Intelligent Bayesian Inference for Multiclass Lung Infection Diagnosis: Network Analysis of Ranked Gray Level Co-occurrence (GLCM) Features

Abstract

Deep learning-powered AI tools offer significant potential to improve COVID-19 lung infection diagnosis. This study proposes a novel AI-based image analysis method for multiclass classification. We analyzed publicly available datasets from Italian Society of Medical and Interventional Radiology (SIRM), Kaggle, and Radiopaedia. However, the relevance, strength, and relationships of static features extracted from these images require further investigation. Bayesian inference approaches have recently emerged as powerful tools for analyzing static features. These approaches can reveal hidden dynamics and relationships between features. Using Analysis of variance (ANOVA) based ranking techniques, we extracted gray level co-occurrence matrix (GLCM) features from images belonging to three classes such as COVID-19, bacterial pneumonia, and normal. To delve deeper into the dynamic behavior and optimize its diagnostic potential, Homogeneity (identified as the most significant feature) was chosen for further analysis using dynamic profiling and optimization methods. This focused investigation aimed to decipher the intricate, non-linear dynamics within GLCM features across all three classes. Our method offers a two-fold benefit. First, it deepens our understanding of the intricate relationships between features extracted from chest X-rays using gray level co-occurrence matrix analysis. Second, it provides a comprehensive examination of these features themselves. This combined analysis sheds light on the hidden dynamics that are crucial for accurate diagnosis and prognosis of various infectious diseases. In addition to the above, we have developed a novel AI-powered imaging analysis method for multiclass classification. This innovative approach has the potential to significantly improve diagnostic accuracy and prognosis of infectious diseases, particularly COVID-19.