Early-Stage Alzheimer's Disease Categorization Using PET Neuroimaging Modality and Convolutional Neural Networks in the 2D and 3D Domains.

Alzheimer's Disease (AD) is a health apprehension of significant proportions that is negatively impacting the ageing population globally. It is characterized by neuronal loss and the formation of structures such as neurofibrillary tangles and amyloid plaques in the early as well as later stages of the disease. Neuroimaging modalities are routinely used in clinical practice to capture brain alterations associated with AD. On the other hand, deep learning methods are routinely used to recognize patterns in underlying data distributions effectively. This work uses Convolutional Neural Network (CNN) architectures in both 2D and 3D domains to classify the initial stages of AD into AD, Mild Cognitive Impairment (MCI) and Normal Control (NC) classes using the positron emission tomography neuroimaging modality deploying data augmentation in a random zoomed in/out scheme. We used novel concepts such as the blurring before subsampling principle and distant domain transfer learning to build 2D CNN architectures. We performed three binaries, that is, AD/NC, AD/MCI, MCI/NC and one multiclass classification task AD/NC/MCI. The statistical comparison revealed that 3D-CNN architecture performed the best achieving an accuracy of 89.21% on AD/NC, 71.70% on AD/MCI, 62.25% on NC/MCI and 59.73% on AD/NC/MCI classification tasks using a five-fold cross-validation hyperparameter selection approach. Data augmentation helps in achieving superior performance on the multiclass classification task. The obtained results support the application of deep learning models towards early recognition of AD.

Frequency of work related musculoskeletal disorders and ergonomic risk assessments among tailors.

OBJECTIVE: To determine the frequency of work-related musculoskeletal disorders and to assess postural ergonomic risk among tailors. METHODS: The cross-sectional study was conducted from September 2017 to February 2018 in Rawalpindi and Islamabad, Pakistan and comprised tailors of both genders aged 25-60 years, working for more than 6 months and having small and medium enterprises. To calculate ergonomic risk of work posture, Quick Exposure Check was used and work-related musculoskeletal disorders were determined through body mapping chart. Data was analysed using SPSS 20. RESULTS: Of the 400 tailors, 382(95.5%) were males. The overall mean age of the sample was 36.9±10.96 years. The mean Quick Exposure Check score was 46.11±14.83. Acceptable work posture was found in 373(93.25%) subjects. The most common work-related acute musculoskeletal symptoms were found in the upper back 320(80%). CONCLUSIONS: Most tailors had acceptable work posture but work-related pain in upper back was common.