AUTHOR=Sharma Sarang , Gupta Sheifali , Gupta Deepali , Juneja Sapna , Mahmoud Amena , El–Sappagh Shaker , Kwak Kyung-Sup 

TITLE=Transfer learning-based modified inception model for the diagnosis of Alzheimer's disease

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2022.1000435

DOI=10.3389/fncom.2022.1000435

ISSN=1662-5188

ABSTRACT=Alzheimer’s Disease (AD) is a neurodegenerative ailment. This ailment sluggishly eradicates memory and gradationally weakens the introductory cognitive functions and capacities of the body similar as allowing, flashing back and logic. Thus, to diagnose this complaint CT, MRI, PET, etc. are enforced. Still, these ways are time consuming and occasionally yield inaccurate results. Thus, to avoid similar lengthy and time-consuming ways, deep learning models are enforced that are lower time consuming, yield results with lesser accuracy and could be enforced with ease. This paper proposes transfer literacy grounded modified Inception model with pre-processing ways of normalization and data addition. The proposed model achieved the accuracy of 94.92 and sensitivity of 94.94. It's concluded from the results that proposed model performs better as compared to other state- of- art models. For training purpose, the dataset has been taken from the Kaggle having 6200 images with 896 Mild Demented (M.D) images, 64 Moderate Demented (Mod.D) images, 3200 Non-Demented (N.D) images and 1966 veritably Mild Demented (V.M.D) images. With similar results these models could be employed for developing clinically useful results that are suitable to descry announcement in MRI images.