Anatomical Feature Segmentation of Femur Point Cloud Based on Medical Semantics

Feature segmentation is an essential phase for geometric modeling and shape processing in anatomical study of human skeleton clinical digital treatment orthopedics. Due to various degrees freedom bone surface, the existing algorithms can hardly meet specific medical need. To address this, a novel methodology features femur model based on semantics put forward. First, reference objects (ARO) are created represent typical characteristics anatomy by 3D point fitting combination with priori knowledge. Then, local clouds between adjacent anatomies selected according AROs extract boundary feature (BFP)s. Finally, complete divided into regions executing enhanced watershed algorithm guided BFPs. Experimental results show that proposed method has advantages automatic femoral head, neck other complex areas, have better semantics. In addition, slight modification be achieved adjusting few threshold parameter values, which improves convenience ordinary users.