Analysis of imaging modalities for classification of tumoral vs. normal tissues using an FD-FLIM based MMF endoscopy probe

Current surgical resections for Head and Neck Cancers aim for clear margins to prevent local recurrence. However, up to 20% of cases result in positive margins, with secondary surgery increasing the chances of death after 5 years. We envision a MMF endoscope that collects high resolution images using wavefront shaping to scan a 405 nm beam at the fiber tip and collecting fluorescence intensity and lifetime to map tumor margins and detect residual malignant cells. To address the question whether the information contained in the fluorescence and morphology can be used to classify cancer and normal tissues, we used images acquired with a microscope and artificial neural network. Initial findings show promise to separate cancer from normal tissue when training neural networks on FLIM data. Spatial and temporal resolution and required field of view for effective margin assessment are determined.