Biosignal and Imaging Informatics: 2024 Review and Emerging Trends
- 1Institute of Health Care Engineering with European Testing Center of Medical Devices, Graz Univer-sity of Technology Austria
- 2Medical Imaging Computing Lab (MICLab), School of Electrical and Computer Engineering, University of Campinas Brazil
- 3Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Braunschweig Germany
Abstract
Objectives: This review identifies and showcases key research contributions and emerging trends in Biosignal and Imaging Informatics (BII) published in 2024. The review focus is on innovative studies demonstrating translational potential, computational rigor, and clinical relevance.
Methods: A structured literature search was conducted in PubMed and Scopus, targeting publications up to January 2025. Queries were designed using domain-specific MeSH terms and keywords related to biosignal (sensors and signals) and imaging informatics. Only journals with at least three relevant articles were considered to ensure quality. After removing duplicates, titles and abstracts were assessed independently using a three-point Likert scale. Fourteen high-scoring papers underwent full-text evaluation, and finally, twelve were reviewed by external reviewers and editors. From this process, two standout papers—one from each subfield—were selected as the best contributions.
Results: Out of 399 reviewed articles, twelve were shortlisted for external evaluation. The selected best papers exemplify beyond state-of-the-art innovation: a spiking neural network model for low-power, real-time detection of sleep apnea from single-lead ECG signals, and a universal vision-language model for organ segmentation and tumor detection in abdominal CT imaging. Other notable works addressed challenges in privacy-preserving learning, efficient signal modeling, annotation uncertainty, and real-time clinical deployment, highlighting the field’s evolution toward integrative and practical solutions.
Conclusion: The 2024 BII review reflects a clear transition from algorithmic exploration to clinically viable implementations. Featured studies emphasize not only high-performing machine learning and deep learning techniques, but also address critical issues such as energy efficiency, data privacy, gen-eralizability, and interpretability. Together, they represent the maturing landscape of BII, where com-putational advances increasingly align with the needs of modern, patient-centered healthcare.
Related
- Functional Brain Imaging in Knee Osteoarthritis: A Bibliometric Analysis of Research Trends and Emerging Clinical Perspectives
- Modeling Biological Systems: Trends in Biosystem Identification and Biosignal Coupling
- Artificial intelligence in breast cancer research: a systematic review and bibliometric analysis of emerging trends and future directions
- Emerging Trends in Pediatric Disease Management and Preventive Care: A Systematic Review.
- From Static Atlases to Intelligent Learning Systems: A Scoping Review of Imaging-Based Tools and Emerging Artificial Intelligence Applications for Facial Aesthetic Education and Training
BibTeX
@article{baumgartner2026biosignal,
title = {{Biosignal and Imaging Informatics: 2024 Review and Emerging Trends}},
author = {Christian Baumgartner and Leticia Rittner and Thomas M. Deserno},
journal = {Yearbook of Medical Informatics},
year = {2026},
month = nov,
doi = {10.1055/s-0046-1816600},
url = {https://doi.org/10.1055/s-0046-1816600},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Biosignal and Imaging Informatics: 2024 Review and Emerging Trends
AU - Christian Baumgartner
AU - Leticia Rittner
AU - Thomas M. Deserno
PY - 2026
DA - 2026/11/03
JO - Yearbook of Medical Informatics
DO - 10.1055/s-0046-1816600
UR - https://doi.org/10.1055/s-0046-1816600
AB - Objectives: This review identifies and showcases key research contributions and emerging trends in Biosignal and Imaging Informatics (BII) published in 2024. The review focus is on innovative studies demonstrating translational potential, computational rigor, and clinical relevance. Methods: A structured literature search was conducted in PubMed and Scopus, targeting publications up to January 2025. Queries were designed using domain-specific MeSH terms and keywords related to biosignal (sensors and signals) and imaging informatics. Only journals with at least three relevant articles were considered to ensure quality. After removing duplicates, titles and abstracts were assessed independently using a three-point Likert scale. Fourteen high-scoring papers underwent full-text evaluation, and finally, twelve were reviewed by external reviewers and editors. From this process, two standout papers—one from each subfield—were selected as the best contributions. Results: Out of 399 reviewed articles, twelve were shortlisted for external evaluation. The selected best papers exemplify beyond state-of-the-art innovation: a spiking neural network model for low-power, real-time detection of sleep apnea from single-lead ECG signals, and a universal vision-language model for organ segmentation and tumor detection in abdominal CT imaging. Other notable works addressed challenges in privacy-preserving learning, efficient signal modeling, annotation uncertainty, and real-time clinical deployment, highlighting the field’s evolution toward integrative and practical solutions. Conclusion: The 2024 BII review reflects a clear transition from algorithmic exploration to clinically viable implementations. Featured studies emphasize not only high-performing machine learning and deep learning techniques, but also address critical issues such as energy efficiency, data privacy, gen-eralizability, and interpretability. Together, they represent the maturing landscape of BII, where com-putational advances increasingly align with the needs of modern, patient-centered healthcare.
SN - 0943-4747
SN - 2364-0502
ER -