hrcak mascot   Srce   HID

Original scientific paper
https://doi.org/10.32985/ijeces.11.1.3

Neural Network based Whole Heart Segmentation from 3D CT images

Marija Habijan   ORCID icon orcid.org/0000-0002-3754-498X ; J.J. Strossmayer University of Osijek,Faculty of Electrical Engineering, Computer Scienceand Information Technology Osijek
Hrvoje Leventić ; J.J. Strossmayer University of Osijek,Faculty of Electrical Engineering, Computer Scienceand Information Technology Osijek
Irena Galić   ORCID icon orcid.org/0000-0002-0211-4568 ; J.J. Strossmayer University of Osijek,Faculty of Electrical Engineering, Computer Scienceand Information Technology Osijek
Danilo Babin ; imec-Ghent University,imec-TELIN-IPI, Faculty of Engineering and Architecture

Fulltext: english, pdf (507 KB) pages 25-31 downloads: 193* cite
APA 6th Edition
Habijan, M., Leventić, H., Galić, I. & Babin, D. (2020). Neural Network based Whole Heart Segmentation from 3D CT images. International journal of electrical and computer engineering systems, 11 (1), 25-31. https://doi.org/10.32985/ijeces.11.1.3
MLA 8th Edition
Habijan, Marija, et al. "Neural Network based Whole Heart Segmentation from 3D CT images." International journal of electrical and computer engineering systems, vol. 11, no. 1, 2020, pp. 25-31. https://doi.org/10.32985/ijeces.11.1.3. Accessed 23 Oct. 2021.
Chicago 17th Edition
Habijan, Marija, Hrvoje Leventić, Irena Galić and Danilo Babin. "Neural Network based Whole Heart Segmentation from 3D CT images." International journal of electrical and computer engineering systems 11, no. 1 (2020): 25-31. https://doi.org/10.32985/ijeces.11.1.3
Harvard
Habijan, M., et al. (2020). 'Neural Network based Whole Heart Segmentation from 3D CT images', International journal of electrical and computer engineering systems, 11(1), pp. 25-31. https://doi.org/10.32985/ijeces.11.1.3
Vancouver
Habijan M, Leventić H, Galić I, Babin D. Neural Network based Whole Heart Segmentation from 3D CT images. International journal of electrical and computer engineering systems [Internet]. 2020 [cited 2021 October 23];11(1):25-31. https://doi.org/10.32985/ijeces.11.1.3
IEEE
M. Habijan, H. Leventić, I. Galić and D. Babin, "Neural Network based Whole Heart Segmentation from 3D CT images", International journal of electrical and computer engineering systems, vol.11, no. 1, pp. 25-31, 2020. [Online]. https://doi.org/10.32985/ijeces.11.1.3

Abstracts
The most recent research is showing the importance and suitability of neural networks for medical image processing tasks. Nonetheless, their efficiency in segmentation tasks is greatly dependent on the amount of available training data. To overcome issues of using small datasets, various data augmentation techniques have been developed. In this paper, an approach for the whole heart segmentation based on the convolutional neural network, specifically on the 3D U-Net architecture, is presented. Also, we propose the incorporation of the principal component analysis as an additional data augmentation technique. The network is trained end-to-end, i.e., no pre-trained network is required. Evaluation of the proposed approach is performed on CT images from MICCAI 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, delivering in a three-fold cross-validation an average dice coefficient overlap of 88.2% for the whole heart, i.e. all heart substructures. Final segmentation results show a high accuracy with the ground truth, indicating that the proposed approach is competitive to the state-of-the-art. Additionally, experiments on the influence of different learning rates are provided as well, showing the optimal learning rate of 0.005 to give the best segmentation results.

Keywords
CT, data augmentation, medical image segmentation, neural networks, volumetric segmentation, whole heart segmentation

Hrčak ID: 242929

URI
https://hrcak.srce.hr/242929

Visits: 428 *