tetano
Editor, Senior Moderator
Quant Imaging Med Surg
. 2026 Jan 1;16(1):65.
doi: 10.21037/qims-2025-449. Epub 2025 Dec 31. Early assessment of myocardial injury in patients with coronavirus disease 2019 using a two-stage deep learning framework based on non-contrast chest computed tomography
Li Wang[SUP] #[/SUP][SUP] 1 [/SUP], Zhitao Cheng[SUP] #[/SUP][SUP] 2 [/SUP], Bingyao Liu[SUP] 1 [/SUP], Mingsong Tang[SUP] 1 [/SUP], Liuting Lu[SUP] 1 [/SUP], Jiayi Qiao[SUP] 2 [/SUP], Yanling Leng[SUP] 3 [/SUP], Maosheng Li[SUP] 3 [/SUP], Song Su[SUP] 4 5 [/SUP], Jian Shu[SUP] 1 [/SUP], Jing Chen[SUP] 1 [/SUP], Yong Tang[SUP] 5 6 [/SUP]
Affiliations
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.
Keywords: Non-contrast chest computed tomography (non-contrast chest CT); coronavirus disease 2019 (COVID-19); deep learning (DL); myocardial injury (MI).
. 2026 Jan 1;16(1):65.
doi: 10.21037/qims-2025-449. Epub 2025 Dec 31. Early assessment of myocardial injury in patients with coronavirus disease 2019 using a two-stage deep learning framework based on non-contrast chest computed tomography
Li Wang[SUP] #[/SUP][SUP] 1 [/SUP], Zhitao Cheng[SUP] #[/SUP][SUP] 2 [/SUP], Bingyao Liu[SUP] 1 [/SUP], Mingsong Tang[SUP] 1 [/SUP], Liuting Lu[SUP] 1 [/SUP], Jiayi Qiao[SUP] 2 [/SUP], Yanling Leng[SUP] 3 [/SUP], Maosheng Li[SUP] 3 [/SUP], Song Su[SUP] 4 5 [/SUP], Jian Shu[SUP] 1 [/SUP], Jing Chen[SUP] 1 [/SUP], Yong Tang[SUP] 5 6 [/SUP]
Affiliations
- PMID: 41522060
- PMCID: PMC12780574
- DOI: 10.21037/qims-2025-449
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.
Keywords: Non-contrast chest computed tomography (non-contrast chest CT); coronavirus disease 2019 (COVID-19); deep learning (DL); myocardial injury (MI).