Early Detection of Alzheimer’s Disease Using Curvelet Transform and Deep Learning with Voice-Enabled NeuroScan+ Interface

View at publisher Summarise with VIRAT
Authors: S. Ijaz Ahmed, M. Dharanibalan, V. S. Dhanussh Raj, M. Hemalatha
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Early diagnosis of Alzheimer’s Disease (AD) is crucial for timely clinical intervention but remains challenging due to subtle structural changes in early stages. This work proposes a multimodal diagnostic framework integrating Curvelet-based MRI preprocessing, a 3D Convolutional Neural Network (3DCNN), and a voice-accessible interface to support hands-free clinical interaction. Curvelet Transform enhances fine-scale edges and textures in structural MRI scans, improving feature extraction, while the 3D-CNN leverages volumetric spatial information for accurate classification of AD, Mild Cognitive Impairment (MCI), and Normal Controls (NC). A voice-enabled NeuroScan+ module facilitates clinician interaction and accelerates workflow with high recognition accuracy and low latency. Experimental evaluation on ADNI and OASIS datasets demonstrates an average accuracy of 94.1%, supported by Grad-CAM interpretability and statistically significant improvements over baseline CNN models. The results highlight the potential of combining advanced image preprocessing, deep learning, and voice accessibility for practical, early-stage Alzheimer’s diagnosis in clinical environments.

Fields of Study & Subjects

Dementia and Cognitive Impairment Research Artificial Intelligence in Healthcare Medical Image Segmentation Techniques

Publication details

Journal / source
International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS)
Pages
1–5
Publication date
26 February 2026
Language
EN