Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1064015

Neural Network based Whole Heart Segmentation from 3D CT images


Habijan, Marija; Leventić, Hrvoje; Galić, Irena; Babin, Danilo
Neural Network based Whole Heart Segmentation from 3D CT images // International journal of electrical and computer engineering systems, 11 (2020), 1; 25-31 doi:10.32985/ijeces (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1064015 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Neural Network based Whole Heart Segmentation from 3D CT images

Autori
Habijan, Marija ; Leventić, Hrvoje ; Galić, Irena ; Babin, Danilo

Izvornik
International journal of electrical and computer engineering systems (1847-6996) 11 (2020), 1; 25-31

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
CT ; data augmentation ; medical image segmentation ; neural networks ; volumetric segmentation ; whole heart segmentation

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
HRZZ-UIP-2017-05-4968 - Metode za interpretaciju medicinskih snimki za detaljnu analizu zdravlja srca (IMAGINEHEART) (Galić, Irena, HRZZ - 2017-05 )

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Profili:

Avatar Url Irena Galić (autor)

Avatar Url Hrvoje Leventić (autor)

Avatar Url Marija Habijan (autor)

Citiraj ovu publikaciju

Habijan, Marija; Leventić, Hrvoje; Galić, Irena; Babin, Danilo
Neural Network based Whole Heart Segmentation from 3D CT images // International journal of electrical and computer engineering systems, 11 (2020), 1; 25-31 doi:10.32985/ijeces (međunarodna recenzija, članak, znanstveni)
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 doi:10.32985/ijeces.
@article{article, year = {2020}, pages = {25-31}, DOI = {10.32985/ijeces}, keywords = {CT, data augmentation, medical image segmentation, neural networks, volumetric segmentation, whole heart segmentation}, journal = {International journal of electrical and computer engineering systems}, doi = {10.32985/ijeces}, volume = {11}, number = {1}, issn = {1847-6996}, title = {Neural Network based Whole Heart Segmentation from 3D CT images}, keyword = {CT, data augmentation, medical image segmentation, neural networks, volumetric segmentation, whole heart segmentation} }

Časopis indeksira:


  • Web of Science Core Collection (WoSCC)
    • Emerging Sources Citation Index (ESCI)
  • Scopus


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font