From Pixels to Diagnosis: Algorithmic Analysis of Clinical Oral Photos for Early Detection of Oral Squamous Cell Carcinoma

Simple Summary The early detection of oral squamous cell carcinoma (OSCC) is crucial because the prognosis is significantly better when diagnosed in its initial stages as opposed to advanced ones. We investigate the use of clinical photographic images captured by common smartphones for the automatic detection of OSCC cases and the identification of suspicious cases necessitating an urgent biopsy. We study a cohort of 1470 patients and examined various deep learning methods for the early detection of OSCC and suspicious cases. Our results demonstrate the efficacy of these methods in predicting both tasks, providing a comprehensive understanding of the patient's condition. Moreover, we demonstrate that the models exhibit enhanced accuracy in differentiating specific patient groups, particularly those with lesions in the lingual mucosa, floor of the mouth, or posterior tongue. These results underscore the potential of leveraging clinical photographic images for the timely and accurate identification of OSCC, with a particular emphasis on specific anatomical locations.Abstract Oral squamous cell carcinoma (OSCC) accounts for more than 90% of oral malignancies. Despite numerous advancements in understanding its biology, the mean five-year survival rate of OSCC is still very poor at about 50%, with even lower rates when the disease is detected at later stages. We investigate the use of clinical photographic images taken by common smartphones for the automated detection of OSCC cases and for the identification of suspicious cases mimicking cancer that require an urgent biopsy. We perform a retrospective study on a cohort of 1470 patients drawn from both hospital records and online academic sources. We examine various deep learning methods for the early detection of OSCC cases as well as for the detection of suspicious cases. Our results demonstrate the efficacy of these methods in both tasks, providing a comprehensive understanding of the patient's condition. When evaluated on holdout data, the model to predict OSCC achieved an AUC of 0.96 (CI: 0.91, 0.98), with a sensitivity of 0.91 and specificity of 0.81. When the data are stratified based on lesion location, we find that our models can provide enhanced accuracy (AUC 1.00) in differentiating specific groups of patients that have lesions in the lingual mucosa, floor of mouth, or posterior tongue. These results underscore the potential of leveraging clinical photos for the timely and accurate identification of OSCC.