One of the first signs of Alzheimer’s disease (AD) is mild cognitive impairment (MCI), in which there are small variants of brain changes among the intermediate stages. Although there has been an increase in research into the diagnosis of AD in its early levels of developments lately, brain changes, and their complexity for functional magnetic resonance imaging (fMRI), makes early detection of AD difficult. This paper proposes a deep learning-based method that can predict MCI, early MCI (EMCI), late MCI (LMCI), and AD. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) fMRI dataset consisting of 138 subjects was used for evaluation. The finetuned ResNet18 network achieved a classification accuracy of 99.99%, 99.95%, and 99.95% on EMCI vs. AD, LMCI vs. AD, and MCI vs. EMCI classification scenarios, respectively. The proposed model performed better than other known models in terms of accuracy, sensitivity, and specificity.

Alzheimer’s disease (AD) is a neurodegenerative disease that affects brain cells, and mild cognitive impairment (MCI) has been defined as the early phase that describes the onset of AD. Early detection of MCI can be used to save patient brain cells from further damage and direct additional medical treatment to prevent its progression. Lately, the use of deep learning for the early identification of AD has generated a lot of interest. However, one of the limitations of such algorithms is their inability to identify changes in the functional connectivity in the functional brain network of patients with MCI. In this paper, we attempt to elucidate this issue with randomized concatenated deep features obtained from two pre-trained models, which simultaneously learn deep features from brain functional networks from magnetic resonance imaging (MRI) images. We experimented with ResNet18 and DenseNet201 to perform the task of AD multiclass classification. A gradient class activation map was used to mark the discriminating region of the image for the proposed model prediction. Accuracy, precision, and recall were used to assess the performance of the proposed system. The experimental analysis showed that the proposed model was able to achieve 98.86% accuracy, 98.94% precision, and 98.89% recall in multiclass classification. The findings indicate that advanced deep learning with MRI images can be used to classify and predict neurodegenerative brain diseases such as AD.

Alzheimer’s disease (AD) has become a serious hazard to human health in recent years, and proper screening and diagnosis of AD remain a challenge. Multimodal neuroimaging input can help identify AD in the early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI) stages from normal cognitive development using magnetic resonance imaging (MRI) and positron emission tomography (PET). MRI provides useful information on brain structural abnormalities, while PET data provide the difference between physiological and pathological changes in brain anatomy. The precision of diagnosing AD can increase when these data are combined. However, they are heterogeneous and appropriate, and an adequate number of features are required for AD classification. This paper proposed a multimodal fusion-based approach that uses a mathematical technique called discrete wavelet transform (DWT) to analyse the data, and the optimisation of this technique is achieved through transfer learning using a pre-trained neural network called VGG16. The final fused image is reconstructed using inverse discrete wavelet transform (IDWT). The fused images are classified using a pre-trained vision transformer. The evaluation of the benchmark Alzheimer’s disease neuroimaging initiative (ADNI) dataset shows an accuracy of 81.25% for AD/EMCI and AD/LMCI in MRI test data, as well as 93.75% for AD/EMCI and AD/LMCI in PET test data. The proposed model performed better than existing studies when tested on PET data with an accuracy of 93.75%.

Multimodal neuroimaging has gained traction in Alzheimer’s Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model’s ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer’s Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

Stroke is a major cause of death worldwide, resulting from a blockage in the flow of blood to different parts of the brain. Many studies have proposed a stroke disease prediction model using medical features applied to deep learning (DL) algorithms to reduce its occurrence. However, these studies pay less attention to the predictors (both demographic and behavioural). Our study considers interpretability, robustness, and generalisation as key themes for deploying algorithms in the medical domain. Based on this background, we propose the use of random forest for stroke incidence prediction. Results from our experiment showed that random forest (RF) outperformed decision tree (DT) and logistic regression (LR) with a macro F1 score of 94%. Our findings indicated age and body mass index (BMI) as the most significant predictors of stroke disease incidence.