EFFICIENT BRAIN TUMOR DETECTION USING DEEP TRANSFER LEARNING
Advances and Applications in Statistics · 06.08.2026 · 93 (8) · 963-991
DOI: 10.17654/0972361726046 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances and Applications in Statistics, online erschienen am 06.08.2026. Verfasst von Muazzam Ali und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Statistical studies for investigation of tumor detection reveal a very shocking fact that 20% of the normal living people on the globe are expected to develop cancer of one or other type in their lifetimes. Moreover, this malicious disease could be controlled by saving 40% patients subject to early detection and identification of the cancer grades and consequently going through the required treatment timely. WHO (World Health Organization) declares tumors into different grades based on their characteristics, i.e., from grade 1 to grade 4. Each grade shows progressively increasing level of danger among human beings. Hence, scientists are busy in devising methods, and technologies that can be expedited in such a unique fashion such that efficient use of these technologies could help in curing those diseases. The published literature shows that these AI based methods are proven methods of detecting and classifying any abnormality in the given MRI of a patient without much supervisory control. Hence, computationally efficient techniques can be applied through deep learning requiring lesser computational cost. This paper applies a deep FineNetB0 model to two publicly available datasets for identification of different brain cancer grades. The datasets are identified as I and II. The proposed AI based techniques can help radiologists in identification of diseases timely without any extra effort. The dataset I containing 3064 MRI images of 233 patients shows a testing accuracy of 99.51% and a testing accuracy of 99.50% for the 1008 MRI images of 57, indicated as Dataset II.
Zitieren
APA
Ali, M., Shaikh, A. Z., Ahmed, S., Hidayat, K., & Naqvi, S. (2026). EFFICIENT BRAIN TUMOR DETECTION USING DEEP TRANSFER LEARNING. Advances and Applications in Statistics, 93(8), 963-991. https://doi.org/10.17654/0972361726046
Vancouver
Ali M, Shaikh AZ, Ahmed S, Hidayat K, Naqvi S. EFFICIENT BRAIN TUMOR DETECTION USING DEEP TRANSFER LEARNING. Advances and Applications in Statistics. 2026;93(8):963-991. doi:10.17654/0972361726046
BibTeX
@article{Ali2026,
author = {Ali, Muazzam and Shaikh, Aamir Zeb and Ahmed, Shakil and Hidayat, Kiran and Naqvi, Shabbar},
title = {EFFICIENT BRAIN TUMOR DETECTION USING DEEP TRANSFER LEARNING},
journal = {Advances and Applications in Statistics},
year = {2026},
volume = {93},
number = {8},
pages = {963--991},
doi = {10.17654/0972361726046}
}
EUVIMED