Abdominal Aortic Aneurysm Segmentation from CT Images using Modified 3D U-Net with Deep Supervision (CROSBI ID 694979)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Habijan, Marija ; Galic, Irena ; Leventic, Hrvoje ; Romic, Kresimir ; Babin, Danilo
engleski
Abdominal Aortic Aneurysm Segmentation from CT Images using Modified 3D U-Net with Deep Supervision
An abdominal aortic aneurysm (AAA) is a dangerous cardiovascular disease that can cause serious health complications and death. Methods that can provide automatic and accurate segmentation of the AAA can significantly help in preoperative planning and postoperative follow-ups. Therefore, in this work, we present an automatic method for AAA segmentation from CT images using a modified 3D U-Net network with deep supervision. We compare obtained results for AAA segmentation using original 3D U-Net, and modified 3D U-Net with deep supervision. The trained network is evaluated on 19 volumetric CT images from the publicly available dataset provided by the University Hospitals Leuven, Belgium, using four-fold cross-validation. We obtained DSC of 91.03% using modified 3D U-Net with deep supervision. Additionally, we provide a discussion of the effects of using up-sampling versus deconvolution layers and its influence on the performance of both networks for this specific clinical application.
Abdominal aortic aneurysm, CT, Deep learning, Medical image segmentation, 3D U-Net
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
123-128.
2020.
nije evidentirano
objavljeno
978-1-7281-5973-7
10.1109/elmar49956.2020.9219015
Podaci o matičnoj publikaciji
2020 International Symposium ELMAR
Zadar: Institute of Electrical and Electronics Engineers (IEEE)
Podaci o skupu
62nd International Symposium ELMAR-2020
predavanje
14.09.2020-15.09.2020
Zadar, Hrvatska