New to MyHealth?
Manage Your Care From Anywhere.
Access your health information from any device with MyHealth. You can message your clinic, view lab results, schedule an appointment, and pay your bill.
ALREADY HAVE AN ACCESS CODE?
DON'T HAVE AN ACCESS CODE?
NEED MORE DETAILS?
MyHealth for Mobile
Automated cross-sectional view selection in CT angiography of aortic dissections with uncertainty awareness and retrospective clinical annotations.
Automated cross-sectional view selection in CT angiography of aortic dissections with uncertainty awareness and retrospective clinical annotations. Computers in biology and medicine Pepe, A., Egger, J., Codari, M., Willemink, M. J., Gsaxner, C., Li, J., Roth, P. M., Schmalstieg, D., Mistelbauer, G., Fleischmann, D. 2023; 165: 107365Abstract
Surveillance imaging of patients with chronic aortic diseases, such as aneurysms and dissections, relies on obtaining and comparing cross-sectional diameter measurements along the aorta at predefined aortic landmarks, over time. The orientation of the cross-sectional measuring planes at each landmark is currently defined manually by highly trained operators. Centerline-based approaches are unreliable in patients with chronic aortic dissection, because of the asymmetric flow channels, differences in contrast opacification, and presence of mural thrombus, making centerline computations or measurements difficult to generate and reproduce. In this work, we present three alternative approaches - INS, MCDS, MCDbS - based on convolutional neural networks and uncertainty quantification methods to predict the orientation (?,?) of such cross-sectional planes. For the monitoring of chronic aortic dissections, we show how a dataset of 162 CTA volumes with overall 3273 imperfect manual annotations routinely collected in a clinic can be efficiently used to accomplish this task, despite the presence of non-negligible interoperator variabilities in terms of mean absolute error (MAE) and 95% limits of agreement (LOA). We show how, despite the large limits of agreement in the training data, the trained model provides faster and more reproducible results than either an expert user or a centerline method. The remaining disagreement lies within the variability produced by three independent expert annotators and matches the current state of the art, providing a similar error, but in a fraction of the time.
View details for DOI 10.1016/j.compbiomed.2023.107365
View details for PubMedID 37647783