based Noise Reduction Methodsmentioning

confidence: 99%

“…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 , …”

Section: Dl‐based Noise Reduction Methodsmentioning

confidence: 99%

“… 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 …”

Section: Dl‐based Noise Reduction Methodsmentioning

confidence: 99%

See 1 more Smart Citation

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

Sadia,

Chen,

Zhang

2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

With the ever‐increasing use of computed tomography (CT), concerns about its radiation dose have become a significant public issue. To address the need for radiation dose reduction, CT denoising methods have been widely investigated and applied in low‐dose CT images. Numerous noise reduction algorithms have emerged, such as iterative reconstruction and most recently, deep learning (DL)‐based approaches. Given the rapid advancements in Artificial Intelligence techniques, we recognize the need for a comprehensive review that emphasizes the most recently developed methods. Hence, we have performed a thorough analysis of existing literature to provide such a review. Beyond directly comparing the performance, we focus on pivotal aspects, including model training, validation, testing, generalizability, vulnerability, and evaluation methods. This review is expected to raise awareness of the various facets involved in CT image denoising and the specific challenges in developing DL‐based models.

show abstract

“…When the x-ray radiation dose is absorbed by the human body, it may potentially induce abnormal metabolism or even genetic damage and cancer (Brenner et al 2001, Brenner andHall 2007). The use of low-dose CT (LDCT) in practice can effectively reduce the radiation risk for patients but the resultant image noise and artifacts could compromise diagnosis (Hong et al 2016, Xia et al 2021, Chaoqun et al 2022, Lu et al 2023. Since the concept of LDCT was proposed (Naidich et al 1990), a variety of methods were developed to suppress image noise and artifacts.…”

Section: Introductionmentioning

confidence: 99%

QS-ADN: quasi-supervised artifact disentanglement network for low-dose CT image denoising by local similarity among unpaired data

Ruan,

Yuan,

Niu

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Deep learning has been successfully applied tolow-dose CT (LDCT) image denoising for reducing potentialradiation risk. However, the widely reported supervised LDCTdenoising networks require a training set of paired images,which is expensive to obtain and cannot be perfectly simulated.Unsupervised learning utilizes unpaired data and is highlydesirable for LDCT denoising. As an example, an artifactdisentanglement network (ADN) relies on unparied imagesand obviates the need for supervision but the results ofartifact reduction are not as good as those through supervisedlearning. An important observation is that there is often hiddensimilarity among unpaired data that can be utilized. Thispaper introduces a new learning mode, called quasi-supervisedlearning, to empower the ADN for LDCT image denoising.For every LDCT image, the best matched image is first foundfrom an unpaired normal-dose CT (NDCT) dataset. Then,the matched pairs and the corresponding matching degree asprior information are used to construct and train our ADNtype network for LDCT denoising. The proposed method isdifferent from (but compatible with) supervised and semisupervised learning modes and can be easily implemented bymodifying existing networks. The experimental results showthat the method is competitive with state-of-the-art methodsin terms of noise suppression and contextual fidelity. Thecode and working dataset are publicly available at https://github.com/ruanyuhui/ADN-QSDL.git.

show abstract

M₃NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising

Cited by 16 publications

References 53 publications

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

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

QS-ADN: quasi-supervised artifact disentanglement network for low-dose CT image denoising by local similarity among unpaired data

Contact Info

Product

Resources

About

M3NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising

Cited by 16 publications

References 53 publications

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

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

QS-ADN: quasi-supervised artifact disentanglement network for low-dose CT image denoising by local similarity among unpaired data

Contact Info

Product

Resources

About

M₃NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising