Title: Enhanced transfer learning techniques: a resilient multi-model framework for multi-class MRI brain tumour diagnosis

Authors: Rashmi Jolhe; Sudhir D. Sawarkar

Addresses: Department of Information Technology, Datta Meghe College of Engineering, Airoli, Navi Mumbai, Maharashtra, India ' Department of Computer Engineering, Datta Meghe College of Engineering, Airoli, Navi Mumbai, Maharashtra, India

Abstract: The diagnosis of brain tumours is difficult and primarily dependent on manual MRI evaluations, which can be laborious and prone to mistakes. We suggest a transfer learning strategy that makes use of pre-trained deep neural networks for effective MRI-based tumour classification in order to enhance this procedure. Our strategy handles the complexity of tumour detection and achieves 97.71% accuracy by fine-tuning six models. For radiologists, this model is a useful tool that improves diagnostic confidence and accuracy. Practical application in clinical settings is ensured by validation using real-world hospital data and a Kaggle dataset.

Keywords: deep learning; glioma; meningioma; pituitary; perfusion MRI.

DOI: 10.1504/IJAISC.2024.146624

International Journal of Artificial Intelligence and Soft Computing, 2024 Vol.8 No.4, pp.257 - 284

Received: 05 Jun 2024
Accepted: 29 Oct 2024
Published online: 09 Jun 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article