Key result
A deep neural network model achieved 95% accuracy, 90% precision, and 100% recall (AUC 0.99) for detecting endoleaks on post-EVAR CT angiography, outperforming general radiologists.
Why the study?
Manual review of multi-slice CTA for endoleak following EVAR is tedious, time-consuming, and susceptible to error.
Does a deep neural network machine learning model improve the detection of endoleaks on CTA in post-EVAR patients compared to human radiologists?
Observational (n=70)
Blinded human readers for comparison
No
Does a deep neural network machine learning model improve the detection of endoleaks on CTA in post-EVAR patients compared to human radiologists?
Effect estimate: AUC 0.99
A deep learning model trained with a novel data augmentation technique demonstrated endoleak detection performance on post-EVAR CTAs comparable to cardiovascular imaging subspecialists and superior to general radiologists.
May aid endoleak detection on post-EVAR CTA; leaves open prospective validation before clinical adoption.
Diagnosis of endoleak following endovascular aortic repair (EVAR) relies on manual review of multi-slice CT angiography (CTA) by physicians which is a tedious and time-consuming process that is susceptible to error. We evaluate the use of a deep neural network for the detection of endoleak on CTA for post-EVAR patients using a novel data efficient training approach. 50 CTAs and 20 CTAs with and without endoleak respectively were identified based on gold standard interpretation by a cardiovascular subspecialty radiologist. The Endoleak Augmentor, a custom designed augmentation method, provided robust training for the machine learning (ML) model. Predicted segmentation maps underwent post-processing to determine the presence of endoleak. The model was tested against 3 blinded general radiologists and 1 blinded subspecialist using a held-out subset (10 positive endoleak CTAs, 10 control CTAs). Model accuracy, precision and recall for endoleak diagnosis were 95%, 90% and 100% relative to reference subspecialist interpretation (AUC = 0.99). Accuracy, precision and recall was 70/70/70% for generalist1, 50/50/90% for generalist2, and 90/83/100% for generalist3. The blinded subspecialist had concordant interpretations for all test cases compared with the reference. In conclusion, our ML-based approach has similar performance for endoleak diagnosis relative to subspecialists and superior performance compared with generalists.
No takes yet. Share an insight, caveat, or question.
Talebi et al. (2020) conducted an observational in Post-endovascular aortic repair (EVAR) endoleak (n=70). Machine learning model (U-net CNN) vs. General diagnostic radiologists was evaluated on Accuracy for endoleak diagnosis (AUC 0.99). A deep neural network model achieved 95% accuracy, 90% precision, and 100% recall (AUC 0.99) for detecting endoleaks on post-EVAR CT angiography, outperforming general radiologists.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: