Maxime Blain1, Michael T Kassin1, Nicole Varble2, Xiaosong Wang3, Ziyue Xu3, Daguang Xu1, Gianpaolo Carrafiello4, Valentina Vespro4, Elvira Stellato4, Anna Maria Ierardi4, Letizia Di Meglio4, Robert D Suh5, Stephanie A Walker6, Sheng Xu1, Thomas H Sanford7, Evrim B Turkbey8, Stephanie Harmon9, Baris Turkbey10, Bradford J Wood11. 1. Center for Interventional Oncology, National Institutes of Health Clinical Center and National Cancer Institute, Bethesda, Maryland, USA. 2. Philips Research North America, Cambridge, Massachusetts, USA. 3. NVIDIA Corporation, Bethesda, Maryland, USA. 4. Department of Radiology,Fondazione IRCCS Cà Granda Ospedale Maggiore Policlinico, University of Milan, Italy. 5. Department of Radiology, University of California Los Angeles, Los Angeles, California, USA. 6. National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA. 7. Center for Interventional Oncology, National Institutes of Health Clinical Center and National Cancer Institute, Bethesda, Maryland, USA;State University of New York Upstate Medical University, Syracuse, Newyork, USA. 8. Molecular Imaging Program, National Institutes of Health, Bethesda, Maryland, USA;Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, Mayland, USA. 9. National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA;Clinical Research Directorate, Frederick National Laboratory for Cancer Research, Frederick, Maryland, USA. 10. Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, Mayland, USA. 11. Center for Interventional Oncology, National Institutes of Health Clinical Center and National Cancer Institute, Bethesda, Maryland, USA;Department of Radiology, University of California Los Angeles, Los Angeles, California, USA;Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, Mayland, USA.
Abstract
PURPOSE: Chest X-ray plays a key role in diagnosis and management of COVID-19 patients and imaging features associated with clinical elements may assist with the development or validation of automated image analysis tools. We aimed to identify associations between clinical and radiographic features as well as to assess the feasibility of deep learning applied to chest X-rays in the setting of an acute COVID-19 outbreak. METHODS: A retrospective study of X-rays, clinical, and laboratory data was performed from 48 SARS-CoV-2 RT-PCR positive patients (age 60±17 years, 15 women) between February 22 and March 6, 2020 from a tertiary care hospital in Milan, Italy. Sixty-five chest X-rays were reviewed by two radiologists for alveolar and interstitial opacities and classified by severity on a scale from 0 to 3. Clinical factors (age, symptoms, comorbidities) were investigated for association with opacity severity and also with placement of central line or endotracheal tube. Deep learning models were then trained for two tasks: lung segmentation and opacity detection. Imaging characteristics were compared to clinical datapoints using the unpaired student's t-test or Mann-Whitney U test. Cohen's kappa analysis was used to evaluate the concordance of deep learning to conventional radiologist interpretation. RESULTS: Fifty-six percent of patients presented with alveolar opacities, 73% had interstitial opacities, and 23% had normal X-rays. The presence of alveolar or interstitial opacities was statistically correlated with age (P = 0.008) and comorbidities (P = 0.005). The extent of alveolar or interstitial opacities on baseline X-ray was significantly associated with the presence of endotracheal tube (P = 0.0008 and P = 0.049) or central line (P = 0.003 and P = 0.007). In comparison to human interpretation, the deep learning model achieved a kappa concordance of 0.51 for alveolar opacities and 0.71 for interstitial opacities. CONCLUSION: Chest X-ray analysis in an acute COVID-19 outbreak showed that the severity of opacities was associated with advanced age, comorbidities, as well as acuity of care. Artificial intelligence tools based upon deep learning of COVID-19 chest X-rays are feasible in the acute outbreak setting.
PURPOSE: Chest X-ray plays a key role in diagnosis and management of COVID-19patients and imaging features associated with clinical elements may assist with the development or validation of automated image analysis tools. We aimed to identify associations between clinical and radiographic features as well as to assess the feasibility of deep learning applied to chest X-rays in the setting of an acute COVID-19 outbreak. METHODS: A retrospective study of X-rays, clinical, and laboratory data was performed from 48 SARS-CoV-2 RT-PCR positive patients (age 60±17 years, 15 women) between February 22 and March 6, 2020 from a tertiary care hospital in Milan, Italy. Sixty-five chest X-rays were reviewed by two radiologists for alveolar and interstitial opacities and classified by severity on a scale from 0 to 3. Clinical factors (age, symptoms, comorbidities) were investigated for association with opacity severity and also with placement of central line or endotracheal tube. Deep learning models were then trained for two tasks: lung segmentation and opacity detection. Imaging characteristics were compared to clinical datapoints using the unpaired student's t-test or Mann-Whitney U test. Cohen's kappa analysis was used to evaluate the concordance of deep learning to conventional radiologist interpretation. RESULTS: Fifty-six percent of patients presented with alveolar opacities, 73% had interstitial opacities, and 23% had normal X-rays. The presence of alveolar or interstitial opacities was statistically correlated with age (P = 0.008) and comorbidities (P = 0.005). The extent of alveolar or interstitial opacities on baseline X-ray was significantly associated with the presence of endotracheal tube (P = 0.0008 and P = 0.049) or central line (P = 0.003 and P = 0.007). In comparison to human interpretation, the deep learning model achieved a kappa concordance of 0.51 for alveolar opacities and 0.71 for interstitial opacities. CONCLUSION: Chest X-ray analysis in an acute COVID-19 outbreak showed that the severity of opacities was associated with advanced age, comorbidities, as well as acuity of care. Artificial intelligence tools based upon deep learning of COVID-19 chest X-rays are feasible in the acute outbreak setting.
Authors: Pir Masoom Shah; Faizan Ullah; Dilawar Shah; Abdullah Gani; Carsten Maple; Yulin Wang; Mohammad Abrar; Saif Ul Islam Journal: IEEE Access Date: 2021-05-05 Impact factor: 3.476
Authors: Abdullah S Al-Malaise Al-Ghamdi; Mahmoud Ragab; Saad Abdulla AlGhamdi; Amer H Asseri; Romany F Mansour; Deepika Koundal Journal: Comput Intell Neurosci Date: 2022-04-30
Authors: Jannis Born; David Beymer; Deepta Rajan; Adam Coy; Vandana V Mukherjee; Matteo Manica; Prasanth Prasanna; Deddeh Ballah; Michal Guindy; Dorith Shaham; Pallav L Shah; Emmanouil Karteris; Jan L Robertus; Maria Gabrani; Michal Rosen-Zvi Journal: Patterns (N Y) Date: 2021-04-30
Authors: Daniel Gourdeau; Olivier Potvin; Patrick Archambault; Carl Chartrand-Lefebvre; Louis Dieumegarde; Reza Forghani; Christian Gagné; Alexandre Hains; David Hornstein; Huy Le; Simon Lemieux; Marie-Hélène Lévesque; Diego Martin; Lorne Rosenbloom; An Tang; Fabrizio Vecchio; Issac Yang; Nathalie Duchesne; Simon Duchesne Journal: Sci Rep Date: 2022-04-04 Impact factor: 4.379
Authors: Matthew D Li; Nishanth T Arun; Mehak Aggarwal; Sharut Gupta; Praveer Singh; Brent P Little; Dexter P Mendoza; Gustavo C A Corradi; Marcelo S Takahashi; Suely F Ferraciolli; Marc D Succi; Min Lang; Bernardo C Bizzo; Ittai Dayan; Felipe C Kitamura; Jayashree Kalpathy-Cramer Journal: Medicine (Baltimore) Date: 2022-07-22 Impact factor: 1.817