Brain Tumour Segmentation and Edge Detection Using Self-Supervised Learning
International Journal of Online and Biomedical Engineering (iJOE) · 18.04.2025 · 21 (05) · 127-141
DOI: 10.3991/ijoe.v21i05.53405 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Online and Biomedical Engineering (iJOE), online erschienen am 18.04.2025. Verfasst von Dasith Samarasinghe und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Brain tumour segmentation is critical in medical image analysis, facilitating diagnosis and treatment planning in neurosurgery. Brain tumour segmentation with supervised learning shows robust results in medical imaging; however, it requires a sufficient amount of annotated data for effective learning. It is important to detect boundaries of tumour subregions accurately in fine-grained segmentation. We propose a novel approach that uses a unique dual-decoder architecture, focusing on edge identification and segmentation accuracy enhancement. Utilising a dual-decoder 3D-UNet model, we prioritise accuracy and fine-grained details in tumour segmentation and introduce an additional tumour edge detection task, aiming to move beyond traditional single-decoder approaches. Incorporating a 3D SimSiam network as the self-supervised pretraining technique, we aim to address the limitation of annotated data and enhance the segmentation accuracy. Our model surpasses many supervised variants of U-net architectures and self-supervised approaches, highlighting the importance of edge detection in tumour segmentation. The proposed approach enhances segmentation accuracy by showing an accuracy of 98.1% and provides critical boundary details for clinical decision-making. Visualisations of segmentation and edge masks further validate the effectiveness of the proposed method.
Zitieren
APA
Samarasinghe, D., Wickramasinghe, D., Wijerathne, T., Meedeniya, D., & Yogarajah, P. (2025). Brain Tumour Segmentation and Edge Detection Using Self-Supervised Learning. International Journal of Online and Biomedical Engineering (iJOE), 21(05), 127-141. https://doi.org/10.3991/ijoe.v21i05.53405
Vancouver
Samarasinghe D, Wickramasinghe D, Wijerathne T, Meedeniya D, Yogarajah P. Brain Tumour Segmentation and Edge Detection Using Self-Supervised Learning. International Journal of Online and Biomedical Engineering (iJOE). 2025;21(05):127-141. doi:10.3991/ijoe.v21i05.53405
BibTeX
@article{Samarasinghe2025,
author = {Samarasinghe, Dasith and Wickramasinghe, Deshan and Wijerathne, Theshan and Meedeniya, Dulani and Yogarajah, Pratheepan},
title = {Brain Tumour Segmentation and Edge Detection Using Self-Supervised Learning},
journal = {International Journal of Online and Biomedical Engineering (iJOE)},
year = {2025},
volume = {21},
number = {05},
pages = {127--141},
doi = {10.3991/ijoe.v21i05.53405}
}
EUVIMED