The early detection of oral cancer (OC) at the earliest stage significantly increases survival rates. Recently, there has been an increasing interest in the use of artificial intelligence (AI) technologies in diagnostic medicine. This study aimed to critically analyse the available evidence concerning the utility of AI in the diagnosis of OC. Special consideration was given to the diagnostic accuracy of AI and its ability to identify the early stages of OC. From the date of inception to December 2021, 4 databases (PubMed, Scopus, EBSCO, and OVID) were searched. Three independent authors selected studies on the basis of strict inclusion criteria. The risk of bias and applicability were assessed using the prediction model risk of bias assessment tool. Of the 606 initial records, 17 studies with a total of 7245 patients and 69,425 images were included. Ten statistical methods were used to assess AI performance in the included studies. Six studies used supervised machine learning, whilst 11 used deep learning. The results of deep learning ranged with an accuracy of 81% to 99.7%, sensitivity 79% to 98.75%, specificity 82% to 100%, and area under the curve (AUC) 79% to 99.5%. Results obtained from supervised machine learning demonstrated an accuracy ranging from 43.5% to 100%, sensitivity of 94% to 100%, specificity 16% to 100%, and AUC of 93%. There is no clear consensus regarding the best AI method for OC detection. AI is a valuable diagnostic tool that represents a large evolutionary leap in the detection of OC in its early stages. Based on the evidence, deep learning, such as a deep convolutional neural network, is more accurate in the early detection of OC compared to supervised machine learning.

Long noncoding RNAs (lncRNAs) are a type of noncoding RNA transcript that are characterized by lack of protein-coding capacity. The vital role of lncRNAs in tongue squamous cell carcinoma (TSCC) is attracting increasing attention. In the present study, we identify a key lncRNA regulating TSCC metastasis and investigated the underlying mechanism. Our results indicate that the lncRNA ADAMTS9-AS2 is most significantly upregulated in TSCC tissues from patients with lymph node metastasis and is closely associated with poor prognosis. Furthermore, ADAMTS9-AS2 knockdown in TSCC cells leads to a inhibition of cell migration and invasion and reverses TGF-β1 induced EMT. ADAMTS9-AS2 knockdown also inhibits TSCC cell growth in vitro and in vivo. In addition, we show that ADAMTS9-AS2 is a cytoplasmic lncRNA that shares the miRNA response elements (MREs) of miR-600 with EZH2, which is confirmed by a luciferase reporter assay and AGO2-dependent RNA immunoprecipitation (RIP). In summary, our results demonstrate an explicit oncogenic role of ADAMTS9-AS2 in TSCC tumorigenesis via competition with miR-600, suggesting a new regulatory mechanism of ADAMTS9-AS2 and providing a potential therapeutic target for TSCC patients.

Secreted frizzled-related proteins (SFRPs), the first identified Wnt antagonists, have been well recognized as tumor suppressors in multiple human cancers through suppressing the Wnt/β-catenin pathway. To better elucidate the mechanisms of SFRPs involved in the carcinogenesis of oral submucous fibrosis (OSF), one of the precancerous lesions of oral squamous cell carcinoma (OSCC), we investigated expression and localization of SFRP1, SFRP5, and β-catenin in normal oral epithelium, OSF, and OSCC tissues. We found that SFRP1 and SFRP5 were readily expressed in normal oral mucous tissues but gradually decreased in OSF early, moderately advanced, and advanced tissues and rarely expressed in OSCC tissues. We found the changes of SFRP1 localization and SFRP5 localization from nucleus to cytoplasm in the carcinogenesis of OSF. There is a significant association among reduced SFRP1, SFRP5, and cytoplasmic/nuclear β-catenin expression, which is correlated with higher tumor grade and stage of OSCC. We further found that SFRP1 and SFRP5 were frequently methylated in OSCC cases with betel quid chewing habit but not in normal oral mucous and different stages of OSF tissues, suggesting that methylation of SFRP1 and SFRP5 is tumor specific in the carcinogenesis of OSF. Taken together, our data demonstrated that reduced SFRP1 and SFRP5 by promoter methylation could lead to cytoplasmic/nuclear accumulation of β-catenin and tumor progression. The changes of SFRPs and β-catenin localization, as well as SFRPs’ methylation, could be useful predictors or biomarkers of OSF malignant progression and prognosis.

Objective: An evidence regarding which bony flap for reconstruction of mandibular defects following tumour resection is associated with the highest survival rate is still lacking. This network meta-analysis (NMA) aimed to guide surgeons selecting which vascularized osseous flap is associated with the highest survival rate for mandibular reconstruction. Methods: From inception to March 2021, PubMed, Embase, Scopus, and Cochrane library were searched to identify the eligible studies. The outcome variable was the flap survival rate. The Bayesian NMA accompanied by a random effect model and 95% credible intervals (CrI) was calculated. Results: Twenty-two studies with a total of 1513 patients, comparing four osseous flaps namely fibula free flap (FFF), deep circumferential iliac artery flap (DCIA), scapula flap, and osteocutaneous radial forearm flap (ORFF) were included. The respective survival rates of FFF, DCIA, Scapula, and ORFF were 94.50%, 93.12%, 97%, and 95.95%. The NMA failed to show a statistically significant difference between all comparators (FFF versus DCIA (Odd ratio, 1.8; CrI, 0.58,5.0); FFF versus ORFF (Odd ratio, 0.57; CrI, 0.077; 2.9); FFF versus scapula flap (Odd ratio, 0.25; CrI, 0.026; 1.5); DCIA versus ORFF (Odd ratio, 0.32; CrI, 0.037; 2.1); DCIA versus scapula flap (Odd ratio, 0.14; CrI, 0.015; 1.1) and ORFF versus scapula flap (Odd ratio, 2.3; CrI, 0.16; 34)). Conclusion: Within the limitations of the current NMA, FFF, DCIA, Scapula, and ORFF showed a comparable survival rate for mandibular reconstruction. Although the scapula flap reported the highest survival rate compared to other osseous flaps for mandibular reconstruction; however, the decision making when choosing an osseous flap should be based on many factors rather than simply flap survival rate.