Affiliation:
1. Digital Center, School of Stomatology The Fourth Military Medical University, State Key Laboratory of Oral & Maxillofacial Reconstruction and Regeneration & National Clinical Research Center for Oral Diseases & Shaanxi Key Laboratory of Stomatology Xi'an Shaanxi China
2. Department of Stomatology 960 Hospital of the Chinese People's Liberation Army Jinan Shandong China
3. Department of Stomatology Xi'an No.3 Hospital, the Affiliated Hospital of Northwest University Xi'an Shaanxi China
4. Department of Plastic and Reconstructive Surgery, Department of Neurosurgery Xijing Hospital, Fourth Military Medical University Xi'an Shaanxi China
Abstract
AbstractObjectivesThis study aims at examining the correlation of intraosseous temperature change with drilling impulse data during osteotomy and establishing real‐time temperature prediction models.Materials and MethodsA combination of in vitro bovine rib model and Autonomous Dental Implant Robotic System (ADIR) was set up, in which intraosseous temperature and drilling impulse data were measured using an infrared camera and a six‐axis force/torque sensor respectively. A total of 800 drills with different parameters (e.g., drill diameter, drill wear, drilling speed, and thickness of cortical bone) were experimented, along with an independent test set of 200 drills. Pearson correlation analysis was done for linear relationship. Four machining learning (ML) algorithms (e.g., support vector regression [SVR], ridge regression [RR], extreme gradient boosting [XGboost], and artificial neural network [ANN]) were run for building prediction models.ResultsBy incorporating different parameters, it was found that lower drilling speed, smaller drill diameter, more severe wear, and thicker cortical bone were associated with higher intraosseous temperature changes and longer time exposure and were accompanied with alterations in drilling impulse data. Pearson correlation analysis further identified highly linear correlation between drilling impulse data and thermal changes. Finally, four ML prediction models were established, among which XGboost model showed the best performance with the minimum error measurements in test set.ConclusionThe proof‐of‐concept study highlighted close correlation of drilling impulse data with intraosseous temperature change during osteotomy. The ML prediction models may inspire future improvement on prevention of thermal bone injury and intelligent design of robot‐assisted implant surgery.