MATERIALS AND METHODS: We developed a web-interface, hosted on a web server to collect oral lesions images from international partners. Further, we developed a customised annotation tool, also a web-interface for systematic annotation of images to build a rich clinically labelled dataset. We evaluated the sensitivities comparing referral decisions through the annotation process with the clinical diagnosis of the lesions.
RESULTS: The image repository hosts 2474 images of oral lesions consisting of oral cancer, oral potentially malignant disorders and other oral lesions that were collected through MeMoSA® UPLOAD. Eight-hundred images were annotated by seven oral medicine specialists on MeMoSA® ANNOTATE, to mark the lesion and to collect clinical labels. The sensitivity in referral decision for all lesions that required a referral for cancer management/surveillance was moderate to high depending on the type of lesion (64.3%-100%).
CONCLUSION: This is the first description of a database with clinically labelled oral lesions. This database could accelerate the improvement of AI algorithms that can promote the early detection of high-risk oral lesions.
OBJECTIVE: This study aimed to investigate the viral load of HPV18 DNA in OSCC and potentially malignant lesions using saliva samples.
MATERIALS AND METHODS: Genomic DNAs of thirty saliva samples of normal subjects and thirty saliva samples compromised of 16 samples from potentially malignant lesions and 14 of OSCC patients were amplified for HPV18 DNA using a nested polymerase chain reaction analysis. All PCR products were then analyzed using the Bioanalyzer to confirm presence of HPV18 DNA.
RESULT: From thirty patients examined, only one of 30 (3.3%) cases was found to be positive for HPV18 in this study.
CONCLUSION: The finding of this study revealed that there is a low viral detection of HPV18 in Malaysian OSCC by using saliva samples, suggesting that prevalence of HPV18 may not be important in this group of Malaysian OSCC.
METHODS: Two villages were selected as the sampling frame based on prevalence of tobacco and betel quid chewing habit. Respondents were asked to check their mouth for presence of lesion or abnormalities. Education on oral cancer, including MSE, was provided. Subsequently, respondents were asked to perform MSE. Finally, a clinical oral examination (COE) was done by a specialist and the presence of oral mucosal lesions was recorded.
RESULTS: Almost 64.5 percent of respondents exhibited high levels of difficulty and low mucosal visualization and retracting ability, whereas 3.0 percent demonstrated high attention level when performing MSE. Prevalence of oral mucosal lesions was 59.0 percent, whereas the prevalence of oral potentially malignant disorders (OPMDs) was 9.0 percent. Detection of oral lesions by respondents using MSE was lower than detection by the gold standard. Sensitivity and specificity of MSE for detection of all types of lesions were 8.6 and 95.0 percent respectively. When analyzing each lesion type separately, MSE was found to be most sensitive in detection of swellings (10.0 percent), and most specific in identifying white lesions (97.8 percent). For detection of OPMDs, although specificity was high (98.9 percent), sensitivity (0 percent), and +LR (0) was poor.
CONCLUSION: MSE is not an effective self-screening tool for early detection of potentially malignant lesions for this population.
METHODS: A literature review was conducted using the keyword of "Odontogenic carcinosarcoma" and all relevant articles were screened. The data collected include demographic profile (age, gender), clinical information (symptoms, location, size), radiologic features, histopathological examination, management, recurrence, metastases, and survival status.
RESULTS: A total of 17 OCS cases including a new case from our hospital. The incidence of OCS was highest in the third decades of life with predilection for male and posterior region of mandible. Clinically, patients may present with swelling and neurological symptoms. Radiographic examination often showed radiolucency with ill-defined border. This tumour demonstrates an aggressive behaviour with reported cases of distant metastases to the lung, lymph nodes, rib, and pelvis. Here, we report an interesting case of OCS in a 38-year-old man with a previous diagnosis of ameloblastoma. The patient was diagnosed with ameloblastoma but refused surgical intervention and returned after 10 years with rapidly enlarging mass on the right side of mandible. Microscopically, the lesion appears as biphasic odontogenic tumour with malignant cytological features seen in both epithelium and mesenchymal components. The spindle to round mesenchymal tumour cells were only positive for vimentin. Ki67 proliferation index was high in both epithelium and mesenchymal components.
CONCLUSION: This case showed the tendency of untreated ameloblastoma to undergo malignant changes in the long term.