Radiation-Induced Pneumonitis in the Era of the COVID-19 Pandemic: Artificial Intelligence for Differential Diagnosis

(1) Aim: To test the performance of a deep learning algorithm in discriminating radiation therapy-related pneumonitis (RP) from COVID-19 pneumonia. (2) Methods: In this retrospective study, we enrolled three groups of subjects: pneumonia-free (control group), COVID-19 pneumonia and RP patients. CT i...

Full description

Saved in:
Bibliographic Details
Published in:Cancers 2021-04, Vol.13 (8), p.1960
Main Authors: Giordano, Francesco Maria, Ippolito, Edy, Quattrocchi, Carlo Cosimo, Greco, Carlo, Mallio, Carlo Augusto, Santo, Bianca, D'Alessio, Pasquale, Crucitti, Pierfilippo, Fiore, Michele, Zobel, Bruno Beomonte, D'Angelillo, Rolando Maria, Ramella, Sara
Format: Article
Language:English
Subjects:
Algorithms
Apoptosis
Artificial intelligence
Cancer therapies
Coronaviruses
COVID-19
Deep learning
Differential diagnosis
Dyspnea
Fever
Hospitals
Lung cancer
Medical imaging
Neural networks
Pandemics
Patients
Pneumonia
Pneumonitis
Radiation therapy
Severe acute respiratory syndrome coronavirus 2
Statistical analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:(1) Aim: To test the performance of a deep learning algorithm in discriminating radiation therapy-related pneumonitis (RP) from COVID-19 pneumonia. (2) Methods: In this retrospective study, we enrolled three groups of subjects: pneumonia-free (control group), COVID-19 pneumonia and RP patients. CT images were analyzed by mean of an artificial intelligence (AI) algorithm based on a novel deep convolutional neural network structure. The cut-off value of risk probability of COVID-19 was 30%; values higher than 30% were classified as COVID-19 High Risk, and values below 30% as COVID-19 Low Risk. The statistical analysis included the Mann-Whitney U test (significance threshold at < 0.05) and receiver operating characteristic (ROC) curve, with fitting performed using the maximum likelihood fit of a binormal model. (3) Results: Most patients presenting RP (66.7%) were classified by the algorithm as COVID-19 Low Risk. The algorithm showed high sensitivity but low specificity in the detection of RP against COVID-19 pneumonia (sensitivity = 97.0%, specificity = 2%, area under the curve (AUC = 0.72). The specificity increased when an estimated COVID-19 risk probability cut-off of 30% was applied (sensitivity 76%, specificity 63%, AUC = 0.84). (4) Conclusions: The deep learning algorithm was able to discriminate RP from COVID-19 pneumonia, classifying most RP cases as COVID-19 Low Risk.
ISSN:2072-6694
2072-6694
DOI:10.3390/cancers13081960