Hydrocephalus is a neurological disease which occurs when normal cerebrospinal fluid (CSF) circulation is impeded within the cranial cavity. As a result, the brain ventricles enlarge, and the tissue compresses, causing physical and mental problems. Treatment has been mainly through CSF flow diversion by surgically implanting a CSF shunt in the brain ventricles or by performing an endoscopic third ventriculostomy (ETV). However, the patient response to either treatment continues to be poor. Therefore, there is an urgent need to design better therapy protocols for hydrocephalus. An important step in this direction is the development of predictive computational models of the mechanics of hydrocephalic brains. In this paper, we propose a combined level set/mesh warping algorithm to track the evolution of the ventricles in the hydrocephalic brain. Our combined level set/mesh warping method is successfully used to track the evolution of the brain ventricles in two hydrocephalic patients.