Id: 3523524 Data Augmentation Using Generative Adversarial Networks for Creating Realistic Artificial Colon Polyp Images: Validation Study by Endoscopists

Thambawita, Vajira; Strümke, Inga; Hicks, Steven A.; Riegler, Michael; Halvorsen, Pål; Parasa, Sravanthi

doi:10.1016/j.gie.2021.03.431

Cited by 8 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, to address the costly and time-consuming expert's data annotation process, we experimented and introduced novel pipelines [75] of GAN architectures using GI-tract dataset to generate synthetic polyp data from the clean colon to overcome data imbalance problems in the medical domain, such as having more truenegative samples compared to true positive samples. Furthermore, we researched and presented a new pipeline to generate synthetic polyp data with the corresponding mask from a single polyp image [67], namely SinGAN-Seg, and showed that generated synthetic medical data is a solution to overcome data problems in the medical domain.…”

Section: Contributionsmentioning

confidence: 99%

“…Good knowledge about the state-of-the-art GANs methods is important for finding a better GAN model for generating synthetic data. In this thesis, novel GANs [70,75,67] and modified versions of different GAN architectures [72,73,74,76] were researched and developed. More details about these GANs are presented in Chapter 3.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

“…[74] Generate synthetic video frames A GAN architecture named Vid2pix with a 3D CNN were investigated to generate synthetic Pilcam video frames [27] for time step t + 1 conditioning on time steps t, t − 1, t − 2. [67,75] Generate synthetic images with corresponding ground truth mask GAN architectures were experimented to generate synthetic polyp images and corresponding ground truth mask as proof of concepts to solve privacy issues and medical data annotation cost problem. [76] Generate synthetic painting to sperm video frames A GAN model was experimented to generate a painting like spots instead of sperms in a sperm video frame.…”

Section: Generating Synthetic Electrocardiogram Signalsmentioning

confidence: 99%

“…Another three advanced GAN architectures were investigated with the HyperKvasir dataset after the foundation analysis from preliminary studies [72,73,74]. These three studies, namely GI-StyleGAN [71], SinGAN-polyp-augmentation [67], and Polyp-inpainting [75],…”

Section: Generating Synthetic Gastrointestinal-tract Imagesmentioning

confidence: 99%

“…After training with the clean colon data, the model was retrained using polyp data and Steps of the polyp inpainting training process as discussed in [75]. Generative multi-column convolutional neural networks (GMCNN) [197] is the core network in this process.…”

Section: Generating Synthetic Gastrointestinal-tract Imagesmentioning

confidence: 99%

See 4 more Smart Citations

DeepSynthBody: the beginning of the end for data deficiency in medicine

Thambawita

Hicks

Isaksen

et al. 2021

2021 International Conference on Applied Artificial Intelligence (ICAPAI)

Self Cite

View full text Add to dashboard Cite

Hammer, for their support, motivation, and always behind me. Without them, this would be only a dream. After joining the HOST department as a Ph.D. candidate in 2018, I started experiencing a completely new environment with new people from different countries and cultures.Michael Riegler became my principal supervisor. I did not know anything about him despite his academic background. However, after few weeks, I realized that he is more than my principal supervisor for my life. Within few months, he became a game-changer in my life. I do not have words to express his qualities and how his advice, encouragement, kindness, and motivations are important to my life. Therefore, I would like to give my most enormous thanks to my primary supervisor, Michael, who is always behind me to support my academic life and get advice for my personal life.Pål Halvorsen is the department head and one of my co-supervisors, and he is a very kind person supporting us always silently. His advice and encouragements make me better and better every day in my academic life. Then, I would like to thank Pål for his kindness showed me through my Ph.D. journey and the wordless help given to me. Hugo Hammer is my second co-supervisor who supports me in handling advanced statistical problems in my Ph.D. research. Then, I would like to thank Hugo for his friendly help, as always.The research has benefited from the Experimental Infrastructure for Exploration of Exascale Computing (eX3), which the Research Council of Norway financially supports under contract 270053. Tore was the person who helped me to use these infrastructures.So, I would like to give my special thanks to him for his outstanding support.I also would like to thank the closest colleague, Steven Hicks, a good friend met within the department and in my life. Moreover, I thank all the other colleagues, Debesh, Hanna, Pia, Hakon, and Daniel, who work closely in my Ph.D. periods. There are more people v I want to thank, but writing them all here is not possible. However, they all are equally important for me, and therefore I would like to thank them all equally. Master students, other Ph.D. students from different departments and other counties, all the co-authors, and persons who are from the administration are a few of them.Finally, I would like to thank my wife, Shalike, who sacrificed the freedom of her life for finishing my Ph.D. successfully. Not only that, she always provided me food and other necessary stuff without asking anything from me. Last but not least, I would like to give my thanks to my parents, who sacrificed their whole life to provide us a good life while facing a challenging lifestyle in my country,

show abstract

Section: Contributionsmentioning

confidence: 99%