Vertebral lamina milling task is one of the high-risk operations in spinal surgeries. The operation is to remove part of vertebral lamina and release the pressure on the spinal nerve. Because many important vessels an...Vertebral lamina milling task is one of the high-risk operations in spinal surgeries. The operation is to remove part of vertebral lamina and release the pressure on the spinal nerve. Because many important vessels and nerves are under the vertebral lamina, any incorrect operation may cause irreparable damage to patients. To improve the safety of lamina milling task, a fuzzy force control strategy is proposed in this paper. Primary experiments have been conducted on bone samples from different animals. The results show that, with the fuzzy force control strategy, the bone milling system can recognize all surgery states and halt the tool at the proper location, achieving satisfactory surgery performance.展开更多
Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring method.However,individual scoring is subjective and error prone.This study proposes an approach for aut...Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring method.However,individual scoring is subjective and error prone.This study proposes an approach for automated knee osteoarthritis classification based on deep neural networks.The knee X-ray images are first preprocessed with frequency-domain filtering and histogram normalisation,making the trabecular bone texture more obvious and benefiting the subsequent classification task.Then,a two-step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet-50 network.In addition,a rebalance operation is proposed to deal with the dataset unbalance problem,and a quick search technique is proposed to improve the iterative search efficiency for the joint centre.With all of these techniques,a classification accuracy of 81.41%is obtained,which is higher compared to the state-of-the-art approaches.展开更多
文摘Vertebral lamina milling task is one of the high-risk operations in spinal surgeries. The operation is to remove part of vertebral lamina and release the pressure on the spinal nerve. Because many important vessels and nerves are under the vertebral lamina, any incorrect operation may cause irreparable damage to patients. To improve the safety of lamina milling task, a fuzzy force control strategy is proposed in this paper. Primary experiments have been conducted on bone samples from different animals. The results show that, with the fuzzy force control strategy, the bone milling system can recognize all surgery states and halt the tool at the proper location, achieving satisfactory surgery performance.
基金supported by the National Natural Science Foundation of China(No.U1713218,No.12026604,and No.62003330)the Shenzhen Science and Technology Program(No.JCYJ20180507182215361,No.JCYJ20200109114233670,and No.JCYJ20200109112818703)supported by the Guangdong Provincial Key Laboratory of Robotics and Intelligent System,Shenzhen Institutes of Advanced Technology.
文摘Currently X-ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence(KL)scoring method.However,individual scoring is subjective and error prone.This study proposes an approach for automated knee osteoarthritis classification based on deep neural networks.The knee X-ray images are first preprocessed with frequency-domain filtering and histogram normalisation,making the trabecular bone texture more obvious and benefiting the subsequent classification task.Then,a two-step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet-50 network.In addition,a rebalance operation is proposed to deal with the dataset unbalance problem,and a quick search technique is proposed to improve the iterative search efficiency for the joint centre.With all of these techniques,a classification accuracy of 81.41%is obtained,which is higher compared to the state-of-the-art approaches.