Oral cancer is a major global health issue accounting for 177,384 deaths in 2018 and it is most prevalent in low- and middle-income countries. Enabling automation in the identification of potentially malignant and malignant lesions in the oral cavity would potentially lead to low-cost and early diagnosis of the disease. Building a large library of well-annotated oral lesions is key. As part of the MeMoSA ® (Mobile Mouth Screening Anywhere) project, images are currently in the process of being gathered from clinical experts from across the world, who have been provided with an annotation tool to produce rich labels. A novel strategy to combine bounding box annotations from multiple clinicians is provided in this paper. Further to this, deep neural networks were used to build automated systems, in which complex patterns were derived for tackling this difficult task. Using the initial data gathered in this study, two deep learning based computer vision approaches were assessed for the automated detection and classification of oral lesions for the early detection of oral cancer, these were image classification with ResNet-101 and object detection with the Faster R-CNN. Image classification achieved an F1 score of 87.07% for identification of images that contained lesions and 78.30% for the identification of images that required referral. Object detection achieved an F1 score of 41.18% for the detection of lesions that required referral. Further performances are reported with respect to classifying according to the type of referral decision. Our initial results demonstrate deep learning has the potential to tackle this challenging task.

Multiplexed biomarker protein detection holds unrealized promise for clinical cancer diagnostics due to lack of suitable measurement devices and lack of rigorously validated protein panels. Here we report an ultrasensitive electrochemical microfluidic array optimized to measure a four-protein panel of biomarker proteins, and we validate the protein panel for accurate oral cancer diagnostics. Unprecedented ultralow detection into the 5–50 fg·mL^–1 range was achieved for simultaneous measurement of proteins interleukin 6 (IL-6), IL-8, vascular endothelial growth factor (VEGF), and VEGF-C in diluted serum. The immunoarray achieves high sensitivity in 50 min assays by using off-line protein capture by magnetic beads carrying 400 000 enzyme labels and ∼100 000 antibodies. After capture of the proteins and washing to inhibit nonspecific binding, the beads are magnetically separated and injected into the array for selective capture by antibodies on eight nanostructured sensors. Good correlations with enzyme-linked immunosorbent assays (ELISA) for protein determinations in conditioned cancer cell media confirmed the accuracy of this approach. Normalized means of the four protein levels in 78 oral cancer patient serum samples and 49 controls gave clinical sensitivity of 89% and specificity of 98% for oral cancer detection, demonstrating high diagnostic utility. The low-cost, easily fabricated immunoarray provides a rapid serum test for diagnosis and personalized therapy of oral cancer. The device is readily adaptable to clinical diagnostics of other cancers.

Introduction: This study examined the concordance in clinical diagnosis of high-risk lesions in the oral cavity and referral decisions between clinical oral examination (COE) and teledentistry. Materials and Methods: Sixteen individuals with a range of oral potentially malignant disorders (OPMD) and normal oral mucosa were included. Five areas of the oral cavity were photographed by three dentists using mobile phone cameras with 5 MP-13 MP resolutions. On the same day, the patients were given COE by two oral medicine specialists (OMS) and 3 weeks later, they reviewed the images taken using the phone, and concordance was examined between the two by Kappa statistics. The sensitivity and specificity of clinical diagnosis using the phone images were also measured. Pre- and post-program questionnaires were answered by both the dentists and the OMS to determine the feasibility of integrating teledentistry in their clinical practice. Results: The Kappa values in determining the presence of lesion, category of lesion (OPMD or not), and making referral decision were moderate to strong (0.64–1.00). The overall sensitivity was more than 70% and specificity was 100%. The false negative rate decreased as the camera resolution increased. All dentists agreed that the process could facilitate early detection of oral mucosal lesion, and was easy to use in the clinic. Conclusions: This study provides evidence that teledentistry can be used for communication between primary care and OMS and could be readily integrated into clinical setting for patient management.

Background: Up to 86% of oral cancer (OC) patients present at the late stage where survival is dismal. Limited access to specialist diagnosis is a significant factor for late presentation. The increasing use of smartphones presents an opportunity to use digital technology to facilitate early detection of OC. Aim: To evaluate the feasibility of using Mobile Mouth Screening Anywhere (MeMoSA ^® ) to facilitate early detection of OC. Methods: A mobile phone app named MeMoSA was developed and the feasibility of integrating this for documentation of oral lesions, and communication between dentists and specialists for management decisions were evaluated. The experience of dentists and specialists in using MeMoSA was determined using qualitative questionnaires. Results: Communication between specialist and dentists using MeMoSA stratified cases and streamlined referral of patients. Twelve of 48 patients were found to have oral lesions or signs suspicious of cancer and 3 required referrals. The patient's compliance for referral was tracked with MeMoSA. All dentists agreed that MeMoSA could facilitate early detection of OC and believed that MeMoSA could assist in the identification of oral mucosal lesions through direct communication with specialists and continuous learning in the recognition of high-risk lesions. Conclusions: MeMoSA has the potential to be used to promote equitable health care and streamline patient management that could result in early detection of OC.

The drug discovery and development pipeline is a long and arduous process that inevitably hampers rapid drug development. Therefore, strategies to improve the efficiency of drug development are urgently needed to enable effective drugs to enter the clinic. Precision medicine has demonstrated that genetic features of cancer cells can be used for predicting drug response, and emerging evidence suggest that gene-drug connections could be predicted more accurately by exploring the cumulative effects of many genes simultaneously. We developed DeSigN, a web-based tool for predicting drug efficacy against cancer cell lines using gene expression patterns. The algorithm correlates phenotype-specific gene signatures derived from differentially expressed genes with pre-defined gene expression profiles associated with drug response data (IC50) from 140 drugs. DeSigN successfully predicted the right drug sensitivity outcome in four published GEO studies. Additionally, it predicted bosutinib, a Src/Abl kinase inhibitor, as a sensitive inhibitor for oral squamous cell carcinoma (OSCC) cell lines. In vitro validation of bosutinib in OSCC cell lines demonstrated that indeed, these cell lines were sensitive to bosutinib with IC50 of 0.8–1.2 μM. As further confirmation, we demonstrated experimentally that bosutinib has anti-proliferative activity in OSCC cell lines, demonstrating that DeSigN was able to robustly predict drug that could be beneficial for tumour control. DeSigN is a robust method that is useful for the identification of candidate drugs using an input gene signature obtained from gene expression analysis. This user-friendly platform could be used to identify drugs with unanticipated efficacy against cancer cell lines of interest, and therefore could be used for the repurposing of drugs, thus improving the efficiency of drug development.