Supervised segmentation with domain adaptation for small sampled orbital CT images

Abstract Deep neural networks have been widely used for medical image analysis. However, the lack of access to a large-scale annotated dataset poses a great challenge, especially in the case of rare diseases or new domains for the research society. Transfer of pre-trained features from the relativel...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of Computational Design and Engineering 2022-04, Vol.9 (2), p.783-792
Hauptverfasser: Suh, Sungho, Cheon, Sojeong, Choi, Wonseo, Chung, Yeon Woong, Cho, Won-Kyung, Paik, Ji-Sun, Kim, Sung Eun, Chang, Dong-Jin, Lee, Yong Oh
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Abstract Deep neural networks have been widely used for medical image analysis. However, the lack of access to a large-scale annotated dataset poses a great challenge, especially in the case of rare diseases or new domains for the research society. Transfer of pre-trained features from the relatively large dataset is a considerable solution. In this paper, we have explored supervised segmentation using domain adaptation for optic nerve and orbital tumour, when only small sampled CT images are given. Even the lung image database consortium image collection (LIDC-IDRI) is a cross-domain to orbital CT, but the proposed domain adaptation method improved the performance of attention U-Net for the segmentation in public optic nerve dataset and our clinical orbital tumour dataset by 3.7% and 13.7% in the Dice score, respectively. The code and dataset are available at https://github.com/cmcbigdata. Graphical Abstract Graphical Abstract
ISSN:2288-5048
2288-4300
2288-5048
DOI:10.1093/jcde/qwac029