Project

Research Area | Unorthodox Machine Learning Solutions for Cancer, Oral, and Infectious Diseases

Pratik Shah

Our published research findings listed below describe new paradigms for low-cost biomarker imaging and clinical diagnoses by obviating the need for specialized medical devices and biological processes at the point-of-care. We have demonstrated a novel, deep learning and classification approach for obtaining the medical diagnostic information of an organ using photographs captured by mobile phones and cameras. We have successfully demonstrated the utility of this approach in predicting fluorescent porphyrin biomarkers (associated with tumors and periodontal diseases) from standard white-light photographs of the mouth vs fluorescent images. We are expanding the repertoire of biomarkers that can be detected in RGB color images acquired at the point-of-care and pairing them with automated machine learning exams. 

Our published research findings listed below describe new paradigms for low-cost biomarker imaging and clinical diagnoses by obviating the need for specialized medical devices and biological processes at the point-of-care. We have demonstrated a novel, deep learning and classification approach for obtaining the medical diagnostic information of an organ using photographs captured by mobile phones and cameras. We have successfully demonstrated the utility of this approach in predicting fluorescent porphyrin biomarkers (associated with tumors and periodontal diseases) from standard white-light photographs of the mouth vs fluorescent images. We are expanding the repertoire of biomarkers that can be detected in RGB color images acquired at the point-of-care and pairing them with automated machine learning exams.