Artificial neural networks algorithms for prediction of human hair loss related autoimmune disorder problem

This study explores the use of artificial neural networks (ANNs) to diagnose Alopecia Areata (AA), an autoimmune condition causing hair loss, affecting 1 in 1000 people globally. The research aims to evaluate the accuracy of neural networks in detecting alopecia by developing a classification framework that distinguishes between healthy hair and AA. The framework enhances image quality using Contrast Limited Adaptive Histogram Equalization (CLAHE) and segmentation techniques, and employs Data Augmentation (DA) to improve precision. Feature extraction is performed using Visual Geometry Group (VGG) networks and Convolutional Neural Networks (CNN), which are effective in learning complex features from data. The classification model is built using the Support Vector Machine (SVM) approach, known for its versatility and effectiveness in supervised learning tasks. The combination of these techniques aims to accurately classify healthy hair and AA cases.