Aim The rate of physiological bone remodelling (PBR) occurring after implant placement has been associated with the later onset of progressive bone loss and peri-implantitis, leading to medium- and long-term implant therapy failure. It is still questionable, however, whether PBR is associated with specific bone characteristics. The aim of this study was to assess whether radiomic analysis could reveal not readily appreciable bone features useful for the prediction of PBR.Materials and Methods Radiomic features were extracted from the radiographs taken at implant placement (T0) using LifeX software. Because of the multi-centre design of the source study, ComBat harmonization was applied to the cohort. Different machine-learning models were trained on selected radiomic features to develop and internally validate algorithms capable of predicting high PBR. In addition, results of the algorithm were included in a multivariate analysis with other clinical variables (tissue thickness and depth of implant position) to test their independent correlation with PBR.Results Specific radiomic features extracted at T0 are associated with higher PBR around tissue-level implants after 3 months of unsubmerged healing (T1). In addition, taking advantage of machine-learning methods, a naive Bayes model was trained using radiomic features selected by fast correlation-based filter (FCBF), which showed the best performance in the prediction of PBR (AUC = 0.751, sensitivity = 66.0%, specificity = 68.4%, positive predictive value = 73.3%, negative predictive value = 60.5%). In addition, results of the whole model were included in a multivariate analysis with tissue thickness and depth of implant position, which were still found to be independently associated with PBR (p-value < .01).Conclusion The combination of radiomics and machine-learning methods seems to be a promising approach for the early prediction of PBR. Such an innovative approach could be also used for the study of not readily disclosed bone characteristics, thus helping to explain not fully understood clinical phenomena. Although promising, the performance of the radiomic model should be improved in terms of specificity and sensitivity by further studies in this field.
Can radiomic features extracted from intra-oral radiographs predict physiological bone remodelling around dental implants? A hypothesis-generating study
Troiano, Giuseppe;Zhurakivska, Khrystyna;
2023-01-01
Abstract
Aim The rate of physiological bone remodelling (PBR) occurring after implant placement has been associated with the later onset of progressive bone loss and peri-implantitis, leading to medium- and long-term implant therapy failure. It is still questionable, however, whether PBR is associated with specific bone characteristics. The aim of this study was to assess whether radiomic analysis could reveal not readily appreciable bone features useful for the prediction of PBR.Materials and Methods Radiomic features were extracted from the radiographs taken at implant placement (T0) using LifeX software. Because of the multi-centre design of the source study, ComBat harmonization was applied to the cohort. Different machine-learning models were trained on selected radiomic features to develop and internally validate algorithms capable of predicting high PBR. In addition, results of the algorithm were included in a multivariate analysis with other clinical variables (tissue thickness and depth of implant position) to test their independent correlation with PBR.Results Specific radiomic features extracted at T0 are associated with higher PBR around tissue-level implants after 3 months of unsubmerged healing (T1). In addition, taking advantage of machine-learning methods, a naive Bayes model was trained using radiomic features selected by fast correlation-based filter (FCBF), which showed the best performance in the prediction of PBR (AUC = 0.751, sensitivity = 66.0%, specificity = 68.4%, positive predictive value = 73.3%, negative predictive value = 60.5%). In addition, results of the whole model were included in a multivariate analysis with tissue thickness and depth of implant position, which were still found to be independently associated with PBR (p-value < .01).Conclusion The combination of radiomics and machine-learning methods seems to be a promising approach for the early prediction of PBR. Such an innovative approach could be also used for the study of not readily disclosed bone characteristics, thus helping to explain not fully understood clinical phenomena. Although promising, the performance of the radiomic model should be improved in terms of specificity and sensitivity by further studies in this field.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
