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

Napredna pretraga

Pregled bibliografske jedinice broj: 1026333

Whole Heart Segmentation from CT images Using 3D U-Net architecture


Habijan, Marija; Leventic, Hrvoje; Galic, Irena; Babin, Danilo
Whole Heart Segmentation from CT images Using 3D U-Net architecture // 2019 International Conference on Systems, Signals and Image Processing (IWSSIP)
Osijek: IEEE, 2019. str. 121-126 doi:10.1109/iwssip.2019.8787253 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1026333 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Whole Heart Segmentation from CT images Using 3D U-Net architecture

Autori
Habijan, Marija ; Leventic, Hrvoje ; Galic, Irena ; Babin, Danilo

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2019 International Conference on Systems, Signals and Image Processing (IWSSIP) / - Osijek : IEEE, 2019, 121-126

ISBN
978-1-7281-3253-2

Skup
2019 International Conference on Systems, Signals and Image Processing (IWSSIP)

Mjesto i datum
Osijek, 5-7.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

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

Sažetak
Recent studies have demonstrated the importance of neural networks in medical image processing and analysis. However, their great efficiency in segmentation tasks is highly dependent on the amount of training data. When these networks are used on small datasets, the process of data augmentation can be very significant. We propose a convolutional neural network approach for the whole heart segmentation which is based upon the 3D U-Net architecture and incorporates principle 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 20 3D CT images from MICCAI 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, divided into 15 training and 5 validation images. Final segmentation results show a high Dice coefficient overlap to ground truth, indicating that the proposed approach is competitive to state-of-the-art Additionally, we provide the discussion of the influence of different learning rates on the final 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 Marija Habijan (autor)

Avatar Url Hrvoje Leventić (autor)

Citiraj ovu publikaciju

Habijan, Marija; Leventic, Hrvoje; Galic, Irena; Babin, Danilo
Whole Heart Segmentation from CT images Using 3D U-Net architecture // 2019 International Conference on Systems, Signals and Image Processing (IWSSIP)
Osijek: IEEE, 2019. str. 121-126 doi:10.1109/iwssip.2019.8787253 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Habijan, M., Leventic, H., Galic, I. & Babin, D. (2019) Whole Heart Segmentation from CT images Using 3D U-Net architecture. U: 2019 International Conference on Systems, Signals and Image Processing (IWSSIP) doi:10.1109/iwssip.2019.8787253.
@article{article, year = {2019}, pages = {121-126}, DOI = {10.1109/iwssip.2019.8787253}, keywords = {CT, data augmentation, heart segmentation, medical image segmentation, neural networks, volumetric segmentation}, doi = {10.1109/iwssip.2019.8787253}, isbn = {978-1-7281-3253-2}, title = {Whole Heart Segmentation from CT images Using 3D U-Net architecture}, keyword = {CT, data augmentation, heart segmentation, medical image segmentation, neural networks, volumetric segmentation}, publisher = {IEEE}, publisherplace = {Osijek} }

Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font