Temporomandibular Joint (TMJ) disorder is a set of orofacial ache syndromes that are the most frequent non-dental ache issue in the maxillofacial area. It mostly refers to a group of musculoskeletal problems that can impact the masticatory system. It is believed that 60-70% of the population suffers from the minimum any signs. This condition is quite common in the wide-ranging community, yet women are afflicted at a 4:1 fraction. Over the past decades, advanced Artificial Intelligence (AI) methods including machine and deep learning algorithms have been developed to recognize and categorize the TMJ disorder early from different imaging modalities like panoramic images, Xray images, etc. Amongst, panoramic radiograph is utilized as a preliminary forecasting technique in association with a complete medicinal evaluation to diagnose TMJ disorder. The findings observed from such methods can help the physicians in decisionmaking and early diagnosis of TMJ disorder. This paper presents a detailed review of different machine and deep learning algorithms developed to recognize and categorize TMJ disorder from panoramic images. First, different TMJ disorder recognition and categorization models designed by many researchers based on machine and deep learning algorithms are studied in brief. Then, a comparative study is conducted to understand the drawbacks of those algorithms and suggest a new solution to classify the TMJ disorder accurately.

Keywords : Temporomandibular disorder, Temporomandibular joint, Artificial intelligence, Machine learning, Deep learning, Panoramic imaging