人工智能
计算机科学
特征(语言学)
疾病
模式识别(心理学)
深度学习
机器学习
医学
鉴定(生物学)
深层神经网络
作者
Deepthi K Moorthy,P. Nagaraj
标识
DOI:10.1080/17582024.2025.2554495
摘要
BACKGROUND: Alzheimer's disease (AD) is considered to be one of the neurodegenerative diseases with possible cognitive deficits related to dementia in human subjects. High priority should be put on efforts aimed at early detection of AD. RESEARCH DESIGN AND METHODS: Here, images undergo a pre-processing phase that integrates image resizing and the application of median filters. After that, processed images are subjected to data augmentation procedures. Feature extraction from WOA-based ResNet, together with extracted convolutional neural network (CNN) features from pre-processed images, is used to train proposed DL model to classify AD. The process is executed using the proposed Attention Gated-VGG model. RESULTS: The proposed method outperformed normal methodologies when tested and achieved an accuracy of 96.7%, sensitivity of 97.8%, and specificity of 96.3%. CONCLUSION: The results have proven that Attention Gated-VGG model is a very promising technique for classifying AD.
科研通智能强力驱动
Strongly Powered by AbleSci AI