Microphysiological system (MPS) is an in vitro culture technology that　reproduces the physiological microenvironment and functionality of humans, and is expected to be applied for evaluating drug efficiency/toxicity. In this study, we developed a MPS for structured culture of human iPSC-derived neurons, then predict drug-induced neurotoxicity by morphological analysis.COP (Cyclo olefin polymer), which has excellent observability and low drug adsorption, is used as the material of the MPS. Successful culture of human iPSC-derived sensory neurons and human iPSC-derived cortical neurons with separating neurites growth were achieved in the MPS for longer than 8 weeks. For human iPSC-derived sensory neurons, after administration of representative CIPN-related anti-cancer drugs (i.e., vincristine, and oxaliplatin), the toxic effects on soma and axons were evaluated by a deep learning image analysis, training two artificial intelligence (AI) models on soma and axonal area images. Combining results from two AI models, we detected significant toxicity in both drugs and could classify them based on different effects on soma or axon, suggesting that the current method provides an effective evaluation of CIPN. For cortical neurons, after administration of different types of Amyloid β, the toxic effects were evaluated by training two AI models on axonal and PSD-95 images. And the combined results indicated that Amyloid β1-42 and 1-40, but not 1-28, induced neuron degeneration, which is close to clinical reports.Taken together, it suggests that the present MPS combined with morphological deep learning is a useful platform for in vitro neurotoxicity assessment.