Semi-supervised segmentation of multi-vendor and multi-center cardiac MRI

Mahyar Bolhassani, Ilkay Oksuz

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

9 Atıf (Scopus)

Özet

Automatic segmentation of the heart cavity is an essential task for the diagnosis of cardiac diseases. In this paper, we propose a semi-supervised segmentation setup for leveraging unlabeled data to segment Left-ventricle, Right-ventricle, and Myocardium. We utilize an enhanced version of residual U-Net architecture on a large-scale cardiac MRI dataset. Handling the class imbalanced data issue using dice loss, the enhanced supervised model is able to achieve better dice scores in comparison with a vanilla U-Net model. We applied several augmentation techniques including histogram matching to increase the performance of our model in other domains. Also, we introduce a simple but efficient semi-supervised segmentation method to improve segmentation results without the need for large labeled data. Finally, we applied our method on two benchmark datasets, STACOM2018, and MMs 2020 challenges, to show the potency of the proposed model. The effectiveness of our proposed model is demonstrated by the quantitative results. The model achieves average dice scores of 0.921, 0.926, and 0.891 for Left-ventricle, Right-ventricle, and Myocardium respectively.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıSIU 2021 - 29th IEEE Conference on Signal Processing and Communications Applications, Proceedings
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)9781665436496
DOI'lar
Yayın durumuYayınlandı - 9 Haz 2021
Etkinlik29th IEEE Conference on Signal Processing and Communications Applications, SIU 2021 - Virtual, Istanbul, Turkey
Süre: 9 Haz 202111 Haz 2021

Yayın serisi

AdıSIU 2021 - 29th IEEE Conference on Signal Processing and Communications Applications, Proceedings

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???29th IEEE Conference on Signal Processing and Communications Applications, SIU 2021
Ülke/BölgeTurkey
ŞehirVirtual, Istanbul
Periyot9/06/2111/06/21

Bibliyografik not

Publisher Copyright:
© 2021 IEEE.

Finansman

ACKNOWLEDGMENTS This paper has been produced benefiting from the 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No: 118C353). However, the entire responsibility of the paper belongs to the owner of the paper. The financial support received from TUBITAK does not mean that the content of the publication is approved in a scientific sense by TUBITAK.

FinansörlerFinansör numarası
TUBITAK118C353

    Parmak izi

    Semi-supervised segmentation of multi-vendor and multi-center cardiac MRI' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

    Alıntı Yap