Deep Ensemble Learning and Transfer Learning Methods for Classification of Senescent Cells in Nonlinear Optical Microscopy Images

Successful chemotherapy and radiotherapy anti-cancer treatments may result in either tumour suppression or senescence induction. Until recently, experts agreed that senescence was a condition of durable growth arrest, promoting it as a favourable therapeutic outcome. However, recent advancements in oncology research evidence senescence as one of the culprits of cancer relapse [1]. Senescence is a complex phenotype, and no specific marker exists, so that multiple assays are required. A solution for fast, non-invasive, and label-free detection of therapy-induced senescent cells comes from nonlinear optical (NLO) microscopy.