Is the generalizability of a developed artificial intelligence algorithm for COVID-19 on chest CT sufficient for clinical use? Results from the International Consortium for COVID-19 Imaging AI (ICOVAI) - Takeaways - MDSpire

Is the generalizability of a developed artificial intelligence algorithm for COVID-19 on chest CT sufficient for clinical use? Results from the International Consortium for COVID-19 Imaging AI (ICOVAI)

  • By

  • Laurens Topff

  • Kevin B. W. Groot Lipman

  • Frederic Guffens

  • Rianne Wittenberg

  • Annemarieke Bartels-Rutten

  • Gerben van Veenendaal

  • Mirco Hess

  • Kay Lamerigts

  • Joris Wakkie

  • Erik Ranschaert

  • Stefano Trebeschi

  • Jacob J. Visser

  • Regina G. H. Beets-Tan

  • January 18, 2023

  • 0 min

Share

  • 1

    The ICOVAI consortium developed an AI model for COVID-19 segmentation and CO-RADS classification using a multicenter dataset of 1286 chest CT scans.

  • 2

    Automated segmentation of lung abnormalities can enhance clinical workflow by providing timely quantitative analysis and CO-RADS classification.

  • 3

    External validation of AI models is crucial, as only 22% of reviewed studies on COVID-19 imaging completed this step, raising concerns about generalizability.

  • 4

    The study included a diverse cohort, with 375 CT scans used for external validation, ensuring a robust evaluation of the AI model's performance.

  • 5

    The ICOVAI model aims to improve diagnostic accuracy and efficiency in interpreting chest CT scans for COVID-19, addressing labor-intensive manual processes.

Original Source(s)

Is the generalizability of a developed artificial intelligence algorithm for COVID-19 on chest CT sufficient for clinical use? Results from the International Consortium for COVID-19 Imaging AI (ICOVAI)

  • by Laurens Topff, Kevin B. W. Groot Lipman, Frederic Guffens, Rianne Wittenberg, Annemarieke Bartels-Rutten, Gerben van Veenendaal, Mirco Hess, Kay Lamerigts, Joris Wakkie, Erik Ranschaert, Stefano Trebeschi, Jacob J. Visser, Regina G. H. Beets-Tan

  • January 18, 2023

Related Content

CT Use May Add to Future Cancer Burden

Researchers projected approximately 103,000 future cancers associated with computed tomography examinations performed in the US in 2023.

Dual-energy and perfusion CT for predicting response to chemo-radiotherapy in head and neck cancer: an exploratory study

AI Model May Help Decipher Malignant, Benign Breast Lesions on MRI

Model matches deep-learning accuracy and helps physicians reclassify benign breast lesions.