Metastatic disease in bone is characterized by highly amorphous and variable lesion geometry, with increased fracture risk. Assumptions of idealized lesion geometry made in previous finite element (FE) studies of metastatic disease in the proximal femur may not sufficiently capture effects of local stress/strain concentrations on predicted failure strength. The goal of this study was to develop and validate a FE failure model of the proximal femur incorporating artificial defects representative of physiologic metastatic disease. Data from 11 cadaveric femur specimens were randomly divided into either a training set (n = 5) or a test set (n = 6). Clinically representative artificial defects were created, and the femurs were loaded to failure under offset torsion. Voxel-based FE models replicating the experimental setup were created from the training set pre-fracture computed tomography data. Failure loads from the linear model with maximum principal strain failure criterion correlated best with the experimental data (R² = 0.86, p = 0.024). The developed model was found to be reliable when applied to the test dataset with a relatively low RMSE of 46.9 N, mean absolute percent error of 12.7 ± 17.1%, and cross-validation R² = 0.88 (p < 0.001). Models simulating realistic lesion geometry explained an additional 26% of the variance in experimental failure load compared to idealized lesion models (R² = 0.62, p = 0.062). Our validated automated FE model representative of physiologic metastatic disease may improve clinical fracture risk prediction and facilitate research studies of fracture risk during functional activities and with treatment interventions.

骨转移性疾病的特征是高度无定形和可变的病变几何形状，骨折风险增加。先前在股骨近端转移性疾病的有限元（FE）研究中做出的理想病变几何学假设可能无法充分捕获局部应力/应变浓度对预测破坏强度的影响。这项研究的目的是开发和验证结合了代表生理性转移性疾病的人工缺陷的股骨近端FE失败模型。来自11个尸体股骨标本的数据被随机分为训练集（n = 5）或测试集（n = 6）。创建了具有临床代表性的人工缺陷，并在偏置扭转下将股骨加载至衰竭。从训练集断裂前计算机断层扫描数据创建了复制实验设置的基于体素的有限元模型。具有最大主应变破坏准则的线性模型的破坏载荷与实验数据最相关（R²  = 0.86，p = 0.024）。当将开发的模型应用于测试数据集时，该模型是可靠的，具有46.9 N的相对较低的RMSE，12.7±17.1％的平均绝对百分比误差和交叉验证R ²  = 0.88（p <0.001）。与理想的病变模型相比，模拟实际病变几何形状的模型解释了实验失败负荷中的26％的方差（R ²  = 0.62，p = 0.062）。我们经过验证的代表生理转移性疾病的自动有限元模型可以改善临床骨折风险的预测，并促进功能活动和治疗干预期间骨折风险的研究。