1. Any unique image biomarkers associated with COVID-19?
- Author
-
Carl R. Fuhrman, Shi Ke, Junli Shi, Jiantao Pu, Juezhao Yu, Andriy I. Bandos, Joseph K. Leader, Pang Du, David O. Wilson, Chenwang Jin, Bohan Yang, Youmin Guo, Jessica B. Field, and Frank C. Sciurba
- Subjects
Adult ,Male ,medicine.medical_specialty ,Coronavirus disease 2019 (COVID-19) ,Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) ,Pneumonia, Viral ,Chest ct ,Convolutional neural network ,030218 nuclear medicine & medical imaging ,Betacoronavirus ,03 medical and health sciences ,0302 clinical medicine ,Artificial Intelligence ,Image Interpretation, Computer-Assisted ,Humans ,Medicine ,Diagnostic biomarker ,Radiology, Nuclear Medicine and imaging ,Lung ,Pandemics ,Retrospective Studies ,Neuroradiology ,Receiver operating characteristic ,SARS-CoV-2 ,business.industry ,Nonparametric statistics ,COVID-19 ,Pneumonia ,General Medicine ,Neural network ,ROC Curve ,Imaging Informatics and Artificial Intelligence ,Radiology Nuclear Medicine and imaging ,030220 oncology & carcinogenesis ,Female ,Radiography, Thoracic ,Radiology ,Coronavirus Infections ,Tomography, X-Ray Computed ,business ,Biomarkers - Abstract
To define the uniqueness of chest CT infiltrative features associated with COVID-19 image characteristics as potential diagnostic biomarkers. We retrospectively collected chest CT exams including n = 498 on 151 unique patients RT-PCR positive for COVID-19 and n = 497 unique patients with community-acquired pneumonia (CAP). Both COVID-19 and CAP image sets were partitioned into three groups for training, validation, and testing respectively. In an attempt to discriminate COVID-19 from CAP, we developed several classifiers based on three-dimensional (3D) convolutional neural networks (CNNs). We also asked two experienced radiologists to visually interpret the testing set and discriminate COVID-19 from CAP. The classification performance of the computer algorithms and the radiologists was assessed using the receiver operating characteristic (ROC) analysis, and the nonparametric approaches with multiplicity adjustments when necessary. One of the considered models showed non-trivial, but moderate diagnostic ability overall (AUC of 0.70 with 99% CI 0.56–0.85). This model allowed for the identification of 8–50% of CAP patients with only 2% of COVID-19 patients. Professional or automated interpretation of CT exams has a moderately low ability to distinguish between COVID-19 and CAP cases. However, the automated image analysis is promising for targeted decision-making due to being able to accurately identify a sizable subsect of non-COVID-19 cases. • Both human experts and artificial intelligent models were used to classify the CT scans. • ROC analysis and the nonparametric approaches were used to analyze the performance of the radiologists and computer algorithms. • Unique image features or patterns may not exist for reliably distinguishing all COVID-19 from CAP; however, there may be imaging markers that can identify a sizable subset of non-COVID-19 cases.
- Published
- 2020