Deep learning for intracranial hemorrhage detection and classification in brain CT scans: a systematic review and hybrid model approach
Frontiers in Digital Health · 07.04.2026 · 8
DOI: 10.3389/fdgth.2026.1703634 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Frontiers in Digital Health, online erschienen am 07.04.2026. Verfasst von Harshith V und 15 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Engineering (Artificial Intelligence and Machine Learning), Vidyavardhaka College of Engineering, Mysuru, Karnataka, India. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Russian Science Foundation.
Abstract (Originalsprache)
Background
Intracranial hemorrhage (ICH) is a life-threatening medical emergency requiring rapid and accurate diagnosis. Non-contrast computed tomography (CT) remains the primary imaging modality for detecting acute hemorrhage. In recent years, machine learning (ML) and deep learning (DL) approaches have gained increasing attention for automated detection and classification of ICH and its subtypes. This systematic review aims to consolidate and critically analyze contemporary machine learning and deep learning methodologies applied to ICH detection and classification from non-contrast CT scans.
Methods
A comprehensive review of published studies was conducted focusing on ML and DL models developed for identifying ICH and its subtypes, including epidural, subdural, intraparenchymal, intraventricular, and subarachnoid hemorrhages. The reviewed techniques encompass conventional convolutional neural networks (CNNs), three-dimensional CNNs, hybrid and ensemble frameworks, and emerging transformer-based architectures. Preprocessing strategies such as Hounsfield Unit windowing, skull stripping, and data augmentation were examined. Additionally, explainable artificial intelligence (XAI) approaches, including Grad-CAM, were evaluated for enhancing model interpretability.
Results
Recent studies demonstrate promising diagnostic performance across multiple deep learning architectures, with improved sensitivity and specificity for subtype classification. Hybrid and transformer-based models show enhanced feature representation capabilities. Preprocessing techniques and explainability methods contribute significantly to model robustness and clinical interpretability.
Conclusion
Machine learning and deep learning models exhibit substantial potential in automated ICH detection and classification from non-contrast CT scans. However, challenges remain regarding generalizability, dataset heterogeneity, and clinical validation. Future research should emphasize large-scale multi-center validation, model interpretability, and integration into real-world clinical workflows to enable effective translation into routine neuroimaging practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science and Engineering (Artificial Intelligence and Machine Learning), Vidyavardhaka College of Engineering, Mysuru, Karnataka, India.
- Department of Pharmacology, JSS Medical College & Hospital, JSS Academy of Higher Education & Research, Mysuru, Karnataka, India.
- Department of Cell Biology and Molecular Genetics, SDU Academy of Higher Education & Research, Tamka, Kolar, Karnataka, India.
- Department of Biotechnology, Acharya Institute of Technology, Bengaluru, Karnataka, India.
- Department of Radio Diagnosis, JSS Medical College & Hospital, JSS Academy of Higher Education & Research, Mysuru, Karnataka, India.
- School of Physical Sciences, Amrita Vishwa Vidyapeetham, Mysuru, Karnataka, India.
Förderung
- Russian Science Foundation
Zitieren
APA
V, H., Athray, B., Murthy, L. T., Joshi, S., Ayoob, A. A., M R, S. C., Reddy, P., Raj, R., Patil, V., Benny, D., Kollur, S. P., Abass, K. S., Stupin, V., Pradeep, S., Shivamallu, C., & Silina, E. (2026). Deep learning for intracranial hemorrhage detection and classification in brain CT scans: a systematic review and hybrid model approach. Frontiers in Digital Health, 8. https://doi.org/10.3389/fdgth.2026.1703634
Vancouver
V H, Athray B, Murthy LT, Joshi S, Ayoob AA, M R SC, et al. Deep learning for intracranial hemorrhage detection and classification in brain CT scans: a systematic review and hybrid model approach. Frontiers in Digital Health. 2026;8. doi:10.3389/fdgth.2026.1703634
BibTeX
@article{V2026,
author = {V, Harshith and Athray, Bhargavram and Murthy, Likhitha T and Joshi, Samyukta and Ayoob, Ameena Amreen and M R, Sai Chakith and Reddy, Pruthvish and Raj, Ranjith and Patil, Vikram and Benny, Deepak and Kollur, Shiva Prasad and Abass, Kasim Sakran and Stupin, Victor and Pradeep, Sushma and Shivamallu, Chandan and Silina, Ekaterina},
title = {Deep learning for intracranial hemorrhage detection and classification in brain CT scans: a systematic review and hybrid model approach},
journal = {Frontiers in Digital Health},
year = {2026},
volume = {8},
doi = {10.3389/fdgth.2026.1703634}
}
EUVIMED