Point of Care Detection and Diagnosis of Oral Cancer using a Low Cost Imaging Module enabled by AI - PROJECT SUMMARY/ABSTRACT The overall vision of the proposed project is to develop, deploy, and evaluate the technical feasibility of an affordable automated point-of-care (POC) telecytology platform for oral cancer screening that will facilitate earlier identification and risk stratification of suspicious oral lesions in community settings and enable timely referral for definitive diagnosis and treatment. Oral cancer is a significant global public health problem in India; 77,000 new cases and 52,000 deaths are reported annually, representing approximately one-quarter of the global disease burden. Approximately 70% of cases present at an advanced stage, when the probability of cure is substantially reduced and the five-year survival rate is approximately 20%. It has been estimated that early diagnosis, coupled with timely and appropriate treatment, could improve survival rates to as high as 90%. While the burden is particularly high in India, oral cavity and oropharyngeal cancers also represent a significant healthcare challenge in the United States, with approximately 60,000 new cases diagnosed annually. Delays in diagnosis remain common, particularly in underserved and rural populations where access to specialists and pathology services may be limited. Consequently, a rapid, affordable point-of-care assessment platform has the potential to improve care pathways not only in low-resource settings but also in U.S. community healthcare environments by enabling earlier identification, faster referral, and more timely treatment. In the United States, visual oral examination performed by dentists, oral surgeons, and otolaryngologists (ENT physicians) is widely used as an adjunctive screening approach; however, definitive diagnosis still relies on tissue biopsy and pathology review. A portable telecytology platform capable of providing rapid cytologic assessment at the point of care could help bridge this gap, support risk stratification of suspicious lesions, expedite referrals, and reduce delays to definitive diagnosis. Our proposed approach comprises a portable system for scanning brush biopsy cytology slides with cloud connectivity for transmission of images to pathologists and/or automated assessment via a validated algorithm for identification of atypical cells. Following standard visual assessment during routine screening, patients identified with suspicious or higher-risk lesions will immediately undergo brush biopsy sampling on the same visit. Samples will be placed on a glass slide, stained, and imaged using the portable slide scanner. Initially, these images will be transmitted via the cloud to a remote pathologist for review and assessment. Subsequent versions of the prototype will incorporate embedded artificial intelligence (AI) algorithms capable of automated detection and classification of atypical cells directly at the point of care. Community-based studies will evaluate the technical performance, workflow implementation, and agreement of telecytology and AI-assisted assessments relative to standard-of-care incisional biopsy and histopathology. We believe this scalable and affordable workflow can substantially reduce delays between screening, assessment, and referral, enabling earlier intervention and treatment for patients with oral cancer. By providing rapid assessment in community settings, the platform has the potential to expand access to specialist expertise, improve patient navigation, and support more timely and equitable cancer care in both resource-limited and developed healthcare environments.
