Transfer learning has become extremely popular in recent years for tackling issues from various sectors, including the analysis of medical images. Medical image analysis has transformed medical care in recent years, enabling physicians to identify diseases early and accelerate patient recovery. Alzheimer’s disease (AD) diagnosis has been greatly aided by imaging. AD is a degenerative neurological condition that slowly deprives patients of their memory and cognitive abilities. Computed tomography (CT) and brain magnetic resonance imaging (MRI) scans are used to detect dementia in AD patients. This research primarily aims to classify AD patients into multiple classes using ResNet50, VGG16, and DenseNet121 as transfer learning along with convolutional neural networks on a large dataset as compared to existing approaches as it improves classification accuracy. The methods employed utilize CT and brain MRI scans for AD patient classification, considering various stages of AD. The study demonstrates promising results in predicting AD phases with MRI, yet challenges persist, including processing large datasets and cognitive workload involved in interpreting scans. Addressing image quality variations is crucial, necessitating advancements in imaging technology and analysis techniques. The different stages of AD are early mental retardation, mild mental impairment, late mild cognitive impairment, and final AD stage. The novel approach gives results with an accuracy of 96.6% and significantly improved outcomes compared to existing models.
Multiple studies have attempted to use a single type of data to predict various stages of Alzheimer’s disease (AD). However, combining multiple data modalities can improve prediction accuracy. In this study, we utilized a combination of biomarkers, including magnetic resonance imaging (MRI), electronic health records, and cerebrospinal fluid (CSF), to classify subjects into three groups based on clinical tests—normal cognitive controls (CN), mild cognitive impairment (MCI), and AD. To determine the significant parameters, we employ a novel technique that utilizes sparse autoencoders to extract features from CSF, clinical data, and convolutional neural networks’ (CNN’s) MRI imaging data. Our results indicate that deep learning methods outperform traditional machine learning models such as decision trees, support vector machines, random forests and K-nearest neighbors. The proposed method significantly outperforms traditional models, achieving an accuracy of 0.87 for CN versus AD, a precision of 0.93 for CN, and a recall of 0.88 for AD on the external test set. The integration of various data modalities and the application of deep learning techniques enhance the prediction accuracy, demonstrating the potential for improved diagnostic tools in clinical settings.