An Optimized Fine-Tuned Transfer Learning Based Resnet-101 Model To Detect Brain Tumor From MRI

Abdul Wahab; Moynul Hoque

doi:10.36948/ijfmr.2026.v08i03.80478

An Optimized Fine-Tuned Transfer Learning Based Resnet-101 Model To Detect Brain Tumor From MRI

Author(s)	Md. Abdul Wahab, Md. Moynul Hoque
Country	Bangladesh
Abstract	A brain tumor is a life-threatening neurological condition with a low survival rate if not adequately treated. Early detection of brain tumors is essential to prevent any tragic outcomes. Technological advancements have enabled the utilization of computer-aided design for tumor detection through imaging modalities such as MRI and CT scans. MRI is predominantly utilized because to its superior image quality and dependence on non-ionizing radiation. This paper proposes a deep transfer learning model with a fine-tuned ResNet-101 for brain tumor detection. ResNet-101 possesses the potential to train a significantly deeper model with a high accuracy rate. This research employs our optimized suggested layers in the ResNet-101 model of a deep convolutional neural network to enhance accuracy and effectively detect brain tumors. The datasets comprise the Br35H dataset and a compilation of publicly accessible datasets. Image enhancement techniques employ diverse filters to augment image quality. Albumentation, a data augmentation technique, is employed to enhance the training of our suggested model. To evaluate optimal performance, we investigate all potential combinations of deep learning-based feature extractors and classifiers. The validation accuracy 99.83% which indicates that the proposed technique surpasses existing models regarding accuracy.
Keywords	Brain tumor, Convolution Neural Networks, Deep learning, ResNet-101
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-06-05
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.80478

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An Optimized Fine-Tuned Transfer Learning Based Resnet-101 Model To Detect Brain Tumor From MRI

Share this