Deep learning-based segmentation of acute pulmonary embolism in cardiac CT images.
Authors
Affiliations (5)
Affiliations (5)
- Department of Medical Informatics and Statistics, University Hospital Schleswig-Holstein, Campus Kiel, Arnold-Heller-Str. 3, 24118, Kiel, Schleswig-Holstein, Germany. [email protected].
- Department of Medical Informatics and Statistics, University Hospital Schleswig-Holstein, Campus Kiel, Arnold-Heller-Str. 3, 24118, Kiel, Schleswig-Holstein, Germany. [email protected].
- Institute for Medical Engineering, Otto-von-Guericke-University Magdeburg, Universitätsplatz 2, 39106, Magdeburg, Sachsen-Anhalt, Germany.
- Department of Radiology, Neuroradiology and Nuclear Medicine, Johannes Wesling University Hospital, Ruhr University Bochum, Hans-Nolte-Str. 1, 32429, Minden, North Rhine-Westphalia, Germany.
- Department of Medical Informatics and Statistics, University Hospital Schleswig-Holstein, Campus Kiel, Arnold-Heller-Str. 3, 24118, Kiel, Schleswig-Holstein, Germany.
Abstract
Acute pulmonary embolism (APE) is a common pulmonary condition that, in severe cases, can progress to right ventricular hypertrophy and failure, making it a critical health concern surpassed in severity only by myocardial infarction and sudden death. CT pulmonary angiogram (CTPA) is a standard diagnostic tool for detecting APE. However, for treatment planning and prognosis of patient outcome, an accurate assessment of individual APEs is required. Within this study, we compiled and prepared a dataset of 200 CTPA image volumes of patients with APE. We then adapted two state-of-the-art neural networks; the nnU-Net and the transformer-based VT-UNet in order to provide fully automatic APE segmentations. The nnU-Net demonstrated robust performance, achieving an average Dice similarity coefficient (DSC) of 88.25 ± 10.19% and an average 95th percentile Hausdorff distance (HD95) of 10.57 ± 34.56 mm across the validation sets in a five-fold cross-validation framework. In comparison, the VT-UNet was achieving on par accuracies with an average DSC of 87.90 ± 10.94% and a mean HD95 of 10.77 ± 34.19 mm. We applied two state-of-the-art networks for automatic APE segmentation to our compiled CTPA dataset and achieved superior experimental results compared to the current state of the art. In clinical routine, accurate APE segmentations can be used for enhanced patient prognosis and treatment planning.