Hybrid optimized deep fuzzy clustering-based segmentation and Deep Maxout Network for Alzheimer’s disease classification
Biomedical Signal Processing and Control · 2024-07 · 93 · 106118
DOI: 10.1016/j.bspc.2024.106118 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2024-07. Verfasst von T.S. Sindhu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben.
Themen: Demenz
Abstract (Originalsprache)
Alzheimer ’ s disease (AD) is a type of dementia, which causes the neuron cell damages. The deep model is used to discover the quick and precise detection of AD. It has acquired immense interest for researchers, but the effective detection of AD with reliable biomarkers is a challenging task. A novel technique is developed using the deep model for AD classification. The Gaussian filter technique is used to remove the noise during the pre-processing stage. The next step is to segment the Region of Interest (RoI) using Deep Fuzzy Clustering (DFC) that has been optimized with the hyperparameters, which is tuned by the Sea Lion Deer Hunting Optimization (SLDHO) al-gorithm, which is developed by fusing the SLOA (Sea Lion Optimization Algorithm) and DHOA (Deer Hunting Optimization Algorithm). The features such as textual features, CNN (Convolutional Neural network) features and statistical features are obtained. For better processing, more suited data are used and the augmentation of data is performed. The classification process is done based on the Deep Maxout network (DMN), and it is trained by the developed SLDHO model. Additionally, the DMN classifies AD into five types Cognitive Impairment (MCI), Early Mild Cognitive Impairment (EMCI), AD, Mild Cognitively Normal (CN), and Late Early Mild Cognitive Impairment (LMCI). The DFC-SLDHO-based DMN outperformed with the maximum specificity, sensitivity and accuracy of 89.8 %, 84.4 % and 87.4 %.
Zitieren
APA
Sindhu, T., Kumaratharan, N., & Anandan, P. (2024). Hybrid optimized deep fuzzy clustering-based segmentation and Deep Maxout Network for Alzheimer’s disease classification. Biomedical Signal Processing and Control, 93, 106118. https://doi.org/10.1016/j.bspc.2024.106118
Vancouver
Sindhu T, Kumaratharan N, Anandan P. Hybrid optimized deep fuzzy clustering-based segmentation and Deep Maxout Network for Alzheimer’s disease classification. Biomedical Signal Processing and Control. 2024;93:106118. doi:10.1016/j.bspc.2024.106118
BibTeX
@article{Sindhu2024,
author = {Sindhu, T.S. and Kumaratharan, N. and Anandan, P.},
title = {Hybrid optimized deep fuzzy clustering-based segmentation and Deep Maxout Network for Alzheimer’s disease classification},
journal = {Biomedical Signal Processing and Control},
year = {2024},
volume = {93},
pages = {106118},
doi = {10.1016/j.bspc.2024.106118}
}
EUVIMED