Search for: All records

The objective of this study was to develop a novel AI-ensembled network based on the most important features and affected brain regions to accurately classify and exhibit the pattern of progression of the stages of Cognitive Impairment (CI).

We proposed a novel ensembled architecture, 3D ResNet-18 - RF (Random Forest), and used this network to categorize the stages of Alzheimer’s disease (AD). The residual unit (blocks of ResNet) was introduced to the 3D Convolutional Neural network (CNN) to solve the degradation problem. It was considered an innovative strategy since the combination with fine-tuning resulted in higher accuracy. This network was trained on selected features and affected brain regions. The structured magnetic resonance images (MRI) were collected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, and the random forest was used for determining the importance of the features and affected regions from the parcellated 170 regions of interest (ROIs) using Atlas, automated anatomical labeling 3(AAL-3). This framework classified five categories of AD and detected the progression pattern.

The proposed network showed promising results with a 66% F-1 score, 76% sensitivity, and 93.5% specificity, which outperformed the performance of conventional methods for categorizing five categories. Ventral Posterolateral and Pulvinar lateral regions were the regions most affected, indicating the progression from early MCI to AD. The five-fold validation accuracy for the developed model was 60.02%.

The results showed that the gray matter to white matter ratio was the most significant feature, which also accurately predicted the progression pattern. The performance metrics fluctuated with different hyperparameters, but they never exceeded 0.05% of the estimated results, indicating the validity and originality of the suggested methodology.

This study aimed to investigate the role of neck muscle activity and neck damping characteristics in traumatic brain injury (TBI) mechanisms.

We used a previously validated head-neck finite element (FE) model that incorporates various components such as scalp, skull, cerebrospinal fluid, brain, muscles, ligaments, cervical vertebrae, and intervertebral discs. Impact scenarios included a Golf ball impact, NBDL linear acceleration, and Zhang’s linear and rotational accelerations. Three muscle activation strategies (no-activation, low-to-medium, and high activation levels) and two neck damping levels by perturbing intervertebral disc properties (high: hyper-viscoelastic and low: hyper-elastic) strategies were examined. We employed Head Injury Criterion (HIC), Brain Injury Criterion (BrIC), and maximum principal strain (MPS) as TBI measures.

Increased neck muscle activation consistently reduced the values of all TBI measures in Golf ball impact (HIC: 4%-7%, BrIC: 11%-25%, and MPS (occipital): 27%-50%) and NBDL study (HIC: 64%-69%, BrIC: 3%-9%, and MPS (occipital): 6%-19%) simulations. In Zhang’s study, TBI metric values decreased with the increased muscle activation from no-activation to low-to-medium (HIC: 74%-83%, BrIC: 27%-27%, and MPS (occipital): 60%-90%) and then drastically increased with further increases to the high activation level (HIC: 288%-507%, BrIC: 1%-25%, and MPS (occipital): 23%-305%). Neck damping changes from low to high decreased all values of TBI metrics, particularly in Zhang’s study (up to 40% reductions).

Our results underscore the pivotal role of neck muscle activation and neck damping in TBI mitigation and holds promise to advance effective TBI prevention and protection strategies for diverse applications.