Strategies for Class-Imbalanced Learning in Multi-Sensor Medical Imaging
Sensors · 23.03.2026 · 26 (6) · 1998
DOI: 10.3390/s26061998 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 23.03.2026. Verfasst von Da Zhou und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biophysics, School of Basic Medical Sciences, Peking University, Beijing 100191, China. Hauptthemen laut MEDLINE: Diagnostic Imaging, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Beijing, China, Open Research Fund of Beijing Key Laboratory of Magnetic Resonance Imaging Devices and Technology, Open Research Fund of the National Center for Protein Sciences at Peking University in Beijing.
Abstract (Originalsprache)
This narrative critical review addresses class imbalance in medical imaging, particularly within the context of multi-sensor and multi-modal environments, poses a critical challenge to developing reliable AI diagnostic systems. The integration of heterogeneous data from sources like CT, MRI, and PET presents a unique opportunity to address data scarcity for rare conditions through fusion techniques. This review provides a structured analysis of strategies to tackle class imbalance, categorizing them into data-centric (e.g., advanced resampling like SMOTE-ENC for mixed data types, GAN-based synthesis) and model-centric (e.g., loss function engineering, transfer learning, and ensemble methods) approaches. Crucially, we highlight how multi-sensor feature fusion and decision-level fusion paradigms can inherently enrich representations for minority classes, offering a powerful frontier beyond single-modality learning. We evaluate each method’s merits, clinical viability, and compliance considerations (e.g., FDA). Finally, we identify emerging trends where imbalance-aware learning synergizes with multi-sensor fusion frameworks, federated learning, and explainable AI, charting a roadmap toward robust, equitable, and clinically deployable diagnostic tools. Our quantitative synthesis shows that data-centric strategies can improve minority class recall by 12–35% in datasets with imbalance ratios (majority:minority) ≥10:1, while model-centric strategies achieve an average AUC improvement of 0.08–0.21 in multi-sensor medical imaging tasks with sample sizes ranging from 50 to 50,000.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biophysics, School of Basic Medical Sciences, Peking University, Beijing 100191, China.
- Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment, Peking University Third Hospital, Beijing 100191, China.
- Key Laboratory for Neuroscience, Ministry of Education and National Health Commission, Beijing 100191, China.
- Institute of Medical Technology, Peking University Health Science Center, Beijing 100191, China.
ORCID-Profile: Xinrui Huang
Förderung
- Natural Science Foundation of Beijing, China
- Open Research Fund of Beijing Key Laboratory of Magnetic Resonance Imaging Devices and Technology
- Open Research Fund of the National Center for Protein Sciences at Peking University in Beijing
- National Natural Science Foundation of China
- Research Project on Medical Imaging Standards and Innovative Development
Zitieren
APA
Zhou, D., Gao, S., & Huang, X. (2026). Strategies for Class-Imbalanced Learning in Multi-Sensor Medical Imaging. Sensors, 26(6), 1998. https://doi.org/10.3390/s26061998
Vancouver
Zhou D, Gao S, Huang X. Strategies for Class-Imbalanced Learning in Multi-Sensor Medical Imaging. Sensors. 2026;26(6):1998. doi:10.3390/s26061998
BibTeX
@article{Zhou2026,
author = {Zhou, Da and Gao, Song and Huang, Xinrui},
title = {Strategies for Class-Imbalanced Learning in Multi-Sensor Medical Imaging},
journal = {Sensors},
year = {2026},
volume = {26},
number = {6},
pages = {1998},
doi = {10.3390/s26061998}
}
EUVIMED