Accuracy of artificial intelligence CT quantification in predicting COVID-19 subjects’ prognosis
Arvin Arian, Mohammad-Mehdi Mehrabi Nejad, Mostafa Zoorpaikar, Navid Hasanzadeh, Saman Sotoudeh-Paima, Shahriar Kolahi, Masoumeh Gity, Hamid Soltanian-Zadeh
PLOS ONE, doi:10.1371/journal.pone.0294899
Background Artificial intelligence (AI)-aided analysis of chest CT expedites the quantification of abnormalities and may facilitate the diagnosis and assessment of the prognosis of subjects with COVID-19.
Objectives This study investigates the performance of an AI-aided quantification model in predicting the clinical outcomes of hospitalized subjects with COVID-19 and compares it with radiologists' performance.
Subjects and methods A total of 90 subjects with COVID-19 (men, n = 59 [65.6%]; age, 52.9±16.7 years) were recruited in this cross-sectional study. Quantification of the total and compromised lung parenchyma was performed by two expert radiologists using a volumetric image analysis software and compared against an AI-assisted package consisting of a modified U-Net model for segmenting COVID-19 lesions and an off-the-shelf U-Net model augmented with COVID-19 data for segmenting lung volume. The fraction of compromised lung parenchyma (%CL) was calculated. Based on clinical results, the subjects were divided into two categories: critical (n = 45) and noncritical (n = 45). All admission data were compared between the two groups.
Results There was an excellent agreement between the radiologist-obtained and AI-assisted measurements (intraclass correlation coefficient = 0.88, P < 0.001). Both the AI-assisted and
Author Contributions Conceptualization: Arvin Arian. Validation: Shahriar Kolahi, Masoumeh Gity.
Data curation: Visualization: Navid Hasanzadeh. Writing -original draft: Arvin Arian, Mostafa Zoorpaikar, Saman Sotoudeh-Paima.
Writing -review & editing: Hamid Soltanian-Zadeh.
References
Abkhoo, Shaker, Mehrabinejad, Azadbakht, Sadighi et al., Factors predicting outcome in intensive care unit-admitted COVID-19 patients: using clinical, laboratory, and radiologic characteristics, Critical Care Research and Practice,
doi:10.1155/2021/9941570
Arian, Mehrabinejad, Zoorpaikar, Hasanzadeh, Sotoudeh-Paima et al., COVID-19 & Normal CT Segmentation Dataset, Mendeley Data,
doi:10.17632/pfmgfpwnmm.1
Arru, Ebrahimian, Falaschi, Hansen, Pasche et al., Comparison of deep learning, radiomics and subjective assessment of chest CT findings in SARS-CoV-2 pneumonia, Clinical Imaging,
doi:10.1016/j.clinimag.2021.06.036
Arunmozhi, Sarojini, Pavithra, Varghese, Deepti et al., Automated detection of COVID-19 lesion in lung CT slices with VGG-UNet and handcrafted features
Cai, Liu, Xue, Luo, Wang et al., CT quantification and machine-learning models for assessment of disease severity and prognosis of COVID-19 patients, Academic radiology,
doi:10.1016/j.acra.2020.09.004
Dong, Tang, Wang, Hui, Gong et al., The role of imaging in the detection and management of COVID-19: a review, IEEE reviews in biomedical engineering,
doi:10.1109/RBME.2020.2990959
Ebrahimian, Homayounieh, Rockenbach, Putha, Raj et al., Artificial intelligence matches subjective severity assessment of pneumonia for prediction of patient outcome and need for mechanical ventilation: a cohort study, Scientific Reports,
doi:10.1038/s41598-020-79470-0
Fang, He, Li, Dong, Yang et al., CT radiomics can help screen the coronavirus disease 2019 (COVID-19): a preliminary study, Science China Information Sciences,
doi:10.1007/s11432-020-2849-3
Hasanzadeh, Paima, Bashirgonbadi, Naghibi, Soltanian-Zadeh, Segmentation of covid-19 infections on ct: Comparison of four unet-based networks
Hofmanninger, Prayer, Pan, Ro ¨hrich, Prosch et al., Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem, European Radiology Experimental,
doi:10.1186/s41747-020-00173-2
Iyer, Raj, Ghildiyal, Nersisson, Performance analysis of lightweight CNN models to segment infectious lung tissues of COVID-19 cases from tomographic images, PeerJ Computer Science,
doi:10.7717/peerj-cs.368
Lanza, Muglia, Bolengo, Santonocito, Lisi et al., Quantitative chest CT analysis in COVID-19 to predict the need for oxygenation support and intubation, European radiology,
doi:10.1007/s00330-020-07013-2
Mushtaq, Pennella, Lavalle, Colarieti, Steidler et al., Initial chest radiographs and artificial intelligence (AI) predict clinical outcomes in COVID-19 patients: analysis of 697 Italian patients, European radiology,
doi:10.1007/s00330-020-07269-8
Nemoto, Futakami, Kunieda, Yagi, Takeda et al., Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs, Radiological Physics and Technology,
doi:10.1007/s12194-021-00630-6
Phua, Weng, Ling, Egi, Lim et al., Intensive care management of coronavirus disease 2019 (COVID-19): challenges and recommendations, The lancet respiratory medicine,
doi:10.1016/S2213-2600(20)30161-2
Pravitasari, Iriawan, Almuhayar, Azmi, Irhamah et al., UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation, TELKOMNIKA (Telecommunication Computing Electronics and Control),
doi:10.12928/telkomnika.v18i3.14753
Romei, Falaschi, Danna, Airoldi, Tonerini et al., Lung vessel volume evaluated with CALIPER software is an independent predictor of mortality in COVID-19 patients: a multicentric retrospective analysis, European radiology,
doi:10.1007/s00330-021-08485-6
Ronneberger, Fischer, Brox, U-Net: Convolutional networks for biomedical image segmentation
Salahshour, Mehrabinejad, Toosi, Gity, Ghanaati et al., Clinical and chest CT features as a predictive tool for COVID-19 clinical progress: introducing a novel semi-quantitative scoring system, European radiology,
doi:10.1007/s00330-020-07623-w
Salvatore, Dl, Cesare, Alfredo, Giuliano, Clinical and laboratory data, radiological structured report findings and quantitative evaluation of lung involvement on baseline chest CT in COVID-19 patients to predict prognosis, La radiologia medica,
doi:10.1007/s11547-020-01293-w
Scapicchio, Chincarini, Ballante, Berta, Bicci et al., A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia, European Radiology Experimental,
doi:10.1186/s41747-023-00334-z
Shaikh, Andersen, Sohail, Mulero, Awan et al., Current landscape of imaging and the potential role for artificial intelligence in the management of COVID-19, Current Problems in Diagnostic Radiology,
doi:10.1067/j.cpradiol.2020.06.009
Shi, Wang, Shi, Wu, Wang et al., Review of artificial intelligence techniques in imaging data acquisition, segmentation, and diagnosis for COVID-19, IEEE reviews in biomedical engineering,
doi:10.1109/RBME.2020.2987975
Sotoudeh-Paima, Hasanzadeh, Bashirgonbadi, Aref, Naghibi et al., A Multicentric Evaluation of Deep Learning Models for Segmentation of COVID-19 Lung Lesions on Chest CT Scans, Iranian Journal of Radiology,
doi:10.5812/iranjradiol-117992
Wasilewski, Mruk, Mazur, Po ´łtorak-Szymczak, Sklinda et al., COVID-19 severity scoring systems in radiological imaging-a review, Polish journal of radiology,
doi:10.5114/pjr.2020.98009
Yang, Li, Liu, Zhen, Zhang et al., Chest CT severity score: an imaging tool for assessing severe COVID-19, Radiology: Cardiothoracic Imaging,
doi:10.1148/ryct.2020200047
Yu, Liu, Xu, Zhang, Lan et al., Prediction of the development of pulmonary fibrosis using serial thin-section CT and clinical features in patients discharged after treatment for COVID-19 pneumonia, Korean journal of radiology,
doi:10.3348/kjr.2020.0215
Zhao, Zhong, Xie, Yu, Liu, Relation between chest CT findings and clinical conditions of coronavirus disease (COVID-19) pneumonia: a multicenter study, Ajr Am J Roentgenol,
doi:10.2214/AJR.20.22976