For the majority of cancers, early detection results in better survival. Oral cancer is one of the few cancers that is visible and many of these cancers are preceded by a potentially malignant lesion where medical intervention can prevent the development of cancer. Taken together, oral cancer presents an opportunity for early detection. However, identifying which oral lesion has a propensity to become oral cancer is not straightforward without specialised training and this problem is confounded by the lack of specialists who are trained in this expertise particularly in low- and middle-income countries, where the majority of oral cancers are diagnosed. One innovative approach to overcome this is to develop an artificial intelligence algorithm to classify oral lesions into those that are benign and those that are potentially malignant or are occult cancer so that patients can be triaged accordingly to receive appropriate clinical management. In this project, we propose to work within a multi-disciplinary, international team to collate a library of images from existing and prospective collections that will facilitate the development of an artificial intelligence algorithm that will be tested and validated. The outcome of this project will pave the way for further rigorous testing, development of an App incorporating this automated tool and clinical validation for the early detection of oral cancer. The development of an automated tool for the classification of oral lesions will facilitate the identification of patients most at risk to develop oral cancer so that these individuals can be managed appropriately. This project is particularly impactful in the low- and middle-income countries as the majority of the global burden of oral cancer is found in these countries.

The research context: Nepal is classified as one of the lowest income countries on the Development Assistance Committee (DAC) list and the general health of the population is considered to be poor by most measures, even in comparison with the rest of Asia. Access to healthcare is severely restricted, particularly in rural regions, which is undoubtedly a limiting factor to progress, generally. We have identified a specific unmet clinical need within Nepal that is fully aligned with this call for proposals; aided as it could be by the provision of affordable, point-of-care imaging diagnostics. There is an unusually high prevalence (up to 43%) of the population in Nepal suffering from chronic obstructive pulmonary disease (COPD) and this has been the number one cause of death (>9%) there in recent years. This is thought to arise principally as a result of poor indoor air quality, with the condition being even more acute in difficult to reach, both geographically and economically, rural regions. It is particularly high amongst women, which may be largely attributable to the deeply embedded culture of indoor cooking and heating with biomass fuels Aims and objectives: Our aim is to develop a low cost miniaturized, integrated chip-based optical coherence tomography (OCT) based diagnostic tool which will provide a transformative change to the level of sophistication that access to such clinical imaging technology can bring to bear on COPD diagnosis and therapy. The key advance will stem from transitioning the fibre based interferometer at the heart of commercial OCT systems onto the silicon photonics chip, which will enable system complexity and cost reductions through manufacturing scalability. Silicon photonics is aptly suited to this because it is transparent at the target operating wavelength (1300nm) of most OCT systems and the required interferometer components have now all been demonstrated in isolation. Manufacturing of these sub-micron optical devices can be massively scaled at lower cost and to extremely high tolerances using the global passive fabrication infrastructure that has been built up around the telecommunications industry. In addition, many of these components have now also been realised in the silicon nitride (SiN) platform, extending capabilities down towards the visible range, which is particularly relevant to certain biomedical imaging regimes. We will develop SiN based interferometers in parallel with the silicon devices through wavelength scaled common optical circuit designs as proof of concept. Finally, we will take the ambitious step of developing a complete, fibre-less chip based solution by hybrid integration of miniature optical sources with the silicon/SiN based interferometers. Potential applications and benefits: The vision of a low complexity, low cost, miniature OCT system incorporated within existing bronchoscopy or catheter based medical devices that could be used along with commercially available data acquisition hardware and analytical software on a mobile platform is within reach. Such a system can provide the necessary access to a sophisticated imaging diagnostic tool that could displace basic spirometry and even fibre based bronchoscopy as the gold standard for early diagnosis of COPD. Its greatest benefit will be felt, initially, within remote regions of our partner LMIC country, Nepal where a high prevalence of the disease is exemplified and where access to such facilities is limited by both geography and economy. Improvements in resolution and speed for tissue imaging can also be expected to help improve our understanding of COPD progression in a fundamental way. For example the development and widespread adoption of the proposed OCT technology would generate population specific datasets of high quality for use by researchers and clinicians.