Isabella Castiglioni1,2, Davide Ippolito3, Matteo Interlenghi2, Caterina Beatrice Monti4, Christian Salvatore5,6, Simone Schiaffino7, Annalisa Polidori8, Davide Gandola3, Cristina Messa9,10, Francesco Sardanelli4,7. 1. Department of Physics, Università degli Studi di Milano-Bicocca, Piazza della Scienza 3, 20126, Milan, Italy. 2. Institute of Biomedical Imaging and Physiology, National Research Council, 20090, Segrate, Milan, Italy. 3. Department of Radiology, San Gerardo Hospital, Via Pergolesi 33, 20900, Monza, Italy. 4. Department of Biomedical Sciences for Health, Università degli Studi di Milano, Via Mangiagalli 31, 20133, Milan, Italy. 5. Scuola Universitaria Superiore IUSS Pavia, Piazza della Vittoria 15, 27100, Pavia, Italy. salvatore@deeptracetech.com. 6. DeepTrace Technologies S.R.L., Via Conservatorio 17, 20122, Milan, Italy. salvatore@deeptracetech.com. 7. Department of Radiology, IRCCS Policlinico San Donato, Via Morandi 30, 20097, San Donato Milanese, Milan, Italy. 8. DeepTrace Technologies S.R.L., Via Conservatorio 17, 20122, Milan, Italy. 9. School of Medicine and Surgery, University of Milano-Bicocca, Piazza dell'Ateneo Nuovo 1, 20126, Milan, Italy. 10. Fondazione Tecnomed, Università degli Studi di Milano-Bicocca, Palazzina Ciclotrone, Via Pergolesi 33, 20900, Monza, Italy.
Abstract
BACKGROUND: We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. METHODS: We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19 patients. Real-time polymerase chain reaction served as the reference standard. RESULTS: At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19 patients with 0.78 sensitivity (95% confidence interval [CI] 0.74-0.81), 0.82 specificity (95% CI 0.78-0.85), and 0.89 area under the curve (AUC) (95% CI 0.86-0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72-0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73-0.87), and 0.81 AUC (95% CI 0.73-0.87). Radiologists' reading obtained 0.63 sensitivity (95% CI 0.52-0.74) and 0.78 specificity (95% CI 0.61-0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52-0.74) and 0.86 specificity (95% CI 0.71-0.95) in Centre 2. CONCLUSIONS: This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.
BACKGROUND: We aimed to train and test a deep learning classifier to support the diagnosis of coronavirus disease 2019 (COVID-19) using chest x-ray (CXR) on a cohort of subjects from two hospitals in Lombardy, Italy. METHODS: We used for training and validation an ensemble of ten convolutional neural networks (CNNs) with mainly bedside CXRs of 250 COVID-19 and 250 non-COVID-19 subjects from two hospitals (Centres 1 and 2). We then tested such system on bedside CXRs of an independent group of 110 patients (74 COVID-19, 36 non-COVID-19) from one of the two hospitals. A retrospective reading was performed by two radiologists in the absence of any clinical information, with the aim to differentiate COVID-19 from non-COVID-19patients. Real-time polymerase chain reaction served as the reference standard. RESULTS: At 10-fold cross-validation, our deep learning model classified COVID-19 and non-COVID-19patients with 0.78 sensitivity (95% confidence interval [CI] 0.74-0.81), 0.82 specificity (95% CI 0.78-0.85), and 0.89 area under the curve (AUC) (95% CI 0.86-0.91). For the independent dataset, deep learning showed 0.80 sensitivity (95% CI 0.72-0.86) (59/74), 0.81 specificity (29/36) (95% CI 0.73-0.87), and 0.81 AUC (95% CI 0.73-0.87). Radiologists' reading obtained 0.63 sensitivity (95% CI 0.52-0.74) and 0.78 specificity (95% CI 0.61-0.90) in Centre 1 and 0.64 sensitivity (95% CI 0.52-0.74) and 0.86 specificity (95% CI 0.71-0.95) in Centre 2. CONCLUSIONS: This preliminary experience based on ten CNNs trained on a limited training dataset shows an interesting potential of deep learning for COVID-19 diagnosis. Such tool is in training with new CXRs to further increase its performance.
Authors: Carlos Roberto Ribeiro Carvalho; Rodrigo Caruso Chate; Marcio Valente Yamada Sawamura; Michelle Louvaes Garcia; Celina Almeida Lamas; Diego Armando Cardona Cardenas; Daniel Mario Lima; Paula Gobi Scudeller; João Marcos Salge; Cesar Higa Nomura; Marco Antonio Gutierrez Journal: BMJ Open Date: 2022-06-13 Impact factor: 3.006
Authors: Kaoutar Ben Ahmed; Gregory M Goldgof; Rahul Paul; Dmitry B Goldgof; Lawrence O Hall Journal: IEEE Access Date: 2021-05-13 Impact factor: 3.367
Authors: Osama Shahid; Mohammad Nasajpour; Seyedamin Pouriyeh; Reza M Parizi; Meng Han; Maria Valero; Fangyu Li; Mohammed Aledhari; Quan Z Sheng Journal: J Biomed Inform Date: 2021-03-24 Impact factor: 8.000