Key result
A deep neural network-based algorithm for automated pulmonary embolism detection on CT angiograms achieved 84.6% sensitivity, 95.1% specificity, and 93.8% overall accuracy.
Why the study?
The study was conducted to assess the performance of a deep neural network-based prototype algorithm for automated pulmonary embolism detection on CTPA scans.
Does a DNN-based algorithm accurately detect pulmonary embolism on CTPA scans in patients with suspected PE?
Observational (n=903)
Does a DNN-based algorithm accurately detect pulmonary embolism on CTPA scans in patients with suspected PE?
A deep neural network algorithm demonstrated high accuracy and specificity for detecting pulmonary embolism on CTPA, suggesting potential utility for assisting radiologists and prioritizing exams.
Answers are grounded in this paper and cite their sources.
DNN shows high retrospective accuracy on CTPA; leaves open prospective validation before any clinical use.
PURPOSE: To assess the performance of a Deep Neural Network (DNN)-based prototype algorithm for automated PE detection on CTPA scans. METHODS: Patients who had previously undergone CTPA with three different systems (SOMATOM Force, go.Top, and Definition AS; Siemens Healthineers, Forchheim, Germany) because of suspected PE from September 2022 to January 2023 were retrospectively enrolled in this study (n = 1,000, 58.8 % women). For detailed evaluation, all PE were divided into three location-based subgroups: central arteries, lobar branches, and peripheral regions. Clinical reports served as ground truth. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were determined to evaluate the performance of DNN-based PE detection. RESULTS: Cases were excluded due to incomplete data (n = 32), inconclusive report (n = 17), insufficient contrast detected in the pulmonary trunk (n = 40), or failure of the preprocessing algorithms (n = 8). Therefore, the final cohort included 903 cases with a PE prevalence of 12 % (n = 110). The model achieved a sensitivity, specificity, PPV, and NPV of 84.6, 95.1, 70.5, and 97.8 %, respectively, and delivered an overall accuracy of 93.8 %. Among the false positive cases (n = 39), common sources of error included lung masses, pneumonia, and contrast flow artifacts. Common sources of false negatives (n = 17) included chronic and subsegmental PEs. CONCLUSION: The proposed DNN-based algorithm provides excellent performance for the detection of PE, suggesting its potential utility to support radiologists in clinical reading and exam prioritization.
No takes yet. Share an insight, caveat, or question.
Zsarnóczay et al. (2025) conducted an observational in Suspected pulmonary embolism (n=903). Deep Neural Network (DNN)-based prototype algorithm vs. Clinical reports (ground truth) was evaluated on Diagnostic performance (sensitivity, specificity, PPV, NPV, and accuracy). A deep neural network-based algorithm for automated pulmonary embolism detection on CT angiograms achieved 84.6% sensitivity, 95.1% specificity, and 93.8% overall accuracy.
Synapse has enriched 10 related papers. Consider them for comparative context: