Related Experiment Video
Updated: Jan 13, 2026
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Early assessment of myocardial injury in patients with coronavirus disease 2019 using a two-stage deep learning
Li Wang1, Zhitao Cheng2, Bingyao Liu1
1Department of Radiology, The Affiliated Hospital of Southwest Medical University, Luzhou, China.
Insights
Deep learning models can now predict myocardial injury (MI) in COVID-19 patients using non-contrast chest CT scans. This technology offers a convenient, one-stop solution for early MI screening and risk stratification.
Area of Science:
- Radiology
- Artificial Intelligence
- Cardiology
Background:
- Risk stratification is crucial for predicting coronavirus disease 2019 (COVID-19) prognosis, especially concerning myocardial injury (MI).
- Non-contrast chest computed tomography (CT) is established for lung injury diagnosis, but its utility for simultaneous MI evaluation is uncertain.
- Early MI screening and resource allocation are vital for managing COVID-19 patients.
Purpose of the Study:
- To develop and evaluate a deep learning (DL) framework for the one-step prediction of MI in COVID-19 patients.
- To assess the feasibility of using non-contrast chest CT for early MI screening.
- To enable efficient identification of high-risk patients for further diagnostic evaluation.
Main Methods:
- A retrospective cohort of 453 COVID-19 patients (230 with MI, 223 without MI) was analyzed.
- A two-stage DL framework was employed: ResNet-101 for left ventricle (LV) segmentation and DenseNet-121 for MI classification.
- The framework was trained on 413 patients and validated on 40 patients using cross-validation.
Main Results:
- The DL framework achieved high accuracy in LV segmentation (IoU: 0.8041, ACC: 0.9949, Dice: 0.8672).
- The framework accurately predicted MI status with an AUC of 0.8618 (95% CI: 0.8049-0.9187).
- Key classification metrics included ACC: 0.7763, SEN: 0.8750, SPE: 0.6071, and F1 score: 0.8317.
Conclusions:
- Deep learning models can effectively determine MI status from non-contrast chest CT images in COVID-19 patients.
- This approach offers a convenient, one-stop solution for the early screening of MI.
- The DL framework facilitates timely risk stratification and resource optimization for COVID-19 care.
Background:
Risk stratification is particularly important for the prognosis of coronavirus disease 2019 (COVID-19), particularly regarding myocardial injury (MI). Non-contrast chest computed tomography (CT) is useful for diagnosing lung injury, but its potential for one-stop evaluation of MI remains unclear. This study aimed to develop a deep learning (DL) framework for the one-step prediction of MI in COVID-19 patients using non-contrast chest CT. This approach seeks to enable early MI screening, direct high-risk patients toward further diagnostic tests, and optimize the allocation of medical resources.
Methods:
A group of 453 patients with COVID-19, including 230 patients with MI and 223 patients without MI, were retrospectively recruited. A two-stage DL framework was developed to first segment the left ventricle (LV) in the non-contrast chest CT images using fully convolutional networks with a ResNet-101 backbone (FCN-ResNet-101) module and then classify the status of MI using densely connected convolutional network with the structure type of 121 (DenseNet-121) module. The framework was trained in a training-validation dataset of 413 patients (MI or non-MI) with a cross-validation approach, and evaluated in a testing dataset of 40 patients.
Results:
The proposed DL framework accurately obtained the segmentations of LV in non-contrast chest CT images with an intersection over union (IoU) of 0.8041, an accuracy (ACC) of 0.9949, and a Dice coefficient of 0.8672. Based on the segmentation, the DL framework further accurately determined MI status and obtained an area under the curve (AUC) of 0.8618 [95% confidence interval (CI): 0.8049-0.9187], an ACC of 0.7763, a sensitivity (SEN) of 0.8750, a specificity (SPE) of 0.6071, and an F1 score of 0.8317.
Conclusions:
DL could determine the status of MI in non-contrast chest CT images of patients with COVID-19, providing one-stop convenience for early screening of MI.
More Related Videos
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT