Your browser doesn't support javascript.
An externally validated fully automated deep learning algorithm to classify COVID-19 and other pneumonias on chest computed tomography.
Vaidyanathan, Akshayaa; Guiot, Julien; Zerka, Fadila; Belmans, Flore; Van Peufflik, Ingrid; Deprez, Louis; Danthine, Denis; Canivet, Gregory; Lambin, Philippe; Walsh, Sean; Occhipinti, Mariaelena; Meunier, Paul; Vos, Wim; Lovinfosse, Pierre; Leijenaar, Ralph T H.
  • Vaidyanathan A; Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Guiot J; The D-Lab, Depts of Precision Medicine, and Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands.
  • Zerka F; These authors have contributed equally to this work and share first authorship.
  • Belmans F; Dept of Pneumology, University Hospital of Liège, Liège, Belgium.
  • Van Peufflik I; These authors have contributed equally to this work and share first authorship.
  • Deprez L; Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Danthine D; The D-Lab, Depts of Precision Medicine, and Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands.
  • Canivet G; Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Lambin P; Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Walsh S; Dept of Radiology, University Hospital of Liège, Liège, Belgium.
  • Occhipinti M; Dept of Radiology, University Hospital of Liège, Liège, Belgium.
  • Meunier P; Dept of Computer Applications, University Hospital of Liège, Liège, Belgium.
  • Vos W; The D-Lab, Depts of Precision Medicine, and Radiology and Nuclear Medicine, GROW-School for Oncology, Maastricht University, Maastricht, The Netherlands.
  • Lovinfosse P; Radiomics (Oncoradiomics SA), Liège, Belgium.
  • Leijenaar RTH; Radiomics (Oncoradiomics SA), Liège, Belgium.
ERJ Open Res ; 8(2)2022 Apr.
Article in English | MEDLINE | ID: covidwho-1833277
ABSTRACT

Purpose:

In this study, we propose an artificial intelligence (AI) framework based on three-dimensional convolutional neural networks to classify computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19), influenza/community-acquired pneumonia (CAP), and no infection, after automatic segmentation of the lungs and lung abnormalities.

Methods:

The AI classification model is based on inflated three-dimensional Inception architecture and was trained and validated on retrospective data of CT images of 667 adult patients (no infection n=188, COVID-19 n=230, influenza/CAP n=249) and 210 adult patients (no infection n=70, COVID-19 n=70, influenza/CAP n=70), respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients (no infection n=55, COVID-19 n= 94, influenza/CAP n=124) and an external validation set from a different centre (305 adult patients COVID-19 n=169, no infection n=76, influenza/CAP n=60).

Results:

The model showed excellent performance in the external validation set with area under the curve of 0.90, 0.92 and 0.92 for COVID-19, influenza/CAP and no infection, respectively. The selection of the input slices based on automatic segmentation of the abnormalities in the lung reduces analysis time (56 s per scan) and computational burden of the model. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score of the proposed model is 47% (15 out of 32 TRIPOD items).

Conclusion:

This AI solution provides rapid and accurate diagnosis in patients suspected of COVID-19 infection and influenza.

Full text: Available Collection: International databases Database: MEDLINE Type of study: Experimental Studies / Observational study / Prognostic study Language: English Year: 2022 Document Type: Article Affiliation country: 23120541.00579-2021

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Type of study: Experimental Studies / Observational study / Prognostic study Language: English Year: 2022 Document Type: Article Affiliation country: 23120541.00579-2021