A Systematic Review of Deep Learning Approaches for Hepatopancreatic Tumor Segmentation
Journal of Imaging · 26.03.2026 · 12 (4) · 147
DOI: 10.3390/jimaging12040147 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Imaging, online erschienen am 26.03.2026. Verfasst von Razeen Hussain und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, 16146 Genoa, Italy. Die Arbeit nennt 117 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Deep learning has advanced rapidly in medical image segmentation, yet hepatopancreatic tumor delineation remains challenging due to low contrast, small lesion size, organ variability, and limited high-quality annotations. Existing reviews are outdated or overly broad, leaving recent architectural developments, training strategies, and dataset limitations insufficiently synthesized. To address this gap, we conducted a PRISMA 2020 systematic literature review of studies published between 2021 and 2026 on deep learning-based liver and pancreatic tumor segmentation. From 2307 records, 84 studies met inclusion criteria. U-Net variants continue to dominate, achieving strong liver segmentation but inconsistent tumor accuracy, while transformer-based and hybrid models improve global context modeling at higher computational cost. Attention mechanisms, boundary-refinement modules, and semi-supervised learning offer incremental gains, yet pancreatic tumor segmentation remains notably difficult. Persistent issues, including domain shift, class imbalance, and limited generalization across datasets, underscore the need for more robust architectures, standardized benchmarks, and clinically oriented evaluation. This review consolidates recent progress and highlights key challenges that must be addressed to advance reliable hepatopancreatic tumor segmentation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Informatics, Bioengineering, Robotics and Systems Engineering, University of Genoa, 16146 Genoa, Italy.
ORCID-Profile: Razeen Hussain, Muhammad Mohsin, Dadan Khan, Mohammad Zohaib
Zitieren
APA
Hussain, R., Mohsin, M., Khan, D., & Zohaib, M. (2026). A Systematic Review of Deep Learning Approaches for Hepatopancreatic Tumor Segmentation. Journal of Imaging, 12(4), 147. https://doi.org/10.3390/jimaging12040147
Vancouver
Hussain R, Mohsin M, Khan D, Zohaib M. A Systematic Review of Deep Learning Approaches for Hepatopancreatic Tumor Segmentation. Journal of Imaging. 2026;12(4):147. doi:10.3390/jimaging12040147
BibTeX
@article{Hussain2026,
author = {Hussain, Razeen and Mohsin, Muhammad and Khan, Dadan and Zohaib, Mohammad},
title = {A Systematic Review of Deep Learning Approaches for Hepatopancreatic Tumor Segmentation},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {4},
pages = {147},
doi = {10.3390/jimaging12040147}
}
EUVIMED