A review of the evolution and challenges of few-shot medical image semantic segmentation
PeerJ Computer Science · 24.04.2026 · 12 · e3761
DOI: 10.7717/peerj-cs.3761 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 24.04.2026. Verfasst von Hong Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 108 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural science Foundation project of Gansu Provincial Science and Technology Department, Science and Technology Plan Project of Gansu Province.
Abstract (Originalsprache)
Image segmentation, as a fundamental task in computer vision, aims to achieve pixel-level delineation between target regions and background. In the field of medical image analysis, traditional segmentation methods heavily rely on large-scale, high-quality annotated datasets. However, expert-level annotations for medical images require substantial professional human resources ( e.g ., radiologists performing slice-by-slice delineation of lesions) and face challenges such as cross-institutional data heterogeneity. To address this data bottleneck, few-shot medical image semantic segmentation has emerged as a promising paradigm. By leveraging strategies such as meta-learning, metric learning, and other related approaches, these approaches enable models to accurately segment the target region and achieve effective generalization to novel categories using minimal annotated samples (typically ≤15 instances per class), thereby significantly reducing dependence on annotated data. This article systematically explores foundational concepts such as medical image segmentation methods, benchmark datasets, performance evaluation metrics, and main approaches for few-shot medical image segmentation. Distinct from existing review literature, our work focuses on summarizing prototype-based few-shot medical image semantic segmentation algorithms. We analyze network architectures from a problem-oriented perspective and critically examine limitations in current methodologies. Finally, grounded in our analysis of current challenges, we propose forward-looking perspectives for future advancements.
Förderung
- National Natural Science Foundation of China
- Natural science Foundation project of Gansu Provincial Science and Technology Department
- Science and Technology Plan Project of Gansu Province
- Cuiying Science and Technology Innovation Program
- Gansu Haizhi Characteristic Demonstration Project
Zitieren
APA
Zhao, H., Chen, Q., Meng, Y., Hu, W., Yu, C., Gao, Z., & Chang, Z. (2026). A review of the evolution and challenges of few-shot medical image semantic segmentation. PeerJ Computer Science, 12, e3761. https://doi.org/10.7717/peerj-cs.3761
Vancouver
Zhao H, Chen Q, Meng Y, Hu W, Yu C, Gao Z, et al. A review of the evolution and challenges of few-shot medical image semantic segmentation. PeerJ Computer Science. 2026;12:e3761. doi:10.7717/peerj-cs.3761
BibTeX
@article{Zhao2026,
author = {Zhao, Hong and Chen, Qingfeng and Meng, Yao and Hu, Wanjun and Yu, Chenglin and Gao, Zhenshan and Chang, Zhaobin},
title = {A review of the evolution and challenges of few-shot medical image semantic segmentation},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3761},
doi = {10.7717/peerj-cs.3761}
}
EUVIMED