Abductive multi-instance multi-label learning for periodontal disease classification with prior domain knowledge

Abstract

Machine learning is widely used in dentistry nowadays, offering efficient solutions for diagnosing dental diseases, such as periodontitis and gingivitis. Most existing methods for diagnosing periodontal diseases follow a two-stage process. Initially, they detect and classify potential Regions of Interest (ROIs) and subsequently determine the labels of the whole images. However, unlike the recognition of natural images, the diagnosis of periodontal diseases relies significantly on pinpointing specific affected regions, which requires professional expertise that is not fully captured by existing models. To bridge this gap, we propose a novel ABductive Multi-Instance Multi-Label learning (AB-MIML) approach. In our approach, we treat entire intraoral images as “bags” and local patches as “instances”. By improving current multi-instance multi-label methods, AB-MIML seeks to establish a comprehensive many-to-many relationship to model the intricate correspondence among images, patches, and corresponding labels. Moreover, to harness the power of prior domain knowledge, AB-MIML converts the expertise of doctors and the structural information of images into a knowledge base and performs abductive reasoning to assist the classification and diagnosis process. Experiments unequivocally confirm the superior performance of our proposed method in diagnosing periodontal diseases compared to state-of-the-art approaches across various metrics. Moreover, our method proves invaluable in identifying critical areas correlated with the diagnosis process, aligning closely with determinations made by human doctors.