Scatter signatures in SFDI data enable breast surgical margin delineation via ensemble learning

Margin assessment in gross pathology is becoming feasible as various explanatory deep learning-powered methods are able to obtain models for macroscopic textural information, tissue microstructure, and local surface optical properties. Unfortunately, each different method seems to lack enough diagnostic power to perform an adequate classification on its own. This work proposes using several separately trained deep convolutional networks, and averaging their responses, in order to achieve a better margin assessment. Qualitative leave-one-out cross-validation results are discussed for a cohort of 70 samples.