A collaborative online AI engine for CT-based COVID-19 diagnosis

  1. Yongchao Xu
  2. Liya Ma
  3. Fan Yang
  4. Yanyan Chen
  5. Ke Ma
  6. Jiehua Yang
  7. Xian Yang
  8. Yaobing Chen
  9. Chang Shu
  10. Ziwei Fan
  11. Jiefeng Gan
  12. Xinyu Zou
  13. Renhao Huang
  14. Changzheng Zhang
  15. Xiaowu Liu
  16. Dandan Tu
  17. Chuou Xu
  18. Wenqing Zhang
  19. Dehua Yang
  20. Ming-Wei Wang
  21. Xi Wang
  22. Xiaoliang Xie
  23. Hongxiang Leng
  24. Nagaraj Holalkere
  25. Neil J. Halin
  26. Ihab Roushdy Kamel
  27. Jia Wu
  28. Xuehua Peng
  29. Xiang Wang
  30. Jianbo Shao
  31. Pattanasak Mongkolwat
  32. Jianjun Zhang
  33. Daniel L. Rubin
  34. Guoping Wang
  35. Chuangsheng Zheng
  36. Zhen Li
  37. Xiang Bai
  38. Tian Xia

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Artificial intelligence can potentially provide a substantial role in streamlining chest computed tomography (CT) diagnosis of COVID-19 patients. However, several critical hurdles have impeded the development of robust AI model, which include deficiency, isolation, and heterogeneity of CT data generated from diverse institutions. These bring about lack of generalization of AI model and therefore prevent it from applications in clinical practices. To overcome this, we proposed a federated learning-based Unified CT-COVID AI Diagnostic Initiative (UCADI, http://www.ai-ct-covid.team/ ), a decentralized architecture where the AI model is distributed to and executed at each host institution with the data sources or client ends for training and inferencing without sharing individual patient data. Specifically, we firstly developed an initial AI CT model based on data collected from three Tongji hospitals in Wuhan. After model evaluation, we found that the initial model can identify COVID from Tongji CT test data at near radiologist-level (97.5% sensitivity) but performed worse when it was tested on COVID cases from Wuhan Union Hospital (72% sensitivity), indicating a lack of model generalization. Next, we used the publicly available UCADI framework to build a federated model which integrated COVID CT cases from the Tongji hospitals and Wuhan Union hospital (WU) without transferring the WU data. The federated model not only performed similarly on Tongji test data but improved the detection sensitivity (98%) on WU test cases. The UCADI framework will allow participants worldwide to use and contribute to the model, to deliver a real-world, globally built and validated clinic CT-COVID AI tool. This effort directly supports the United Nations Sustainable Development Goals’ number 3, Good Health and Well-Being, and allows sharing and transferring of knowledge to fight this devastating disease around the world.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.05.10.20096073: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: Thank you for sharing your code.

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.05.10.20096073v2 on medRxiv
  3. Version published to 10.1101/2020.05.10.20096073v1 on medRxiv