Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195343,
        author = {BODDU SAI VARDHAN and CHINTADA SIREESHA and Bammidi Danthiswararao and Erotu Santhoshi and A. Srikar},
        title = {Explainable Alzheimer Detection Using Transfer Learning and Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7580-7582},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195343},
        abstract = {Alzheimer’s disease is a progressive neurodegenerative disorder that causes memory loss, cognitive decline, and behavioural impairment. Early detection of Alzheimer’s disease is essential for improving treatment outcomes and patient care. Traditional diagnostic approaches rely on manual analysis of brain Magnetic Resonance Imag-ing (MRI) scans by neurologists, which is time-consuming and prone to human interpretation errors. To address this issue, this paper proposes an automated Alzheimer’s disease detection system using transfer learning and Explainable Artificial Intelligence (XAI). The proposed system utilizes the EfficientNetB3 deep learning architecture to classify MRI brain images into four stages: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. Transfer learning enables efficient feature extraction while improving clas-sification accuracy even with limited medical datasets. To enhance model transparency, Grad-CAM and LIME techniques are integrated to visualize the brain regions influencing the model’s prediction. The system is im-plemented as a web-based application using Stream lit and deployed on a cloud platform, allowing users to upload MRI images and obtain real-time predictions. Experimental results show that the proposed model achieves an accuracy of approximately 91.2%, demon-strating its effectiveness as a decision-support tool for assisting medical professionals in the early detection of Alzheimer’s disease.},
        keywords = {Alzheimer’s Disease, Transfer Learning, EfficientNetB3, Explainable Artificial Intelligence, Grad-CAM, LIME, MRI Image Classification, Deep Learning},
        month = {March},
        }