COVID-19 Compatible Chest CT Pattern



Provide a likelihood of a diagnosis compatible with COVID-19




Define-AI ID



Eric J. Stern, Adam Bernheim, Michael Chung


Eric J. Stern

Panel Chair

Eric J. Stern

Panel Reviewers

Thoracic Panel


Creative Commons 4.0


Public Comment

RadElement Set


Clinical Implementation

Value Proposition

Early published reports suggest an increasing role for chest CT in detection and diagnosis of COVID-19 that results fromsevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. This pandemic infection may have distinctive imaging features that when combined with clinical suspicion and high pre-test probability make AI potentially useful in distinguishing these affected patients from other causes of pneumonia or respiratory distress. In clinical settings where a radiologist is not readily available, such evaluation would be of value to non-radiologists. 

Over half of patients imaged 0-2 days (‘early’) after symptom onset had a normal chest CT, suggesting limited sensitivity and negative predictive value early after symptom onset, and thereby unlikely a reliable standalone tool to rule out COVID-19. []

The hallmarks of COVID-19on imaging were bilateral and peripheral ground-glass and consolidative pulmonary opacities. Preponderance of ground-glass abnormality is noted in early disease, followed by development of crazy paving, and finally increasing consolidation later in the disease course. With a longer time after the onset of symptoms, CT findings were more frequent, including consolidation, bilateral and peripheral disease, greater total lung involvement, linear opacities, “crazy-paving” pattern and the “reverse halo” sign. []

This pattern of disease is similar to that described in other coronavirus outbreaks such as SARS and MERS, and similar to the response to acute lung injury whereby an initial (often infectious or inflammatory) acute insult causes ground-glass opacities that may coalesce into dense consolidative lesions, and then progressively evolve and organize with predilection for the lung periphery. This point emphasizes the relative non-specificity of CT findings and the need for testing in a high-probability environment. []

Notable absence of ancillary chest CT findings such as lymphadenopathy, pleural effusions, pulmonary nodules, and   lung cavitation. []


A 52 year-old male with fever (T > 101o F or 38.3o C) , rhinorrhea, cough, and new onset shortness of breath of duration two days after recent travel from affected geographic regions presents for evaluation.

A 49 year-old female who initially presents with productive cough, new onset shortness of breath, muscle soreness, and malaise develops increasing fever (T > 101o F or 38.3o C)  and requires intensive care unit admission and mechanical ventilation, without alternative explanatory diagnosis.

A 37 year-old female healthcare employee at a nursing care facility who had close contact with a laboratory confirmed COVID-19 patient,  developed new onset shortness of breath, cough, headache, and fatigue with fever (T > 101o F or 38.3o C) over the course of five days.

Workflow Description

Image obtained from modality and sent to PACS and the AI engine. Image analyzed by engine. System returns a likelihood score for COVID-19 compatible disease and returns prediction along with any relevant clinical information. An alert message is sent to PACS from the engine with the prediction and graphic highlighting the most important features the model drew upon for its prediction of COVID-19.

Considerations for Dataset Development


≥ 15 years old

Clinical note: no noticeable imaging features on younger patients

Sex at birth

Male, female, other

Comorbid lung diseases

Emphysema, bronchitis, bronchiolitis, lung fibrosis, and other diffuse lung diseases, malignancy, immunosuppression.

Pathologic Diagnosis

Negative STAT rapid influenza/RSV PCR tests. Positive Real-Time Reverse Transcriptase Polymerase Chain Reaction (rRT-PCR)


CT, Chest with or without intravenous contrast, with or without high-resolution protocols, Contiguous thin sections (≤ 1.5 mm) preferred, LDCT

Most scans will be protocoled without iv contrast.


Axial supine, multiplanar reformats


fever, cough, dyspnea and synonyms, exposure, travel history

Associated findings

presence or absence of pleural fluid, presence or absence of pulmonary edema, presence or absence of lymphadenopathy, presence or absence of pulmonary nodules.

Lung tissue involvement

segmental, patchy, lobar, multilobar, unilateral, bilateral, diffuse,, cavitary, peripheral, central, ground glass, consolidation, cavitation, crazy-paving, reverse-halo, rounded morphology, interlobular septal thickening


Technical Specifications




CT, Chest


axial supine, multiplanar

Data Type




Body Region


Anatomic Focus



Primary Output

COVID-19 Detection

RadElement ID



COVID-19 compatible disease

Data Type


Value Set

COVID-19 Likelihood





Secondary Output

Extent of lung involvement

RadElement ID



Extent of lung involvement by percent volume of ground glass or consolidation.

Data Type


Value Set



% Volume

Future Development Ideas

Track serial/temporal examination changes.


Chest CT Findings in Coronavirus Disease-19 (COVID-19): Relationship to Duration of Infection
Adam Bernheim, Xueyan Mei, Mingqian Huang, Yang Yang, Zahi A. Fayad, Ning Zhang, Kaiyue Diao, Bin Lin, Xiqi Zhu, Kunwei Li, Shaolin Li, Hong Shan, Adam Jacobi, and Michael Chung
Radiology 0 0:0

Chest Imaging Appearance of COVID-19 Infection
Weifang Kong and Prachi P. Agarwal
Radiology: Cardiothoracic Imaging 2020 2:1

Coronavirus Disease 2019 (COVID-19): Role of Chest CT in Diagnosis and Management
Yan Li and Liming Xia
American Journal of Roentgenology 0 0:0, 1-7

CT Provides Best Diagnosis for COVID-19 [Internet]. COVID-19-CT-Diagnosis-Study
2020 [cited 2020Mar9]. Available from:

Imaging Profile of the COVID-19 Infection: Radiologic Findings and Literature Review
Ming-Yen Ng, Elaine YP Lee, Jin Yang, Fangfang Yang, Xia Li, Hongxia Wang, Macy Mei-sze Lui, Christine Shing-Yen Lo, Barry Leung, Pek-Lan Khong, Christopher Kim-Ming Hui, Kwok-yung Yuen, and Michael David Kuo
Radiology: Cardiothoracic Imaging 2020 2:1

Pre- and Posttreatment Chest CT Findings: 2019 Novel Coronavirus (2019-nCoV) Pneumonia
Ya-ni Duan and Jie Qin
Radiology 0 0:0

Sensitivity of Chest CT for COVID-19: Comparison to RT-PCR
Yicheng Fang, Huangqi Zhang, Jicheng Xie, Minjie Lin, Lingjun Ying, Peipei Pang, and Wenbin Ji
Radiology 0 0:0

Related Datasets

The Cancer Imaging Archive (TCIA)

Know of more related datasets? Please let us know