Transcranial magnetic stimulation (TMS) is a non-invasive clinical technique used for treatment of several neurological diseases such as depression, Alzheimer’s disease and Parkinson’s disease. However, it is always challenging to accurately adjust the electric field on different specific brain regions due to the requirement of several stimulation parameters’ optimizations. A major factor of brain induced electric field is the inter-subject variability, therefore a computer simulation is frequently used to simulate different TMS setups using anatomical models generated from MR images of the examined subject. Human head models are generated by segmentation of MR images into different anatomical tissues with a uniform electric conductivity value for each tissue. This process is time-consuming and requires a special experience to segment a relatively large number of tissues.

In this paper, we propose a deep convolution network for human head segmentation that is convenient for simulation of electrical field distribution, such as TMS. The proposed network is used to generate head models and is evaluated using TMS simulation studies. Results indicate that the head models generated using the proposed network demonstrate strong matching results with those achieved from manually segmented ones.