More patients diagnosed with stage I (local) melanoma die than any other metastatic stage, because there exists no biomarker to reliably diagnose metastatic melanoma, preventing many patients from receiving appropriate treatment. We pursue an approach based on femtosecond pump-probe microscopy of melanin; a natural pigment found in most melanoma. The measured pump-probe signals of melanin are complex superpositions of multiple nonlinear processes, making interpretation challenging, especially for clinical applications. We will provide updates on our latest progress in experimental techniques such as polarization pump-probe microscopy that allow for cleaner decomposition of measured signals into fundamental physical interactions. We will also discuss supervised learning algorithms for classification and their application to metastatic melanoma diagnosis, and compare them to conventional data analysis methods such as fitting.
|