Classification of Maxillofacial Morphology by Artificial Intelligence Using Cephalometric Analysis Measurements.

The characteristics of maxillofacial morphology play a major role in orthodontic diagnosis and treatment planning. While Sassouni's classification scheme outlines different categories of maxillofacial morphology, there is no standardized approach to assigning these classifications to patients. This study aimed to create an artificial intelligence (AI) model that uses cephalometric analysis measurements to accurately classify maxillofacial morphology, allowing for the standardization of maxillofacial morphology classification. This study used the initial cephalograms of 220 patients aged 18 years or older. Three orthodontists classified the maxillofacial morphologies of 220 patients using eight measurements as the accurate classification. Using these eight cephalometric measurement points and the subject's gender as input features, a random forest classifier from the Python sci-kit learning package was trained and tested with a k-fold split of five to determine orthodontic classification; distinct models were created for horizontal-only, vertical-only, and combined maxillofacial morphology classification. The accuracy of the combined facial classification was 0.823 ± 0.060; for anteroposterior-only classification, the accuracy was 0.986 ± 0.011; and for the vertical-only classification, the accuracy was 0.850 ± 0.037. ANB angle had the greatest feature importance at 0.3519. The AI model created in this study accurately classified maxillofacial morphology, but it can be further improved with more learning data input.

Extracellular adenosine 5'-diphosphate promotes MCP-1/CCL2 expression via the P2Y13 purinergic receptor/ERK signaling axis in temporomandibular joint-derived mouse fibroblast-like synoviocytes.

BACKGROUND: Temporomandibular joint osteoarthritis (TMJ-OA) causes cartilage degeneration, bone cavitation, and fibrosis of the TMJ. However, the mechanisms underlying the fibroblast-like synoviocyte (FLS)-mediated inflammatory activity in TMJ-OA remain unclear. METHODS AND RESULTS: Reverse transcription-quantitative polymerase chain reaction analysis revealed that the P2Y1, P2Y12, and P2Y13 purinergic receptor agonist adenosine 5'-diphosphate (ADP) significantly induces monocyte chemotactic protein 1 (MCP-1)/ C-C motif chemokine ligand 2 (CCL2) expression in the FLS1 synovial cell line. In contrast, the uracil nucleotide UTP, which is a P2Y2 and P2Y4 agonist, has no significant effect on MCP-1/CCL2 production in FLS1 cells. In addition, the P2Y13 antagonist MRS 2211 considerably decreases the expression of ADP-induced MCP-1/CCL2, whereas ADP stimulation enhances extracellular signal-regulated kinase (ERK) phosphorylation. Moreover, it was found that the mitogen-activated protein kinase/ERK kinase (MEK) inhibitor U0126 reduces ADP-induced MCP-1/CCL2 expression. CONCLUSION: ADP enhances MCP-1/CCL2 expression in TMJ FLSs via P2Y13 receptors in an MEK/ERK-dependent manner, thus resulting in inflammatory cell infiltration in the TMJ. Collectively, the findings of this study contribute to a partial clarification of the signaling pathway underlying the development of inflammation in TMJ-OA and can help identify potential therapeutic targets for suppressing ADP-mediated purinergic signaling in this disease.

Receptor tyrosine kinase ligands and inflammatory cytokines cooperatively suppress the fibrogenic activity in temporomandibular-joint-derived fibroblast-like synoviocytes via mitogen-activated protein kinase kinase/extracellular signal-regulated kinase.

Osteoarthritis (OA)-related fibrosis is a possible cause of temporomandibular joint (TMJ) stiffness. However, the molecular mechanisms underlying the fibrogenic activity in fibroblast-like synoviocytes (FLSs) remain to be clarified. The present study examined the effects of receptor tyrosine kinase (RTK) ligands, such as fibroblast growth factor (FGF)-1 and epidermal growth factor (EGF), on myofibroblastic differentiation of the FLS cell line FLS1, which is derived from the mouse TMJ. The present study revealed that both FGF-1 and EGF dose-dependently suppressed the expression of the myofibroblast (MF) markers, including α-smooth muscle actin (α-SMA) and type I collagen, in FLS1 cells. Additionally, both FGF-1 and EGF activated extracellular signal-regulated kinase (ERK) in FLS1 cells. In addition, the mitogen-activated protein kinase (MAPK)/ERK kinase (MEK) inhibitor U0126 abrogated the FGF-1- and EGF-mediated suppression of MF marker expression. On the other hand, inflammatory cytokines, such as interleukin-1ß and tumor necrosis factor-α, also suppressed the expression of MF markers in FLS1 cells. Importantly, U0126 abrogated the inflammatory cytokine-mediated suppression of MF marker expression. Interestingly, RTK ligands and inflammatory cytokines additively suppressed the expression of type I collagen. These results suggested that RTK ligands and inflammatory cytokines cooperatively inhibited the fibrogenic activity in FLSs derived from the TMJ in a MEK/ERK-dependent manner. The present findings partially clarify the molecular mechanisms underlying the development of OA-related fibrosis in the TMJ and may aid in identifying therapeutic targets for this condition. Additionally, FGF-1 and EGF could be therapeutically utilized to prevent OA-related fibrosis around the inflammatory TMJ.