Any unique image biomarkers associated with COVID-19?
- PDF / 767,026 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 143 Views
IMAGING INFORMATICS AND ARTIFICIAL INTELLIGENCE
Any unique image biomarkers associated with COVID-19? Jiantao Pu 1 & Joseph Leader 1 & Andriy Bandos 2 & Junli Shi 1 & Pang Du 1 & Juezhao Yu 1 & Bohan Yang 1 & Shi Ke 4 & Youmin Guo 4 & Jessica B. Field 3 & Carl Fuhrman 1 & David Wilson 3 & Frank Sciurba 3 & Chenwang Jin 4 Received: 17 April 2020 / Revised: 3 May 2020 / Accepted: 14 May 2020 # European Society of Radiology 2020
Abstract Objective To define the uniqueness of chest CT infiltrative features associated with COVID-19 image characteristics as potential diagnostic biomarkers. Methods We retrospectively collected chest CT exams including n = 498 on 151 unique patients RT-PCR positive for COVID19 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. Results 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. Conclusions Professional or automated interpretation of CT exams has a moderately low ability to distinguish between COVID19 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. Key Points • 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. Keywords COVID-19 . Biomarkers . Pneumonia . Neural network
* Jiantao Pu [email protected] 1
Department of Radiology, University of Pittsburgh, Pittsburgh, PA 15213, USA
2
Department of Biostatistics, University of Pittsburgh, Pittsburgh, PA 15213, USA
3
Division of Pulmonary, Allergy, and Critical Care Medicine, Department of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, USA
4
Department of Radiology, Xi’an Jiaotong University The First Affiliated Hospital, Xi’an, China
Abbreviations AUC Area under the curve BCE Binary cross-entropy CAP Community-acquired pneumonia CI Confidencial interval CNN Convolutional neural network COVID-19 Novel coronavirus CT Computed tomography FC
Data Loading...
