Ensemble Deep-Learning-Based Prognostic and Prediction for Recurrence of Sporadic Odontogenic Keratocysts on Hematoxylin and Eosin Stained Pathological Images of Incisional Biopsies.

(1) Background: Odontogenic keratocysts (OKCs) are enigmatic developmental cysts that deserve special attention due to their heterogeneous appearance in histopathological characteristics and high recurrence rate. Despite several nomenclatures for classification, clinicians still confront challenges in its diagnosis and predicting its recurrence. This paper proposes an ensemble deep-learning-based prognostic and prediction algorithm, for the recurrence of sporadic odontogenic keratocysts, on hematoxylin and eosin stained pathological images of incisional biopsies before treatment. (2) Materials and Methods: In this study, we applied a deep-learning algorithm to an ensemble approach integrated with DenseNet-121, Inception-V3, and Inception-Resnet-V3 classifiers. Around 1660 hematoxylin and eosin stained pathologically annotated digital images of OKC-diagnosed (60) patients were supplied to train and predict recurrent OKCs. (3) Results: The presence of SEH (p = 0.004), an incomplete epithelial lining, (p = 0.023), and a corrugated surface (p = 0.049) were the most significant histological parameters distinguishing recurrent and non-recurrent OKCs. Amongst the classifiers, DenseNet-121 showed 93% accuracy in predicting recurrent OKCs. Furthermore, integrating and training the traditional ensemble model showed an accuracy of 95% and an AUC of 0.9872, with an execution time of 192.9 s. In comparison, our proposed model showed 97% accuracy with an execution time of 154.6 s. (4) Conclusions: Considering the outcome of our novel ensemble model, based on accuracy and execution time, the presented design could be embedded into a computer-aided design system for automation of risk stratification of odontogenic keratocysts.

Role of Toothbrushes as Gene Expression Profiling Tool for Oral Cancer Screening in Tobacco and Alcohol Users.

AIM: The use of toothbrushes was investigated as a potential RNA source and gene expression profiling tool for oral cancer screening in tobacco and alcohol users. METHODOLOGY: A total of 20 subjects were selected on the basis of inclusion and exclusion criteria. They were divided into two groups: group I-healthy controls (n = 6); group II-individuals who consume tobacco and alcohol (n = 14). After the volunteers brushed their teeth using a soft-bristle toothbrush with ~0.5 gm of toothpaste, the toothbrushes were collected, and the gene expression of BAX, BCL2, CDK4, CKDN2A, GNB3, and TCF7L2 was assessed. RESULTS: The gene expression of BAX decreased significantly in alcoholics and smokers (0.13867 ± 0.12014), while the gene expression of BCL2 increased in alcoholics and smokers (1.91001 ± 0.90425) in comparison with healthy controls (p = 0.0054 and p = 0.0055). Although there was increased expression of CDK4, CKDN2A, and TCF7L2 and decreased expression of GNB3 in smokers and alcoholics, the results were not significant. CONCLUSIONS: A toothbrush is a good source of RNA, and gene expression analysis can be performed using the genetic material retrieved from toothbrushes, which can aid in the early diagnosis of oral squamous cell carcinoma among tobacco and alcohol users. Further studies with a larger sample size and different durations of toothbrush use should be conducted to explore the role of toothbrushes as a noninvasive tool for disease diagnosis.