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. INDEX TERMS Composite annotation, deep learning, image classification, object detection, oral cancer, oral potentially malignant disorders.

The results suggest that tacrolimus 0.1% cream is an effective alternative to topical steroid and can be considered a first-line therapy in OLP. However, further studies are needed to confirm the effectiveness of this treatment before it is recommended for use in clinical practice.

Oral Submucous fibrosis (OSMF) has traditionally been described as "a chronic, insidious, scarring disease of the oral cavity, often with involvement of the pharynx and the upper esophagus". Millions of individuals are affected, especially in South and South East Asian countries. The main risk factor is areca nut chewing. Due to its high morbidity and high malignant transformation rate, constant efforts have been made to develop effective management. Despite this, there have been no significant improvements in prognosis for decades. This expert opinion paper updates the literature and provides a critique of diagnostic and therapeutic pitfalls common in developing countries and of deficiencies in management. An inter-professional model is proposed to avoid these pitfalls and to reduce these deficiencies.

BackgroundHealth Related Quality of Life (HRQoL) is an important outcome measure in health economic evaluation that guides health resource allocations. Population norms for HRQoL are an essential ingredient in health economics and in the evaluation of population health. The aim of this study was to produce EQ-5D-3L-derived population norms for Sri Lanka.MethodA population sample (n =  780) was selected from four districts of Sri Lanka. A stratified cluster sampling approach with probability proportionate to size was employed. Twenty six clusters of 30 participants each were selected; each participant completed the EQ-5D-3L in a face-to-face interview. Utility weights for their EQ-5D-3L health states were assigned using the Sri Lankan EQ-5D-3L algorithm. The population norms are reported by age and socio-economic variables.ResultsThe EQ-5D-3L was completed by 736 people, representing a 94% response rate. Sixty per cent of the sample reported being in full health. The percentage of people responding to any problems in the five EQ-5D-3L dimensions increased with age. The mean EQ-5D-3L weight was 0.85 (SD 0.008; 95%CI 0.84-0.87). The mean EQ-5D-3L weight was significantly associated with age, housing type, disease experience and religiosity. People above 70 years of age were 7.5 times more likely to report mobility problems and 3.7 times more likely to report pain/discomfort than those aged 18-29 years. Those with a tertiary education were five times less likely to report any HRQoL problems than those without a tertiary education. A person living in a shanty was 4.3 more likely to have problems in usual activities than a person living in a single house.ConclusionThe population norms in Sri Lanka vary with socio-demographic characteristics. The socioeconomically disadvantaged have a lower HRQoL. The trends of population norms observed in this lower middle income country were generally similar to those previously reported in high income countries.

ObjectiveCancer of the oral cavity is the leading malignancy among males in Sri Lanka, and sixth among women. This study aimed to estimate costs of managing patients with oral cancer (OCA) in Sri Lanka for a 12 month period from diagnosis.DesignHospital based costing study.SettingsFour selected cancer treatment centres in Sri Lanka.ParticipantsSixty-nine OCA patients: 60 were males and 12 had recurrent tumours.OutcomeSocietal perspectives (healthcare, household and indirect costs) were itemised. Costs to the healthcare system included surgery, Intensive Care Unit (ICU) care, chemotherapy and radiotherapy. Capital costs including apportioned value of land, buildings, equipment and furniture. Household costs consisted of out of pocket expenditure for healthcare and indirect costs of lost income. Costs were estimated from the stage of presentation for treatment to 1 year of follow-up.ResultsMean cost of managing a single stage II OCA patient for 1 year was Sri Lankan rupees (SLR) 58 979 (US$394, at the midyear exchange rate in 2016) to the health system. Mean household cost was SLR 77 649 (US$518). The annual cost of managing a stage III or IV patient was SLR 303 620 (US$2027), with household costs of SLR 71 932 (US$480).ConclusionsOwing to the high incidence of OCA in Sri Lanka, the economic costs associated with these diseases are enormous, resulting in negative impacts on both the healthcare system and individual families, seriously impacting the country’s economy. Policy-makers should take note of this burden and increase steps for prevention and control of this devastating disease.