Your browser doesn't support javascript.
Effective deep learning approaches for predicting COVID-19 outcomes from chest computed tomography volumes.
Ortiz, Anthony; Trivedi, Anusua; Desbiens, Jocelyn; Blazes, Marian; Robinson, Caleb; Gupta, Sunil; Dodhia, Rahul; Bhatraju, Pavan K; Liles, W Conrad; Lee, Aaron; Ferres, Juan M Lavista.
  • Ortiz A; AI for Good Research Lab, Microsoft, Seattle, WA, USA.
  • Trivedi A; AI for Good Research Lab, Microsoft, Seattle, WA, USA.
  • Desbiens J; Intelligent Retinal Imaging Systems, Pensacola, FL, USA.
  • Blazes M; Department of Ophthalmology, University of Washington, Seattle, WA, USA.
  • Robinson C; AI for Good Research Lab, Microsoft, Seattle, WA, USA.
  • Gupta S; Intelligent Retinal Imaging Systems, Pensacola, FL, USA.
  • Dodhia R; AI for Good Research Lab, Microsoft, Seattle, WA, USA.
  • Bhatraju PK; Department of Medicine and Sepsis Center of Research Excellence, University of Washington (SCORE-UW), Seattle, WA, USA.
  • Liles WC; Department of Medicine and Sepsis Center of Research Excellence, University of Washington (SCORE-UW), Seattle, WA, USA.
  • Lee A; Department of Ophthalmology, University of Washington, Seattle, WA, USA. leeay@uw.edu.
  • Ferres JML; AI for Good Research Lab, Microsoft, Seattle, WA, USA. jlavista@microsoft.com.
Sci Rep ; 12(1): 1716, 2022 02 02.
Article in English | MEDLINE | ID: covidwho-1900583
ABSTRACT
The rapid evolution of the novel coronavirus disease (COVID-19) pandemic has resulted in an urgent need for effective clinical tools to reduce transmission and manage severe illness. Numerous teams are quickly developing artificial intelligence approaches to these problems, including using deep learning to predict COVID-19 diagnosis and prognosis from chest computed tomography (CT) imaging data. In this work, we assess the value of aggregated chest CT data for COVID-19 prognosis compared to clinical metadata alone. We develop a novel patient-level algorithm to aggregate the chest CT volume into a 2D representation that can be easily integrated with clinical metadata to distinguish COVID-19 pneumonia from chest CT volumes from healthy participants and participants with other viral pneumonia. Furthermore, we present a multitask model for joint segmentation of different classes of pulmonary lesions present in COVID-19 infected lungs that can outperform individual segmentation models for each task. We directly compare this multitask segmentation approach to combining feature-agnostic volumetric CT classification feature maps with clinical metadata for predicting mortality. We show that the combination of features derived from the chest CT volumes improve the AUC performance to 0.80 from the 0.52 obtained by using patients' clinical data alone. These approaches enable the automated extraction of clinically relevant features from chest CT volumes for risk stratification of COVID-19 patients.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Thorax / Tomography, X-Ray Computed / Deep Learning / SARS-CoV-2 / COVID-19 Type of study: Diagnostic study / Experimental Studies / Prognostic study Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-05532-0

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Thorax / Tomography, X-Ray Computed / Deep Learning / SARS-CoV-2 / COVID-19 Type of study: Diagnostic study / Experimental Studies / Prognostic study Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-05532-0