A Deep-Learning Model for Predicting the Efficacy of Non-vascularized Fibular Grafting Using Digital Radiography.

RATIONALE AND OBJECTIVES: To develop a fully automated deep-learning (DL) model using digital radiography (DR) with relatively high accuracy for predicting the efficacy of non-vascularized fibular grafting (NVFG) and identifying suitable patients for this procedure. MATERIALS AND METHODS: A retrospective analysis was conducted on osteonecrosis of femoral head patients who underwent NVFG between June 2009 and June 2021. All patients underwent standard preoperative anteroposterior (AP) and frog-lateral (FL) DR. Subsequently, the radiographs were pre-processed and labeled based on the follow-up results. The dataset was randomly divided into training and testing datasets. The DL-based prediction model was developed in the training dataset and its diagnostic performance was evaluated using the testing dataset. RESULTS: A total of 339 patients with 432 hips were included in this study, with a hip preservation success rate of 71.52% as of June 2023. The hips were randomly divided into a training dataset (n = 324) and a testing dataset (n = 108). The ensemble model in predicting the efficacy of NVFG, reaching an accuracy of 78.9%, a precision of 78.7%, a recall of 96.0%, a F1-score of 86.5%, and an area under the curve (AUC) of 0.780. FL views (AUC, 0.71) exhibited better performance compared to AP views (AUC, 0.66). CONCLUSION: The proposed DL model using DR enables automatic and efficient prediction of NVFG efficacy without additional clinical and financial burden. It can be seamlessly integrated into various clinical scenarios, serving as a practical tool to identify suitable patients for NVFG.

Sclerosis rim volume ratio and Japanese Investigation Committee classification as predictive factors for femoral head collapse progression after non-vascularized fibular grafting in osteonecrosis patients.

OBJECTIVE: The purpose of this retrospective cohort study was to determine the relationship between sclerosis rim volume ratio (SVR) and the progression of femoral head collapse after non-vascularized fibular grafting (NVFG) surgery in patients with osteonecrosis of the femoral head (ONFH), investigating risk factors associated with femoral head collapse progression and establishing a predictive model to enhance clinical decision-making. METHODS: ONFH patients who underwent NVFG between January 2008 and December 2021 were analyzed retrospectively to assess the risk of post-operative collapse progression (collapse >2 mm). A logistic regression model was used to evaluate the independent risk factors associated with collapse progression, including age, sex, etiology, affected side, Japanese Investigation Committee classification (JIC), and the sclerosis rim volume ratio (SVR). SVR values was collected from three weight-bearing columns, namely SVR1, SVR2, and SVR3, respectively. RESULTS: 57 patients with 64 hips who had undergone NVFG and were followed up for at least one year were included. During the follow-up, collapse＞2 mm occurred in 30 hips (46.88%). Multivariable analysis revealed that JIC (p =0.037) and SVR1 (p = 0.04) were independent risk factors for collapse progression after NVFG. The results of the receiver operating characteristic (ROC) analysis indicated that the aforementioned indices provided a satisfactory prediction of early femoral head collapse progression in ONFH patients after NVFG. The regression model using the above two indicators as a composite index showed satisfactory performance in predicting early postoperative femoral head collapse progression, with an area under the curve (AUC) of 84.6%. CONCLUSIONS: SVR is significant predictor of post-operative collapse progression following NVFG, and the composite index provides an optimal predictive value for femoral head collapse progression after surgery.