Bhansali Ashok, Sudheer Devulapalli, Tiwari Shrikant, Desanamukula Venkata Subbaiah, Ahmad Faiyaz
Dept of Computer Engineering and Applications, GLA University, Uttar Pradesh, Mathura, 281406, India.
Department of CSE, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad, Telangana, 500090, India.
J Imaging Inform Med. 2025 Aug;38(4):2210-2228. doi: 10.1007/s10278-024-01262-z. Epub 2024 Dec 11.
Alzheimer's disease is a degenerative neurological condition resulting in brain cell death and brain tissue loss. Most importantly, memory-related brain cells are permanently harmed due to this condition. Alzheimer's disease diagnosis is a challenging task due to its high discriminative feature representation for classification using traditional machine learning (ML) methods. These challenges exist due to similar brain processes and pixel intensities. To overcome the above mentioned drawbacks, hybrid feature extraction techniques such as Gray Level Run Length Matrix (GLRLM), Gabor wavelet transform and Local Energy-based Shape Histogram (LESH) are used. In this designed model, Alzheimer's disease is predicted using brain MRI. At first, the collected magnetic resonance imaging (MRI) of the brain are resized and enhanced using the image resizing and BW-net technique. Features from these enhanced images are extracted using the GLRLM, Gabor wavelet transform and LESH techniques for shape, texture and edge of the brain MRI. Then, the extracted features are optimally selected using the SEAGULL optimization technique. These optimally selected features are trained using the modified DNN for predicting Alzheimer's disease. Performance metrics for proposed and existing models are studied and contrasted in order to assess the planned model. For the proposed model, 91%, 2%, 98% and 97% are performance metrics that were reached in aspects of precision, error, accuracy and recall. Thus, designed Alzheimer's disease prediction using modified DNN with optimal feature selection based on seagull optimization performs better and accurately predicts Alzheimer's disease.
阿尔茨海默病是一种退行性神经疾病，会导致脑细胞死亡和脑组织损失。最重要的是，与记忆相关的脑细胞会因这种疾病而受到永久性损害。由于阿尔茨海默病在使用传统机器学习（ML）方法进行分类时具有高度可区分的特征表示，其诊断是一项具有挑战性的任务。由于大脑过程和像素强度相似，这些挑战才存在。为了克服上述缺点，使用了诸如灰度行程长度矩阵（GLRLM）、伽柏小波变换和基于局部能量的形状直方图（LESH）等混合特征提取技术。在这个设计模型中，使用脑部磁共振成像（MRI）来预测阿尔茨海默病。首先，使用图像缩放和BW-net技术对收集到的脑部磁共振成像（MRI）进行缩放和增强。使用GLRLM、伽柏小波变换和LESH技术从这些增强图像中提取脑部MRI的形状、纹理和边缘特征。然后，使用海鸥优化技术对提取的特征进行最优选择。使用改进的深度神经网络（DNN）对这些最优选择的特征进行训练，以预测阿尔茨海默病。为了评估所规划的模型，对所提出模型和现有模型的性能指标进行了研究和对比。对于所提出的模型，在精度、误差、准确率和召回率方面分别达到了91%、2%、98%和97%的性能指标。因此，基于海鸥优化的最优特征选择，使用改进的深度神经网络设计的阿尔茨海默病预测模型表现更好，能够准确预测阿尔茨海默病。
