Key result
Deep learning algorithm detects pulmonary embolism on chest CTA with ~0.92 AUC.
Why the study?
Prompt recognition of acute pulmonary embolism (PE) and immediate treatment reduce mortality, motivating the validation of a deep learning algorithm to automatically detect PEs on chest CTAs and alert radiologists.
Does a deep learning-based algorithm accurately detect pulmonary embolism in patients undergoing chest CT angiography?
Cross-Sectional (n=387)
Blinded
Yes
Does a deep learning-based algorithm accurately detect pulmonary embolism in patients undergoing chest CT angiography?
Effect estimate: AUC 0.92 (95% CI 0.88-0.94)
p-value: p=<0.0001
The deep learning algorithm provides high diagnostic accuracy for pulmonary embolism detection on CT angiograms, supporting its potential use for prioritizing urgent exams in radiology workflows.
PURPOSE: Since the prompt recognition of acute pulmonary embolism (PE) and the immediate initiation of treatment can significantly reduce the risk of death, we developed a deep learning (DL)-based application aimed to automatically detect PEs on chest computed tomography angiograms (CTAs) and alert radiologists for an urgent interpretation. Convolutional neural networks (CNNs) were used to design the application. The associated algorithm used a hybrid 3D/2D UNet topology. The training phase was performed on datasets adequately distributed in terms of vendors, patient age, slice thickness, and kVp. The objective of this study was to validate the performance of the algorithm in detecting suspected PEs on CTAs. METHODS: The validation dataset included 387 anonymized real-world chest CTAs from multiple clinical sites (228 U.S. cities). The data were acquired on 41 different scanner models from five different scanner makers. The ground truth (presence or absence of PE on CTA images) was established by three independent U.S. board-certified radiologists. RESULTS: The algorithm correctly identified 170 of 186 exams positive for PE (sensitivity 91.4% [95% CI: 86.4-95.0%]) and 184 of 201 exams negative for PE (specificity 91.5% [95% CI: 86.8-95.0%]), leading to an accuracy of 91.5%. False negative cases were either chronic PEs or PEs at the limit of subsegmental arteries and close to partial volume effect artifacts. Most of the false positive findings were due to contrast agent-related fluid artifacts, pulmonary veins, and lymph nodes. CONCLUSIONS: The DL-based algorithm has a high degree of diagnostic accuracy with balanced sensitivity and specificity for the detection of PE on CTAs.
No takes yet. Share an insight, caveat, or question.
Greniér et al. (2023) conducted a cross-sectional in Suspected pulmonary embolism (n=387). CINA-PE (Deep learning-based algorithm) vs. Reference standard by 3 U.S. board-certified radiologists was evaluated on Area under the receiver operating characteristic curve (AUC) for detection of pulmonary embolism (AUC 0.92, 95% CI 0.88-0.94, p=<0.0001). The deep learning-based algorithm accurately detected pulmonary embolism on chest CT angiograms with a sensitivity of 91.4%, specificity of 91.5%, and an AUC of 0.92.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: