A novel algorithmic approach of progressive transfer learning for MRI braintumor classification using VGG16 architecture
Journal of Interdisciplinary Mathematics · 2026 · 29 (4) · 1023-1031
DOI: 10.47974/jim-2572 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Interdisciplinary Mathematics, 2026. Verfasst von Sunil Kumar Agarwal und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Many diseases exist worldwide. Among them, a brain tumour is the most dangerous and critical disease for human survival. Early detection of this abnormality is essential for effective patient treatment. The objective of the present research is to define a progressive transfer learning technique with the help of the VGG16 model to accurately identify and classify human brain tumour MR images. The results provide evidence of the significance of the applied framework. The experimental efficiency of the framework was 98.15%, demonstrating the importance of the VGG16 model over other frameworks. Moreover, future work suggests important concepts related to improving the fine-tuning process, regularisation methods, and other related work to enhance the overall performance of the suggested framework.
Zitieren
APA
Agarwal, S. K., Gupta, Y. K., & Dadheech, P. (2026). A novel algorithmic approach of progressive transfer learning for MRI braintumor classification using VGG16 architecture. Journal of Interdisciplinary Mathematics, 29(4), 1023-1031. https://doi.org/10.47974/jim-2572
Vancouver
Agarwal SK, Gupta YK, Dadheech P. A novel algorithmic approach of progressive transfer learning for MRI braintumor classification using VGG16 architecture. Journal of Interdisciplinary Mathematics. 2026;29(4):1023-1031. doi:10.47974/jim-2572
BibTeX
@article{Agarwal2026,
author = {Agarwal, Sunil Kumar and Gupta, Yogesh Kumar and Dadheech, Pankaj},
title = {A novel algorithmic approach of progressive transfer learning for MRI braintumor classification using VGG16 architecture},
journal = {Journal of Interdisciplinary Mathematics},
year = {2026},
volume = {29},
number = {4},
pages = {1023--1031},
doi = {10.47974/jim-2572}
}
EUVIMED