Evaluation of acute pulmonary embolism and clot burden on CTPA with deep learning

• Published in: European radiology Vol. 30; no. 6; pp. 3567 - 3575
• Main Authors: Liu, Weifang, Liu, Min, Guo, Xiaojuan, Zhang, Peiyao, Zhang, Ling, Zhang, Rongguo, Kang, Han, Zhai, Zhenguo, Tao, Xincao, Wan, Jun, Xie, Sheng
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-06-2020; Springer Nature B.V
• Subjects: Algorithms; Angiography; Artificial neural networks; Computed tomography; Correlation analysis; Deep learning; Diagnostic Radiology; Embolism; Embolisms; Heart; Image segmentation; Imaging; Imaging Informatics and Artificial Intelligence; Internal Medicine; Interventional Radiology; Learning algorithms; Machine learning; Medicine; Medicine & Public Health; Neural networks; Neuroradiology; Parameters; Performance evaluation; Physicians; Pulmonary embolisms; Radiology; Sensitivity; Statistical analysis; Thresholds; Ultrasound; Ventricle; Workload; Pulmonary embolism; Computed tomography angiography; Neural networks (computer); Lung
• ISSN: 0938-7994; 1432-1084
• DOI: 10.1007/s00330-020-06699-8

Objectives
To take advantage of the deep learning algorithms to detect and calculate clot burden of acute pulmonary embolism (APE) on computed tomographic pulmonary angiography (CTPA).
Materials and methods
The training set in this retrospective study consisted of 590 patients (460 with APE and 130 without APE) who underwent CTPA. A fully deep learning convolutional neural network (DL-CNN), called U-Net, was trained for the segmentation of clot. Additionally, an in-house validation set consisted of 288 patients (186 with APE and 102 without APE). In this study, we set different probability thresholds to test the performance of U-Net for the clot detection and selected sensitivity, specificity, and area under the curve (AUC) as the metrics of performance evaluation. Furthermore, we investigated the relationship between the clot burden assessed by the Qanadli score, Mastora score, and other imaging parameters on CTPA and the clot burden calculated by the DL-CNN model.
Results
There was no statistically significant difference in AUCs with the different probability thresholds. When the probability threshold for segmentation was 0.1, the sensitivity and specificity of U-Net in detecting clot respectively were 94.6% and 76.5% while the AUC was 0.926 (95% CI 0.884–0.968). Moreover, this study displayed that the clot burden measured with U-Net was significantly correlated with the Qanadli score (
r
 = 0.819,
p
 < 0.001), Mastora score (
r
 = 0.874,
p
 < 0.001), and right ventricular functional parameters on CTPA.
Conclusions
DL-CNN achieved a high AUC for the detection of pulmonary emboli and can be applied to quantitatively calculate the clot burden of APE patients, which may contribute to reducing the workloads of clinicians.
Key Points
• Deep learning can detect APE with a good performance and efficiently calculate the clot burden to reduce the physicians’ workload.
• Clot burden measured with deep learning highly correlates with Qanadli and Mastora scores of CTPA.
• Clot burden measured with deep learning correlates with parameters of right ventricular function on CTPA.