A Deep Learning-Based Approach to Extracting Periosteal and Endosteal Contours of Proximal Femur in Quantitative CT Images
This work provides an automated, accurate, and reproducible method for segmenting proximal femur contours, which is significant for clinicians and researchers in orthopedics for hip fracture risk prediction and finite element analysis, improving upon time-consuming manual methods.
This paper addresses the problem of automatically segmenting periosteal and endosteal contours of the proximal femur in quantitative CT images, which is crucial for orthopedic disease diagnosis. The authors developed a 3D end-to-end fully convolutional neural network that achieved Dice Similarity Coefficients of 97.87% for periosteal and 96.49% for endosteal contours, with volume measurement errors less than 5% compared to ground truth.
Automatic CT segmentation of proximal femur is crucial for the diagnosis and risk stratification of orthopedic diseases; however, current methods for the femur CT segmentation mainly rely on manual interactive segmentation, which is time-consuming and has limitations in both accuracy and reproducibility. In this study, we proposed an approach based on deep learning for the automatic extraction of the periosteal and endosteal contours of proximal femur in order to differentiate cortical and trabecular bone compartments. A three-dimensional (3D) end-to-end fully convolutional neural network, which can better combine the information between neighbor slices and get more accurate segmentation results, was developed for our segmentation task. 100 subjects aged from 50 to 87 years with 24,399 slices of proximal femur CT images were enrolled in this study. The separation of cortical and trabecular bone derived from the QCT software MIAF-Femur was used as the segmentation reference. We randomly divided the whole dataset into a training set with 85 subjects for 10-fold cross-validation and a test set with 15 subjects for evaluating the performance of models. Two models with the same network structures were trained and they achieved a dice similarity coefficient (DSC) of 97.87% and 96.49% for the periosteal and endosteal contours, respectively. To verify the excellent performance of our model for femoral segmentation, we measured the volume of different parts of the femur and compared it with the ground truth and the relative errors between predicted result and ground truth are all less than 5%. It demonstrated a strong potential for clinical use, including the hip fracture risk prediction and finite element analysis.