Enhancing Airway Assessment with a Secure Hybrid Network-Blockchain System for CT & CBCT Image Evaluation

Abstract

Our investigation explored the intricacies of airway evaluation through Cone-Beam Computed Tomography (CBCT) and Computed Tomography (CT) images. By employing innovative data augmentation strategies, we expanded our dataset significantly, enabling a more comprehensive analysis of airway characteristics. The utility of these techniques was evident in their ability to yield a diverse array of synthetic images, each representing different airway scenarios with high fidelity. A notable outcome of our study was the effective categorization of the initial image as "Class II" under the Mallampati Classification system. The augmented images further enhanced our understanding by exhibiting a spectrum of airway parameters. Moreover, our approach included training a Recurrent Neural Network (RNN) model on a dataset of CT images. This model, fortified with pseudo-labels created via K-means clustering, showcased its proficiency by accurately predicting airway assessment categories in various test scenarios. These results underscore the model's potential as a tool for swift and precise airway evaluation in clinical settings, marking a significant advancement in medical imaging technologies.