Unknown

Dataset Information

0

Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.


ABSTRACT: Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.

SUBMITTER: Harmon SA 

PROVIDER: S-EPMC7429815 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

altmetric image

Publications

Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.

Harmon Stephanie A SA   Sanford Thomas H TH   Xu Sheng S   Turkbey Evrim B EB   Roth Holger H   Xu Ziyue Z   Yang Dong D   Myronenko Andriy A   Anderson Victoria V   Amalou Amel A   Blain Maxime M   Kassin Michael M   Long Dilara D   Varble Nicole N   Walker Stephanie M SM   Bagci Ulas U   Ierardi Anna Maria AM   Stellato Elvira E   Plensich Guido Giovanni GG   Franceschelli Giuseppe G   Girlando Cristiano C   Irmici Giovanni G   Labella Dominic D   Hammoud Dima D   Malayeri Ashkan A   Jones Elizabeth E   Summers Ronald M RM   Choyke Peter L PL   Xu Daguang D   Flores Mona M   Tamura Kaku K   Obinata Hirofumi H   Mori Hitoshi H   Patella Francesca F   Cariati Maurizio M   Carrafiello Gianpaolo G   An Peng P   Wood Bradford J BJ   Turkbey Baris B  

Nature communications 20200814 1


Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8  ...[more]

Similar Datasets

| S-EPMC8516252 | biostudies-literature
| S-EPMC7674009 | biostudies-literature
| S-EPMC7465292 | biostudies-literature
| S-EPMC7816060 | biostudies-literature
| S-EPMC8659534 | biostudies-literature
| S-EPMC7934290 | biostudies-literature
| S-EPMC8049482 | biostudies-literature
| S-EPMC7233414 | biostudies-literature
| S-EPMC7233473 | biostudies-literature
| S-EPMC7537264 | biostudies-literature