Early diagnosis of mild cognitive impairment (MCI) with magnetic resonance imaging (MRI) has been shown to positively affect patients’ lives. To save time and costs associated with clinical investigation, deep learning approaches have been used widely to predict MCI. This study proposes optimized deep learning models for differentiating between MCI and normal control samples. In previous studies, the hippocampus region located in the brain is used extensively to diagnose MCI. The entorhinal cortex is a promising area for diagnosing MCI since severe atrophy is observed when diagnosing the disease before the shrinkage of the hippocampus. Due to the small size of the entorhinal cortex area relative to the hippocampus, limited research has been conducted on the entorhinal cortex brain region for predicting MCI. This study involves the construction of a dataset containing only the entorhinal cortex area to implement the classification system. To extract the features of the entorhinal cortex area, three different neural network architectures are optimized independently: VGG16, Inception-V3, and ResNet50. The best outcomes were achieved utilizing the convolution neural network classifier and the Inception-V3 architecture for feature extraction, with accuracy, sensitivity, specificity, and area under the curve scores of 70%, 90%, 54%, and 69%, respectively. Furthermore, the model has an acceptable balance between precision and recall, achieving an F1 score of 73%. The results of this study validate the effectiveness of our approach in predicting MCI and may contribute to diagnosing MCI through MRI.

Epilepsy is a neurological disorder characterized by abnormal brain activity. Epileptic patients suffer from unpredictable seizures, which may cause a loss of awareness. Seizures are considered drug resistant if treatment does not affect success. This leads practitioners to calculate the cortical thickness to measure the distance between the brain’s white and grey matter surfaces at various locations to perform a surgical intervention. In this study, we introduce using machine learning as an approach to classify extracted measurements from T1-weighted magnetic resonance imaging. Data were collected from the epilepsy unit at King Abdulaziz University Hospital. We applied two trials to classify the extracted measurements from T1-weighted MRI for drug-resistant epilepsy and healthy control subjects. The preprocessing sequence on T1-weighted MRI images was performed using C++ through BrainSuite’s pipeline. The first trial was performed on seven different combinations of four commonly selected measurements. The best performance was achieved in Exp6 and Exp7, with 80.00% accuracy, 83.00% recall score, and 83.88% precision. It is noticeable that grey matter volume and white matter volume measurements are more significant than the cortical thickness measurement. The second trial applied four different machine learning classifiers after applying 10-fold cross-validation and principal component analysis on all extracted measurements as in the first trial based on the mentioned previous works. The K-nearest neighbours model outperformed the other machine learning classifiers with 97.11% accuracy, 75.00% recall score, and 75.00% precision.

Bipolar disorder is a multifaceted psychiatric condition characterized by fluctuating activity levels and dysfunctional mood states, oscillating between manic and depressive episodes. These mood disturbances are accompanied by persistent functional and cognitive impairments, even during periods of euthymia. Prior studies have underscored the critical role of amygdala activity in the pathophysiology of bipolar disorder. This research aims to utilize resting-state functional Magnetic Resonance Imaging (rs-fMRI) to explore the functional modifications in the six sub-regions that compose the amygdala of individuals diagnosed with bipolar disorder. The study encompassed 80 participants, bifurcated into two groups: 40 individuals with bipolar disorder and 40 healthy controls. Each group comprised an equal gender distribution of 20 females and 20 males, ranging in age from 21 to 50 years. Using rs-fMRI, we examined the functional connectivity within six amygdala sub-regions across eight regional functional networks. Comparative analysis between the control group and the bipolar patients revealed that all six amygdala sub-regions demonstrated connectivity with the eight functional brain networks. Notable similarities and disparities were observed in the connectivity patterns between the bipolar group and controls, particularly within the amygdala's sub-regions and other brain networks. The most significant functional connectivity alterations were found with the salience network and the default mode network. Additionally, alterations in the functional connectivity between the amygdala, sensory-motor, and visual networks were noted in bipolar patients. The study's findings highlight the distinct patterns of resting-state functional connectivity of the amygdala and various brain networks in differentiating bipolar patients from healthy controls. These variations suggest the existence of multiple pathophysiological mechanisms contributing to emotional dysregulation in bipolar disorder.

Background: At present, clinical use of MRI in Alzheimer’s disease (AD) is mostly focused on the assessment of brain atrophy, namely in the hippocampal region. Despite this, multiple biomarkers reflecting structural and functional brain connectivity changes have shown promising results in the assessment of AD. To help identify the most relevant ones that may stand a chance of being used in clinical practice, we compared multiple biomarker in terms of their value to discriminate AD from healthy controls and analyzed their age dependency. Methods: 20 AD patients and 20 matched controls underwent MRI-scanning (3T GE), including T1-weighted, diffusion-MRI, and resting-state-fMRI (rsfMRI). Whole-brain, white-matter, gray-matter, cortical-gray-matter and hippocampi volumes were measured using icobrain. rsfMRI between regions of the default-mode-network (DMN) was assessed using group independent-component-analysis. Median diffusivity and kurtosis were determined in gray and white-matter.Logistic-Regression and Random-Forest models were trained to classify AD-status based on different features and feature-groups. Results: Hippocampal and DMN features involving the medial-Pre-Frontal-Cortex (mPFC) showed the strongest differences between AD-patients and controls. mPFC-DMN-features, WM volume, and relative hippocampal asymmetry showed only an association with AD-status (p <0.05) but not with age. Whole-brain volume, hippocampi volumes, and DTI/DKI features showed an association both with age and AD-status. Smallest-hippocampus-volume was the most discriminative feature. The best performance (accuracy:0.77, sensitivity:0.77, specificity:0.77) was obtained with an RF-model combining the best feature from each feature-group (smallest hippocampus volume, WM volume, median GM AxD and lTPJ-mPFC connectivity) and age. Conclusions: Brain-connectivity changes are reflected in multiple MRI-biomarkers. Inclusion of structural and functional connectivity biomarkers in addition to hippocampal volumes can contribute to a higher diagnostic accuracy and may provide a more complete assessment of the clinical status of each patient.

In brain mapping, structural templates derived from population-specific MRI scans are essential for normalizing individual brains into a common space. This normalization facilitates accurate group comparisons and statistical analyses. Although templates have been developed for various populations, none currently exist for the Saudi population. To our knowledge, this work introduces the first structural brain template constructed and evaluated from a homogeneous subset of T1-weighted MRI scans of 11 healthy Saudi female subjects aged 25 to 30. Our approach combines the symmetric model construction (SMC) method with a covariance-based weighting scheme to mitigate bias caused by over-represented anatomical features. To enhance the quality of the template, we employ a patch-based mean-shift intensity estimation method that improves image sharpness, contrast, and robustness to outliers. Additionally, we implement computational optimizations, including parallelization and vectorized operations, to increase processing efficiency. The resulting template exhibits high image quality, characterized by enhanced sharpness, improved tissue contrast, reduced sensitivity to outliers, and minimized anatomical bias. This Saudi-specific brain template addresses a critical gap in neuroimaging resources and lays a reliable foundation for future studies on brain structure and function in this population.