Superimposition of cranio-maxillofacial images acquired from cone-beam computed tomography (CBCT) and facial images acquired from three-dimensional photography (3D photography) can assist in diagnosis and surgical planning. Conventional approaches individually identified prominent facial landmarks on both modalities, respectively and assessed their correspondence. Considering, however, variation of facial expressions or drastic feature distortion when the face or head was imaged at different timing, landmark registration can become challenging. This paper proposes a disturbance-region removal (DRR) procedure to improve the efficacy of registration. The disturbance regions (DRs) are defined as those exhibiting strong responses in the concavity intensity maps that are computed from the facial surface mesh. Following this identification process for the DRs, an adapted symmetric region growing algorithm is used to form the connected DRs that are to be removed prior to superimposition of both modalities. The results show a twenty-eight percent better match of overall correspondence of the facial fiducial markers. Instead of being the registration guides in conventional approaches, in this study the fiducial markers are employed as only a means to assess the performance of registration
Detection of altered hippocampal morphology in multiple sclerosis-associated depression using automated surface mesh modeling