Meta-transfer Learning for Brain Tumor Segmentation: Within and Beyond Glioma.

Autor:	Yan S; School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia., Liu S; Centre for Health Informatics, Australian Institute of Health Innovation, Faculty of Medicine, Human and Health Sciences, Macquarie University, Sydney, NSW, Australia.; Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Faculty of Medicine, Human and Health Sciences, Macquarie University, Sydney, NSW, Australia., Di Ieva A; Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Faculty of Medicine, Human and Health Sciences, Macquarie University, Sydney, NSW, Australia.; Macquarie Neurosurgery & Spine, MQ Health, Macquarie University Hospital, Sydney, NSW, Australia.; Department of Neurosurgery, Nepean Blue Mountains Local Health District, Kingswood, NSW, Australia.; Centre for Applied Artificial Intelligence, School of Computing, Macquarie University, Sydney, NSW, Australia., Pagnucco M; School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia., Song Y; School of Computer Science and Engineering, University of New South Wales, Sydney, NSW, Australia. yang.song1@unsw.edu.au.
Jazyk:	angličtina
Zdroj:	Advances in experimental medicine and biology [Adv Exp Med Biol] 2024; Vol. 1462, pp. 221-230.
DOI:	10.1007/978-3-031-64892-2_13
Abstrakt:	In recent years, numerous algorithms have emerged for the segmentation of brain tumors, propelled by both the advancements of deep learning techniques and the influential open benchmark set by the BraTS challenge. This chapter provides an overview of the background that gave rise to automated brain tumor segmentation algorithms, reviews representative deep learning-based approaches, and reflects their limits on clinical applicability. While these algorithms showcase promising results in fully supervised settings, they may not perform well to other types of brain tumors without substantial samples for model re-training or fine-tuning. Recognizing this limitation, we explore a new learning framework designed to facilitate fast adaptation to new tumor types with only a few labeled data samples. (© 2024. The Author(s), under exclusive license to Springer Nature Switzerland AG.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu