No abstract

Background: Manual landmarking is a time consuming and highly professional work.Although some algorithm-based landmarking methods have been proposed, they lack flexibility and may be susceptible to data diversity. Methods: The CT images from 66 patients who underwent oral and maxillofacial surgery (OMS) were landmarked manually in MIMICS. Then the CT slices were exported as images for recreating the 3D volume. The coordinate data of landmarks were further processed in Matlab using a principal component analysis (PCA) method. A patch-based deep neural network model with a three-layer convolutional neural network (CNN) was trained to obtain landmarks from CT images. Results: The evaluating experiment showed that this CNN model could automatically finish landmarking in an average processing time of 37.871 seconds with an average accuracy of 5.785 mm. Conclusion: This study shows a promising potential to relieve the workload of the surgeon and reduces the dependence on human experience for OMS landmarking. K E Y W O R D S 3D cephalometry, automatic landmarking, convolutional neural network, machine learning, oral and maxillofacial surgery

Background Human‐related factors affect the accuracy and safety of the oral and maxillofacial surgery (OMS). This study proposed an autonomous surgical system aiming to conduct the OMS under the assistance and surveillance of the surgeon. Methods A markerless navigation module and a compact OMS robot were seamlessly integrated into this system. The specifications of each module and the working concept of the system were elaborated in this paper. A drilling experiment was conducted on five 3D‐printed mandible models to test the pose detecting capability and evaluate the operational performance. Results The experiment showed that this system could successfully guide the robot finishing the operation regardless of the mandible pose. The accuracy of software and hardware are acceptable and potential performance improvement can be achieved in positioning accuracy. Conclusion This system proposed a novel concept and a practical solution to decrease the human‐related factors on the OMS, which may change the role of the surgeon in the future operating room and finally benefit the outcomes of OMS.

No abstract

SUMMARYIt is well known that multi-input, multi-output nature of nonlinear system and generalized exosystem have posed some challenges to output regulation theory. Recently, the global robust output regulation problem for a class of multivariable nonlinear system subject to a linear neutrally stable exosystem has been studied. It has been shown that a linear internal model-based state feedback control law can lead to the solution of previous problem. In this paper, we will further study the global robust output regulation problem of the system subject to a nonlinear exosystem. By utilizing nonlinear internal model design and decomposing the multi-input control problem into several single-input control problems, we will solve the problem by recursive control law design. The theoretical result is applied to the non-harmonic load torque disturbance rejection problem of a surface-mounted permanent magnet synchronous motor.