Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images

Ju, Zhang; Yu, Lunduan; Chen, Decheng; Pan, Weidong; Shi, Chao; Yan, Ning; Yao, Xinwei; Xu, Xiaobin; Cao, Yun

doi:10.1016/j.bspc.2021.102901

Cited by 53 publications

(31 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As the diagnosis of COVID-19 using medical imaging has been a priority since the pandemic started, 39 (68%) of 57 studies reported the diagnosis of COVID-19 as the main focus of their work [ 19 - 21 , 23 - 33 , 35 - 37 , 39 , 41 , 42 , 44 , 46 , 50 , 52 , 53 , 55 , 56 , 58 - 60 , 63 - 69 , 71 , 72 ]. In addition, 9 (16%) studies reported data augmentation as the main task addressed in the work [ 18 , 43 , 45 , 49 , 54 , 61 , 62 ], 1 (2%) study reported prognosis of COVID-19 [ 22 ], 3 (5%) studies reported segmentation of lungs [ 34 , 51 , 57 ], and 1 (2%) study reported diagnosis of multiple lung diseases [ 47 ].…”

Section: Resultsmentioning

confidence: 99%

“…Of the 57 studies, only 10 (18%) [ 18 , 19 , 26 , 27 , 30 , 34 , 43 , 61 - 73 ] reported changes to the architecture of the GAN they were using. In the rest of the studies, no major changes were reported to the architecture of the GAN.…”

Section: Resultsmentioning

confidence: 99%

“…Specifically, the use of X-ray images dominated the studies. In total, 29 (51%) studies used X-ray images of lungs [ 20 , 21 , 25 , 27 - 29 , 31 , 32 , 35 , 37 , 40 - 43 , 45 , 50 , 52 , 54 , 56 , 57 , 59 , 60 , 62 , 64 , 65 , 67 , 70 , 73 , 74 ], while 21 (37%) studies used CT images [ 18 , 19 , 22 - 24 , 26 , 30 , 33 , 34 , 36 , 38 , 48 , 49 , 51 , 53 , 55 , 58 , 61 , 63 , 66 , 71 ], and 6 (11%) studies reported the use of both X-ray and CT images [ 39 , 44 , 46 , 47 , 68 , 72 ]. Only 1 (2%) study used ultrasound images for COVID-19 diagnosis [ 69 ], which shows that ultrasound is not a popular imaging modality for training GANs and other deep learning models for COVID-19 detection (also see Figure 4 ).…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Ali¹,

Shah²

2022

JMIR Med Inform

View full text Add to dashboard Cite

Background Research on the diagnosis of COVID-19 using lung images is limited by the scarcity of imaging data. Generative adversarial networks (GANs) are popular for synthesis and data augmentation. GANs have been explored for data augmentation to enhance the performance of artificial intelligence (AI) methods for the diagnosis of COVID-19 within lung computed tomography (CT) and X-ray images. However, the role of GANs in overcoming data scarcity for COVID-19 is not well understood. Objective This review presents a comprehensive study on the role of GANs in addressing the challenges related to COVID-19 data scarcity and diagnosis. It is the first review that summarizes different GAN methods and lung imaging data sets for COVID-19. It attempts to answer the questions related to applications of GANs, popular GAN architectures, frequently used image modalities, and the availability of source code. Methods A search was conducted on 5 databases, namely PubMed, IEEEXplore, Association for Computing Machinery (ACM) Digital Library, Scopus, and Google Scholar. The search was conducted from October 11-13, 2021. The search was conducted using intervention keywords, such as “generative adversarial networks” and “GANs,” and application keywords, such as “COVID-19” and “coronavirus.” The review was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines for systematic and scoping reviews. Only those studies were included that reported GAN-based methods for analyzing chest X-ray images, chest CT images, and chest ultrasound images. Any studies that used deep learning methods but did not use GANs were excluded. No restrictions were imposed on the country of publication, study design, or outcomes. Only those studies that were in English and were published from 2020 to 2022 were included. No studies before 2020 were included. Results This review included 57 full-text studies that reported the use of GANs for different applications in COVID-19 lung imaging data. Most of the studies (n=42, 74%) used GANs for data augmentation to enhance the performance of AI techniques for COVID-19 diagnosis. Other popular applications of GANs were segmentation of lungs and superresolution of lung images. The cycleGAN and the conditional GAN were the most commonly used architectures, used in 9 studies each. In addition, 29 (51%) studies used chest X-ray images, while 21 (37%) studies used CT images for the training of GANs. For the majority of the studies (n=47, 82%), the experiments were conducted and results were reported using publicly available data. A secondary evaluation of the results by radiologists/clinicians was reported by only 2 (4%) studies. Conclusions Studies have shown that GANs have great potential to address the data scarcity challenge for lung images in COVID-19. Data synthesized with GANs have been helpful to i...

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Ali¹,

Shah²

2022

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…Two types of data namely synthetic data and limited unlabeled CT images of COVID-19 were used to train this network. Authors in [26] have coped with this issue differently by using an improved dense generative adversarial network (GAN) to expand the existing dataset of COVID-19 images. However, it remains very challenging to achieve accurate segmentation of COVID-19 for several reasons.…”

Section: Related Workmentioning

confidence: 99%

A fast lightweight network for the discrimination of COVID-19 and pulmonary diseases

Aiadi

Khaldi

2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Among several generative models, Generative Adversarial Networks (GANs) [15] have gained the attention of medical image processing researchers. Recently, GANs were used in medical image (MI) generation [16,17], medical image editing in latent space [18], MI segmentation [19], and MI classification [20], because of their better performance among all generative models. A typical GAN consists of a generator (G) and a discriminator (D) network.…”

Section: Introductionmentioning

confidence: 99%

Improving Skin Cancer Classification Using Heavy-Tailed Student T-Distribution in Generative Adversarial Networks (TED-GAN)

et al. 2021

View full text Add to dashboard Cite

Deep learning has gained immense attention from researchers in medicine, especially in medical imaging. The main bottleneck is the unavailability of sufficiently large medical datasets required for the good performance of deep learning models. This paper proposes a new framework consisting of one variational autoencoder (VAE), two generative adversarial networks, and one auxiliary classifier to artificially generate realistic-looking skin lesion images and improve classification performance. We first train the encoder-decoder network to obtain the latent noise vector with the image manifold’s information and let the generative adversarial network sample the input from this informative noise vector in order to generate the skin lesion images. The use of informative noise allows the GAN to avoid mode collapse and creates faster convergence. To improve the diversity in the generated images, we use another GAN with an auxiliary classifier, which samples the noise vector from a heavy-tailed student t-distribution instead of a random noise Gaussian distribution. The proposed framework was named TED-GAN, with T from the t-distribution and ED from the encoder-decoder network which is part of the solution. The proposed framework could be used in a broad range of areas in medical imaging. We used it here to generate skin lesion images and have obtained an improved classification performance on the skin lesion classification task, rising from 66% average accuracy to 92.5%. The results show that TED-GAN has a better impact on the classification task because of its diverse range of generated images due to the use of a heavy-tailed t-distribution.

show abstract

Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images

Cited by 53 publications

References 27 publications

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review

A fast lightweight network for the discrimination of COVID-19 and pulmonary diseases

Improving Skin Cancer Classification Using Heavy-Tailed Student T-Distribution in Generative Adversarial Networks (TED-GAN)

Contact Info

Product

Resources

About