A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis
PeerJ Computer Science · 10.06.2025 · 11 · e2920
DOI: 10.7717/peerj-cs.2920 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 10.06.2025. Verfasst von Seref Sagiroglu und 11 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering, Gazi University, Ankara, Turkey. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 229 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Turkish Brain, Digital Transformation Office of the Presidency of the Republic of Turkiye.
Abstract (Originalsprache)
This article presents a new benchmark MRI dataset called the Gazi Brains Dataset 2020, containing MRI images of 100 patients, and introduces initial experimental results performed on this dataset in comparison with available brain MRI datasets. Furthermore, the dataset is analyzed using eight different deep learning models for high-grade glioma tumor prediction, classification, and detection tasks. Additionally, this study demonstrates the results of an explainable Artificial Intelligence (XAI) approach applied to the trained models. To demonstrate the utility of the proposed dataset, different deep learning models were applied to the problem, and these models were tested on various data and models applied for various tasks such as region of interest extraction, whole tumor segmentation, prediction, detection, and classification with accuracy, precision, recall, and F1-score. The experimental results indicate that the dataset is highly effective for multiple purposes, and the models reached significant results with successful F1-scores ranging between 93.2% and 96.4%. ROI and whole tumor segmentations were successfully performed and compared with seven algorithms with accuracies of 87.61% and 97.18%. The Grad-CAM model also demonstrated satisfactory accuracy across the tests that were conducted. Moreover, this study explores the application of XAI to the trained models, providing interpretability and insights into the decision-making processes. The findings signify that this dataset holds significant potential for various future research directions, including age estimation, gender detection, causal inference with XAI, and disease-related survival analysis.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Engineering, Gazi University, Ankara, Turkey.
- Computer Engineering, Amasya University, Amasya, Turkey.
- Presidency of The Republic of Türkiye, Digital Transformation Office, Ankara, Turkey.
- Medicine, Gazi University, Ankara, Turkey.
- Neurosurgery, Kulu State Hospital, Konya, Turkey.
- Internal Medicine, Icahn School of Medicine, New York City, United States.
ORCID-Profile: Alp Özgün Börcek, Yilmaz Atay, Mustafa Caglar Sahin, Okan Bilge Ozdemir
Förderung
- Turkish Brain
- Digital Transformation Office of the Presidency of the Republic of Turkiye
Zitieren
APA
Sagiroglu, S., Terzi, R., Celtikci, E., Börcek, A. Ö., Atay, Y., Arslan, B., Sahin, M. C., Nernekli, K., Demirezen, U., Ozdemir, O. B., Özdem Karaca, K., & Azgınoğlu, N. (2025). A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis. PeerJ Computer Science, 11, e2920. https://doi.org/10.7717/peerj-cs.2920
Vancouver
Sagiroglu S, Terzi R, Celtikci E, Börcek AÖ, Atay Y, Arslan B, et al. A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis. PeerJ Computer Science. 2025;11:e2920. doi:10.7717/peerj-cs.2920
BibTeX
@article{Sagiroglu2025,
author = {Sagiroglu, Seref and Terzi, Ramazan and Celtikci, Emrah and Börcek, Alp Özgün and Atay, Yilmaz and Arslan, Bilgehan and Sahin, Mustafa Caglar and Nernekli, Kerem and Demirezen, Umut and Ozdemir, Okan Bilge and Özdem Karaca, Kevser and Azgınoğlu, Nuh},
title = {A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis},
journal = {PeerJ Computer Science},
year = {2025},
volume = {11},
pages = {e2920},
doi = {10.7717/peerj-cs.2920}
}
EUVIMED