Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks

Gomi, Tsutomu; Sakai, Rina; Hara, Hidetake; Watanabe, Yusuke; Mizukami, Shinya

doi:10.3390/diagnostics11091629

Cited by 8 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bermudez and other researchers [ 18 ] trained a GAN to synthesize new T1-weighted brain MRIs with high quality compared to that of real images. In the paper by Gomi and others [ 17 ], the authors showed that GAN-based networks could achieve promising results in LDCT denoising. GANs were also used to generate more training data.…”

Section: Methodsmentioning

confidence: 99%

“…There is an increasing amount of researches on GANs, with each iteration making further progress [ 14 , 15 ]. Due to the excellent performance of GANs on natural image synthesis, GANs were introduced to perform various medical imaging tasks including solving problems associated with data imbalance of virtual STIR images [ 16 ], reducing metal artifacts and the radiation dose during digital tomosynthesis [ 17 ], as well as helping to process medical image [ 18 , 19 ]. Although neural networks and GANs were used to extract strain images from radio frequency data [ 20 , 21 ], and generate shear wave elastography images [ 22 ], we attempted to directly map conventional ultrasound images towards the corresponding strain elastography (SE) images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network

et al. 2022

View full text Add to dashboard Cite

Problem: Ultrasonography is recommended as the first choice for evaluation of thyroid nodules, however, conventional ultrasound features may not be able to adequately predict malignancy. Ultrasound elastography, adjunct to conventional B-mode ultrasound, can effectively improve the diagnostic accuracy of thyroid nodules. However, this technology requires professional elastography equipment and experienced physicians. Aim: in the field of computational medicine, Generative Adversarial Networks (GANs) were proven to be a powerful tool for generating high-quality images. This work therefore utilizes GANs to generate ultrasound elastography images. Methods: this paper proposes a new automated generation method of ultrasound elastography (AUE-net) to generate elastography images from conventional ultrasound images. The AUE-net was based on the U-Net architecture and optimized by attention modules and feature residual blocks, which could improve the adaptability of feature extraction for nodules of different sizes. The additional color loss function was used to balance color distribution. In this network, we first attempted to extract the tissue features of the ultrasound image in the latent space, then converted the attributes by modeling the strain, and finally reconstructed them into the corresponding elastography image. Results: a total of 726 thyroid ultrasound elastography images with corresponding conventional images from 397 patients were obtained between 2019 and 2021 as the dataset (646 in training set and 80 in testing set). The mean rating accuracy of the AUE-net generated elastography images by ultrasound specialists was 84.38%. Compared with that of the existing models in the visual aspect, the presented model generated relatively higher quality elastography images. Conclusion: the AUE-net generated ultrasound elastography images showed natural appearance and retained tissue information. Accordingly, it seems that B-mode ultrasound harbors information that can link to tissue elasticity. This study may pave the way to generate ultrasound elastography images readily without the need for professional equipment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The most recent advance in DT is the application of a deep learning program to achieve more advanced metal artifact reduction. Gomi et al reported a novel projection-based cross-domain learning framework for MAR [ 27 ]. They used the novel algorithm and successfully reduced metal artifacts more than with conventional TMAR algorithms.…”

Section: Metal Artifact Reduction Strategiesmentioning

confidence: 99%

Advances in Bone Joint Imaging-Metal Artifact Reduction

et al. 2022

View full text Add to dashboard Cite

Numerous types of metal implants have been introduced in orthopedic surgery and are used in everyday practice. To precisely evaluate the postoperative condition of arthroplasty or trauma surgery, periprosthetic infection, and the loosening of implants, it is important to reduce artifacts induced by metal implants. In this review, we focused on technical advances in metal artifact reduction using digital tomosynthesis, computed tomography, and magnetic resonance imaging. We discussed new developments in diagnostic imaging methods and the continuous introduction of novel technologies to reduce metal artifacts; however, these innovations have not yet completely removed metal artifacts. Different algorithms need to be selected depending on the size, shape, material and implanted body parts of an implant. Future advances in metal artifact reduction algorithms and techniques and the development of new sequences may enable further reductions in metal artifacts even on original images taken previously. Moreover, the combination of different imaging modalities may contribute to further reductions in metal artifacts. Clinicians must constantly update their knowledge and work closely with radiologists to select the best diagnostic imaging method for each metal implant.

show abstract

“…In the accelerating evolution of deep learning, the transition from a convolutional neural network [ 24 ] to a generative adversarial network (GAN) [ 25 , 26 ] has contributed to digital tomosynthesis imaging [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]. Prior studies reported that GANs are particularly useful for reducing metal artifacts [ 29 , 30 ] and noise [ 27 ] and are expected to contribute to improvements in image quality processes to reduce the exposure dose. Some studies have recently reported the usefulness of deep learning to improve image quality and reduce noise in tomosynthesis [ 27 , 29 ].…”

Section: Introductionmentioning

confidence: 99%

“…Some studies have recently reported the usefulness of deep learning to improve image quality and reduce noise in tomosynthesis [ 27 , 29 ]. Noise and radiation-dose reductions using deep learning for digital tomosynthesis of the breast and metal artifact reduction are possible [ 27 , 30 ]. Thus, application of deep learning can be used to improve image quality further and reduce the radiation-dose.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of a Generative Adversarial Network to Improve Image Quality and Reduce Radiation-Dose during Digital Breast Tomosynthesis

et al. 2022

Self Cite

View full text Add to dashboard Cite

In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre-reconstruction processing with filtered back projection (FBP) was compared with and without multiscale bilateral filtering (MSBF) during pre-reconstruction processing. Noise reduction and preserve contrast rates were compared using full width at half-maximum (FWHM), contrast-to-noise ratio (CNR), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) in the in-focus plane using a BR3D phantom at various radiation doses [reference-dose (automatic exposure control reference dose: AECrd), 50% and 75% reduction of AECrd] and phantom thicknesses (40 mm, 50 mm, and 60 mm). The overall performance of pix2pix pre-reconstruction processing was effective in terms of FWHM, PSNR, and SSIM. At ~50% radiation-dose reduction, FWHM yielded good results independently of the microcalcification size used in the BR3D phantom, and good noise reduction and preserved contrast. PSNR results showed that pix2pix pre-reconstruction processing represented the minimum in the error with reference FBP images at an approximately 50% reduction in radiation-dose. SSIM analysis indicated that pix2pix pre-reconstruction processing yielded superior similarity when compared with and without MSBF pre-reconstruction processing at ~50% radiation-dose reduction, with features most similar to the reference FBP images. Thus, pix2pix pre-reconstruction processing is promising for reducing noise with preserve contrast and radiation-dose reduction in clinical practice.

show abstract

Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks

Cited by 8 publications

References 35 publications

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network

Advances in Bone Joint Imaging-Metal Artifact Reduction

Evaluation of a Generative Adversarial Network to Improve Image Quality and Reduce Radiation-Dose during Digital Breast Tomosynthesis

Contact Info

Product

Resources

About