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

Napredna pretraga

Pregled bibliografske jedinice broj: 1125310

Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization


Habijan, Marija; Galić, Irena; Leventić, Hrvoje; Romić, Krešimir
Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization // Applied Sciences, 11 (2021), 9; 3912, 21 doi:10.3390/app11093912 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1125310 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization

Autori
Habijan, Marija ; Galić, Irena ; Leventić, Hrvoje ; Romić, Krešimir

Izvornik
Applied Sciences (2076-3417) 11 (2021), 9; 3912, 21

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

Ključne riječi
artificial intelligence ; cardiac CT ; cardiac MRI ; deep learning ; ResNet ; variational autoencoder ; whole heart segmentation

Sažetak
An accurate whole heart segmentation (WHS) on medical images, including computed tomography (CT) and magnetic resonance (MR) images, plays a crucial role in many clinical applications, such as cardiovascular disease diagnosis, pre-surgical planning, and intraoperative treatment. Manual whole-heart segmentation is a time-consuming process, prone to subjectivity and error. Therefore, there is a need to develop a quick, automatic, and accurate whole heart segmentation systems. Nowadays, convolutional neural networks (CNNs) emerged as a robust approach for medical image segmentation. In this paper, we first introduce a novel connectivity structure of residual unit that we refer to as a feature merge residual unit (FM-Pre-ResNet). The proposed connectivity allows the creation of distinctly deep models without an increase in the number of parameters compared to the pre-activation residual units. Second, we propose a three-dimensional (3D) encoder–decoder based architecture that successfully incorporates FM-Pre-ResNet units and variational autoencoder (VAE). In an encoding stage, FM-Pre-ResNet units are used for learning a low-dimensional representation of the input. After that, the variational autoencoder (VAE) reconstructs the input image from the low-dimensional latent space to provide a strong regularization of all model weights, simultaneously preventing overfitting on the training data. Finally, the decoding stage creates the final whole heart segmentation. We evaluate our method on the 40 test subjects of the MICCAI Multi-Modality Whole Heart Segmentation (MM-WHS) Challenge. The average dice values of whole heart segmentation are 90.39% (CT images) and 89.50% (MRI images), which are both highly comparable to the state-of-the-art.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekti:
UIP-2017-05-4968 - Metode za interpretaciju medicinskih snimki za detaljnu analizu zdravlja srca (IMAGINEHEART) (Galić, Irena, HRZZ - 2017-05) ( POIROT)

Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Profili:

Avatar Url Hrvoje Leventić (autor)

Avatar Url Marija Habijan (autor)

Avatar Url Krešimir Romić (autor)

Avatar Url Irena Galić (autor)

Poveznice na cjeloviti tekst rada:

doi www.mdpi.com

Citiraj ovu publikaciju:

Habijan, Marija; Galić, Irena; Leventić, Hrvoje; Romić, Krešimir
Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization // Applied Sciences, 11 (2021), 9; 3912, 21 doi:10.3390/app11093912 (međunarodna recenzija, članak, znanstveni)
Habijan, M., Galić, I., Leventić, H. & Romić, K. (2021) Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization. Applied Sciences, 11 (9), 3912, 21 doi:10.3390/app11093912.
@article{article, author = {Habijan, Marija and Gali\'{c}, Irena and Leventi\'{c}, Hrvoje and Romi\'{c}, Kre\v{s}imir}, year = {2021}, pages = {21}, DOI = {10.3390/app11093912}, chapter = {3912}, keywords = {artificial intelligence, cardiac CT, cardiac MRI, deep learning, ResNet, variational autoencoder, whole heart segmentation}, journal = {Applied Sciences}, doi = {10.3390/app11093912}, volume = {11}, number = {9}, issn = {2076-3417}, title = {Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization}, keyword = {artificial intelligence, cardiac CT, cardiac MRI, deep learning, ResNet, variational autoencoder, whole heart segmentation}, chapternumber = {3912} }
@article{article, author = {Habijan, Marija and Gali\'{c}, Irena and Leventi\'{c}, Hrvoje and Romi\'{c}, Kre\v{s}imir}, year = {2021}, pages = {21}, DOI = {10.3390/app11093912}, chapter = {3912}, keywords = {artificial intelligence, cardiac CT, cardiac MRI, deep learning, ResNet, variational autoencoder, whole heart segmentation}, journal = {Applied Sciences}, doi = {10.3390/app11093912}, volume = {11}, number = {9}, issn = {2076-3417}, title = {Whole Heart Segmentation Using 3D FM-Pre-ResNet Encoder–Decoder Based Architecture with Variational Autoencoder Regularization}, keyword = {artificial intelligence, cardiac CT, cardiac MRI, deep learning, ResNet, variational autoencoder, whole heart segmentation}, chapternumber = {3912} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font