Deep-learning-based breast CT for radiation dose reduction

Cong, Wenxiang; Shan, Hongming; Zhang, Xiaohua; Liu, Shaohua; Ning, Ruola; Wang, Ge

doi:10.1117/12.2530234

Cited by 8 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the machines are costly and have yet to be incorporated into thea National Health Service (NHS). A study by Cong et al [ 188 ] created a ResNet network to restore images from a few-view breast CT. The suggested network model yielded impressive results and has significant value in clinical breast-imaging applications.…”

Section: Imaging Modalitiesmentioning

confidence: 99%

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

Mridha

Hamid

Monowar

et al. 2021

Cancers

View full text Add to dashboard Cite

Breast cancer is now the most frequently diagnosed cancer in women, and its percentage is gradually increasing. Optimistically, there is a good chance of recovery from breast cancer if identified and treated at an early stage. Therefore, several researchers have established deep-learning-based automated methods for their efficiency and accuracy in predicting the growth of cancer cells utilizing medical imaging modalities. As of yet, few review studies on breast cancer diagnosis are available that summarize some existing studies. However, these studies were unable to address emerging architectures and modalities in breast cancer diagnosis. This review focuses on the evolving architectures of deep learning for breast cancer detection. In what follows, this survey presents existing deep-learning-based architectures, analyzes the strengths and limitations of the existing studies, examines the used datasets, and reviews image pre-processing techniques. Furthermore, a concrete review of diverse imaging modalities, performance metrics and results, challenges, and research directions for future researchers is presented.

show abstract

Section: Imaging Modalitiesmentioning

confidence: 99%

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

Mridha

Hamid

Monowar

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…For qualitative assessment, we compared DEER with two state-of-the-art deep learning methods, including FBPConvNet [12] and Residual-CNN [14]. Both of these methods are considered as image-domain methods, in which the FBP operation is fixed and not learnable.…”

Section: A Data and Experimental Designmentioning

confidence: 99%

“…For example, FBPConvNet [12] uses the classical U-net [13] structure with conveying paths to remove streak artifacts. The residual convolutional neural network (Residual-CNN) [14] implements residual paths [15] in CNN to link previous layers to later layers. Also, a shallow architecture was developed [16] that learns a weighted combination of multiple filtered back-projection (FBP) [17] reconstructions with different learned filters.…”

Section: Introductionmentioning

confidence: 99%

Deep Efficient End-to-End Reconstruction (DEER) Network for Few-View Breast CT Image Reconstruction

et al. 2020

Self Cite

View full text Add to dashboard Cite

Breast CT provides image volumes with isotropic resolution in high contrast, enabling detection of small calcification (down to a few hundred microns in size) and subtle density differences. Since breast is sensitive to x-ray radiation, dose reduction of breast CT is an important topic, and for this purpose, fewview scanning is a main approach. In this article, we propose a Deep Efficient End-to-end Reconstruction (DEER) network for few-view breast CT image reconstruction. The major merits of our network include high dose efficiency, excellent image quality, and low model complexity. By the design, the proposed network can learn the reconstruction process with as few as O(N) parameters, where N is the side length of an image to be reconstructed, which represents orders of magnitude improvements relative to the state-of-the-art deeplearning-based reconstruction methods that map raw data to tomographic images directly. Also, validated on a cone-beam breast CT dataset prepared by Koning Corporation on a commercial scanner, our method demonstrates a competitive performance over the state-of-the-art reconstruction networks in terms of image quality.

show abstract

“…For qualitative comparison, the proposed DEAR-3D network was compared with two deep-learning-based methods for few-view CT image reconstruction, including the FBPConvNet method (a classic U-net [17] with conveying paths to solve the CT problem [16]) and a CNN-based residual network [40] (denoted as residual-CNN in this paper). The network settings were made the same as the default settings described in the original papers.…”

Section: Hyperparameter Selection and Network Comparisonmentioning

confidence: 99%

Deep Encoder-Decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-View Data

2019

Self Cite

View full text Add to dashboard Cite

X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizing X-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dose has been an important topic in recent years. Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper, we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT image reconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in 3D instead of 2D geometry, a 3D deep network has a great potential for improving the image quality in a data-driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publicly available abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other 2D deep-learning methods, the proposed DEAR-3D network can utilize 3D information to produce promising reconstruction results. Keywords:Deep encoder-decoder adversarial network (DEAR), generative adversarial network (GAN), few-view CT, sparse-view CT, machine learning, deep learning.

show abstract

Deep-learning-based breast CT for radiation dose reduction

Cited by 8 publications

References 24 publications

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

Deep Efficient End-to-End Reconstruction (DEER) Network for Few-View Breast CT Image Reconstruction

Deep Encoder-Decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-View Data

Contact Info

Product

Resources

About