Progressive transfer learning strategy for low-dose CT image reconstruction with limited annotated data

Meng, Min; Li, Danyang; Li, Sui; Zhu, Manman; Wang, Lei; Gao, Qi; Bian, Zhaoying; Zhang, Xinyu; Huang, Jing; Ma, Jianhua

doi:10.1117/12.2548946

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data). Some of semi-supervised and unsupervised studies reviewed are [39,66,74,[127][128][129][130][131][132][133][134][135][136][137][138][139][140]. For example, [129] proposed an unsupervised model-based deep learning (MBDL) for LDCT reconstruction.…”

Section: Applications In Semi-supervised/unsupervised Mannermentioning

confidence: 99%

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Zhang

Yang

Shi

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Conventional reconstruction techniques, such as filtered back projection (FBP) and iterative reconstruction (IR), which have been utilised widely in the image reconstruction process of computed tomography (CT) are not suitable in the case of low-dose CT applications, because of the unsatisfying quality of the reconstructed image and inefficient reconstruction time. Therefore, as the demand for CT radiation dose reduction continues to increase, the use of artificial intelligence (AI) in image reconstruction has become a trend that attracts more and more attention. This systematic review examined various deep learning methods to determine their characteristics, availability, intended use and expected outputs concerning low-dose CT image reconstruction. Utilising the methodology of Kitchenham and Charter, we performed a systematic search of the literature from 2016 to 2021 in Springer, Science Direct, arXiv, PubMed, ACM, IEEE, and Scopus. This review showed that algorithms using deep learning technology are superior to traditional IR methods in noise suppression, artifact reduction and structure preservation, in terms of improving the image quality of low-dose reconstructed images. In conclusion, we provided an overview of the use of deep learning approaches in low-dose CT image reconstruction together with their benefits, limitations, and opportunities for improvement.

show abstract

Section: Applications In Semi-supervised/unsupervised Mannermentioning

confidence: 99%

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Zhang

Yang

Shi

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…also proposed a new transfer learning framework, which yields better denoising performance compared to commercial iterative reconstruction algorithms. Meng et al 29 . proposed a two‐stage progressive transfer‐learning network.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, Shan et al 28 also proposed a new transfer learning framework, which yields better denoising performance compared to commercial iterative reconstruction algorithms. Meng et al 29 proposed a two-stage progressive transfer-learning network. Their method can not only achieve good denoising effect but also retain the learned feature information with limited annotated CT data.…”

Section: Introductionmentioning

confidence: 99%

Domain‐adaptive denoising network for low‐dose CT via noise estimation and transfer learning

Wang

Tang

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Background: In recent years, low-dose computed tomography (LDCT) has played an important role in the diagnosis CT to reduce the potential adverse effects of X-ray radiation on patients, while maintaining the same diagnostic image quality. Purpose: Deep learning (DL)-based methods have played an increasingly important role in the field of LDCT imaging. However, its performance is highly dependent on the consistency of feature distributions between training data and test data. Due to patient's breathing movements during data acquisition, the paired LDCT and normal dose CT images are difficult to obtain from realistic imaging scenarios. Moreover, LDCT images from simulation or clinical CT examination often have different feature distributions due to the pollution by different amounts and types of image noises. If a network model trained with a simulated dataset is used to directly test clinical patients' LDCT data, its denoising performance may be degraded. Based on this, we propose a novel domain-adaptive denoising network (DADN) via noise estimation and transfer learning to resolve the out-of -distribution problem in LDCT imaging. Methods: To overcome the previous adaptation issue, a novel network model consisting of a reconstruction network and a noise estimation network was designed. The noise estimation network based on a double branch structure is used for image noise extraction and adaptation. Meanwhile, the U-Net-based reconstruction network uses several spatially adaptive normalization modules to fuse multi-scale noise input. Moreover, to facilitate the adaptation of the proposed DADN network to new imaging scenarios, we set a two-stage network training plan. In the first stage, the public simulated dataset is used for training. In the second transfer training stage, we will continue to fine-tune the network model with a torso phantom dataset, while some parameters are frozen. The main reason using the two-stage training scheme is based on the fact that the feature distribution of image content from the public dataset is complex and diverse,whereas the feature distribution of noise pattern from the torso phantom dataset is closer to realistic imaging scenarios. Results: In an evaluation study, the trained DADN model is applied to both the public and clinical patient LDCT datasets. Through the comparison of visual inspection and quantitative results, it is shown that the proposed DADN network model can perform well in terms of noise and artifact suppression, while effectively preserving image contrast and details. Conclusions: In this paper, we have proposed a new DL network to overcome the domain adaptation problem in LDCT image denoising. Moreover, the results demonstrate the feasibility and effectiveness of the application of our proposed DADN network model as a new DL-based LDCT image denoising method.

show abstract

“…While in many real situations, large paired NDCT dataset are expensive or even impossible to acquire. Considering the training efficiency and large NDCT dataset demand, transfer learning has been investigated for LDCT deep learning in recent years [30][31][32][33]. Transfer learning makes use of pre-trained models in the source domain and generalizes them to new applications in the target domain considering the domain similarity.…”

Section: Introductionmentioning

confidence: 99%

“…trained a LDCT denosing network with 848 paired medium-dose CT image labels firstly. The pre-trained network combined with an additional simple CNN network was further fine-tuned with 200 high-dose CT image labels [32]. Shan et.…”

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

Progressive transfer learning strategy for low-dose CT image reconstruction with limited annotated data

Cited by 4 publications

References 0 publications

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Domain‐adaptive denoising network for low‐dose CT via noise estimation and transfer learning

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

Contact Info

Product

Resources

About