Synthetic Datasets: Opportunities for Development оf Medical Artificial Intelligence Products

Capa

Citar

Texto integral

Resumo

Currently, intelligent solutions and artificial intelligence products are being intensively developed for various areas of life, including healthcare. Process of creating and implementing medical AI products is a time-consuming and costly process. The authors of the article consider the potential possibility of accelerating the development and implementation of medical AI products, primarily due to a new solution - the synthetic datasets. The key factors associated with the training datasets collecting are analyzed, including synthetic ones that shorten the development time and improve the quality of products AI based technology.

Texto integral

Acesso é fechado

Sobre autores

Dmitry Shamaev

Resource Center for Universal Design and Rehabilitation Technologies

Autor responsável pela correspondência
Email: shamaev.dmitry@yandex.ru

Candidate of technical sciences. Researcher

Rússia, Moscow

Vitaliy Zayats

Resource Center for Universal Design and Rehabilitation Technologies

Email: vvzayats@rcud-rt.ru

Candidate of medical sciences, docent. Director

Rússia, Moscow

Sergey Orlov

Resource Center for Universal Design and Rehabilitation Technologies

Email: SBOrlov@rcud-rt.ru

Head of Design and Methodological Department

Rússia, Moscow

Albert Shirinyan

Resource Center for Universal Design and Rehabilitation Technologies

Email: aashirinyan@rcud-rt.ru

Programmer-Researcher

Rússia, Moscow

Bibliografia

  1. The 4 Trends That Prevail on the Gartner Hype Cycle for AI, 2021 Available at: https://www.gartner.com/en/articles/the-4-trends-that-prevail-on-the-gartner-hype-cycle-for-ai-2021,accessed September 15, 2022.
  2. ImageNet homepage Available at: https://image-net.org, accessed September 15, 2022.
  3. Kak iskusstvennyj intellekt primenyayut v rabote s grafikoj [How artificial intelligence is used in working with graphics] Available at: https://dtf.ru/promo/688429-msi-creator,accessed September 15, 2022.
  4. Khan S.M. et al. A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalizability // Lancet Digit Health. 2021. 3(1). P.51-66.
  5. Shin, H., A.Neil, T. Jameson, K. Rogers at al. Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks, SASHIMI 2018, LNCS 11037. Р. 1–11.
  6. Edinyj radiologicheskij informacionnyj servis [Unified Radiological information service]Available at: https://tele-med.ai/proekty/edinyj-radiologicheskij-informacionnyj-servis_2020,accessed September 15, 2022.
  7. Besplatnaya Onlajn-konferenciya Data Science, mashinnoe obuchenie i nejroseti [Free Online Conference Data Science, Machine learning and Neural networks] Available at: https://datastart.ru, accessed September 15, 2022.
  8. Tran N.H., Zhang X., Li M. Deep Omics // Proteomics. 2018. 18. doi: 10.1002/pmic.201700319.
  9. Lemley J., S. Bazrafkan, P. Corcoran Smart Augmentation - Learning an Optimal Data Augmentation Strategy, IEEE Access(5). Р.5858 – 5869.
  10. Shin R., N. Kant, K. Gupta, C. M. Bender at al. Synthetic Datasets for Neural Program Synthesis, 2019.
  11. Wolterink J. M, A, Mukhopadhyay, T. Leiner et al. Generative Adversarial Networks: A Primer for Radiologists, Radiographics. May-Jun 2021; 41(3). Р.840-857.
  12. Sorin V., Y. Barash, E. Konen et al. Creating Artificial Images for Radiology Applications Using Generative Adversarial Networks (GANs) - A Systematic Review, 2020 Aug;27(8). Р.1175-1185.
  13. Zheng C., X. Xie, K. Zhou et al. Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders, 2020 May 27;9(2):29.
  14. You A., J. K. Kim, I. H. Ryu el al. Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey, Eye and Vision.2022. 9:6.
  15. Wang Y. A Mathematical Introduction to Generative Adversarial Nets (GAN), Computer Science. 2020 (1).
  16. Arjovsky M., S. Chintala, L. Bottou, Wasserstein GAN 2017 Machine Learning (stat.ML).
  17. Quang T., M. Pham, S. Ahn a, J. Shin et al. Generating future fundus images for early age-related macular degeneration based on generative adversarial networks, Computer Methods and Programs in Biomedicine 216.2022.106648 р.
  18. Burlina P, N. Joshi, W. Paul, K.D. Pacheco, N.M. Bressler. Addressing artificial intelligence bias in retinal diagnostics. Trans Vis Sci Tech. 2021;10(2):13.
  19. Zheng C, X. Xie, K. Zhou, B. Chen, J. et al. Assessment of generative adversarial networks model for synthetic optical coherence tomography images of retinal disorders. Trans Vis Sci Tech. 2020; 9(2):29.
  20. Danesh H., K. Maghooli, A. Dehghani et al. Synthetic OCT data in challenging conditions: three-dimensional OCT and presence of abnormalities. Medical & Biological Engineering & Computing (2022) 60. Р.189–203.
  21. Finlayson S. G., A. Subbaswamy, K. Singh et al. The Clinician and Dataset Shift in Artificial Intelligence, N Engl J Med. 2021 July 15; 385(3). Р. 283–286.
  22. Hsu Sh., Y. Cao, K. Huang, M. Feng et al. Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy, Phys. Med. Biol. 58. 2013. Р.8419–8435.
  23. Magn J. Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI, Reson Imaging. 2019 April; 49(4). Р.939–954.

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar
2. Fig. 1. Gartner's AI technology timeline

Baixar (530KB)
Metadados

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).