Background: The image registration using positron emission tomography (PET) and magnetic resonance imaging (MRI) has been studied extensively. The purpose of this project is to propose a patient-specific image registration model that can improve both the accuracy and efficiency of the registration process. Large-scale deformation of the breast makes image registration of the breast a challenging task. Usually, a patient undergoes MRI in the prone position and PET in the supine position. Registration of breast in supine position with breast in prone position is a challenge. Methods: Eight cases with corresponding pairs of PET/computed tomography (CT) and MRI breast images were used in this study for the performance of PET/MRI registration. Registration was based on a biomechanical finite element model that could simulate large-scale deformation of the breast under pressure. Results: In this study, an accurate patient-specific registration model was built with a target registration error (TRE) of 4.77±2.20 mm. Conclusion: Image deformation due to the effect of gravity was successfully modeled by the finite element method.