A custom, patient-specific unicompartmental knee replacement was developed using a unsupervised neural network trained on a database of healthy knee geometries. This custom implant was then compared to a conventional implant in terms of contact stress in a Finite Element Model. The custom implant experienced lower contact stresses at the tibiofemoral joint compared to the conventional implant. The custom implant stresses were further reduced with the use of a customized mobile bearing. The custom implant also displayed more uniform stress distribution at the bone-implant interface.
展开▼
