Key result
Deep-learning algorithm accurately detects PE on CTPA scans with an AUROC of 0.94.
Why the study?
To externally validate the RSNA 2020 challenge second-place deep-learning algorithm for detecting pulmonary embolism on CTPA scans, with an additional focus on subsegmental-only pulmonary embolisms.
Does a deep-learning algorithm accurately detect pulmonary embolism on CTPA scans in adult patients?
Observational (n=1,038)
No
Does a deep-learning algorithm accurately detect pulmonary embolism on CTPA scans in adult patients?
The deep-learning model demonstrated high diagnostic performance for detecting central and lobar/segmental pulmonary embolism on CTPA, but struggled to accurately identify subsegmental-only embolisms.
Supports DL for central PE detection on CTPA; leaves open SSPE performance without targeted training.
To externally validate the RSNA 2020 challenge 2 nd -place deep-learning (DL) algorithm for detecting pulmonary embolism (PE) on computed tomography pulmonary angiography (CTPA) scans with additional focus on subsegmental-only PEs (SSPE). Between 2015 and 2022 1,038 CTPAs were retrospectively enrolled. An experienced radiologist (> five years) labelled CTPAs for the presence, location (central, lobar and segmental, subsegmental-only) and side (right-sided, left-sided, bilateral) of PE. The DL model was tested for its ability to predict these labels by analyzing accuracy, sensitivity, specificity and area under the receiver operating characteristic curve (AUROC) using different model outcome probabilities for each analysis. Overall, 136 central, 375 peripheral PEs (303 lobar and segmental PEs, 72 SSPEs), and 527 patients without any PE were analyzed. The model correctly predicted the presence of any PE in 921/1,038 patients (88.7%), yielding a sensitivity of 0.80, specificity of 0.97 and AUROC of 0.94. No central PE was missed, whereas 100/375 (26.7%) peripheral PEs remained undetected. Using the corresponding model output probability, the central PE status was correctly identified in 999/1,038 (96.2%) patients, while peripheral PE was correctly identified in 785/1,038 (75.6%) patients. This corresponded to sensitivities of 0.94 and 0.77, specificities of 0.97 and 0.75, and AUROC values of 0.99 and 0.74, respectively. The model performed better in detecting right-sided compared to left-sided PEs (AUROC: right- vs. left-sided: 0.95 and 0.92, p < 0.05). SSPE status was correctly predicted in 796/1,038 (76.7%) patients, yielding a sensitivity of 0.94, a specificity of 0.22, and an AUROC of 0.48, respectively. The model demonstrated high performance in detecting any PE, performing best on central and slightly lower on lobar and segmental PE. Predicting the presence of SSPEs was difficult, likely due to the model not being explicitly trained for this subtype.
No takes yet. Share an insight, caveat, or question.
Hahlbohm et al. (2026) conducted an observational in Pulmonary embolism (n=1,038). RSNA 2020 challenge 2nd-place deep-learning algorithm vs. Ground truth labels by experienced radiologists was evaluated on Prediction of the presence of any pulmonary embolism (AUROC 0.94, 95% CI 0.92-0.95, p=<0.001). The RSNA 2020 challenge 2nd-place deep-learning algorithm accurately detected the presence of any pulmonary embolism on CTPA scans with an AUROC of 0.94, a sensitivity of 0.80, and a specificity of 0.97.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: