Lee Youngjun, Bandara Wikum R, Park Sangjun, Lee Miran, Seo Choongboem, Yang Sunwoo, Lim Kenneth J, Moe Sharon M, Warden Stuart J, Surowiec Rachel K
Weldon School of Biomedical Engineering, Purdue University, West Lafayette, IN, United States of America.
Department of Radiation Therapy, Samsung Medical Center, The Sungkyunkwan University of Korea, South Korea.
Bone Rep. 2024 Dec 26;24:101821. doi: 10.1016/j.bonr.2024.101821. eCollection 2025 Mar.
High resolution peripheral quantitative computed tomography (HRpQCT) offers detailed bone geometry and microarchitecture assessment, including cortical porosity, but assessing chronic kidney disease (CKD) bone images remains challenging. This proof-of-concept study merges deep learning and machine learning to 1) improve automatic segmentation, particularly in cases with severe cortical porosity and trabeculated endosteal surfaces, and 2) maximize image information using machine learning feature extraction to classify CKD-related skeletal abnormalities, surpassing conventional DXA and CT measures. We included 30 individuals (20 non-CKD, 10 stage 3 to 5D CKD) who underwent HRpQCT of the distal and diaphyseal radius and tibia and contributed data to develop and validate four different AI models for each anatomical site. Manually annotated cortical bone was used to train each segmentation deep-learning model. Textural features were extracted via Gray-Level Co-occurrence Matrix (GLCM) and classified as CKD or non-CKD using XGBoost with each segmentation model. For comparison, manufacturer-supplied segmentation was used to extract cortical geometry, microarchitecture, and finite element analysis (FEA) outcomes. Model performance was confirmed using the test dataset and a separate independent validation cohort which included HRpQCT imaging from 42 additional individuals (18 non-CKD, 24 CKD stage 5D). For segmentation, the diaphyseal location showed strong performance on test datasets, with Mean IoUs of 0.96 and 0.95, and accuracies of 0.97 for both radius and tibia sites in CKD. Model 4 developed from the diaphyseal tibia region excelled in classifying test and independent validation datasets, achieving F1 scores of 0.99 and 0.96, AUCs of 0.99 and 0.94, sensitivities of 0.99, and specificities of 0.99 and 0.92. No single parameter, including BMD and cortical porosity, among conventional CT outcomes consistently differentiated CKD from non-CKD across all anatomical sites. Integrating HRpQCT with deep and machine learning, this innovative approach enables precise automatic segmentation of severely deteriorated endocortical surfaces and enhances sensitivity to CKD-related cortical bone changes compared to standard DXA and HRpQCT outcomes.
高分辨率外周定量计算机断层扫描（HRpQCT）可提供详细的骨几何结构和微结构评估，包括皮质骨孔隙率，但评估慢性肾脏病（CKD）的骨图像仍然具有挑战性。这项概念验证研究将深度学习和机器学习相结合，以1）改善自动分割，特别是在皮质骨孔隙率严重和骨小梁状骨内膜表面的情况下，以及2）使用机器学习特征提取最大化图像信息，以对CKD相关的骨骼异常进行分类，超越传统的双能X线吸收法（DXA）和CT测量。我们纳入了30名个体（20名非CKD患者，10名3至5D期CKD患者），他们接受了桡骨远端和骨干以及胫骨的HRpQCT检查，并贡献数据以开发和验证每个解剖部位的四种不同人工智能模型。使用手动标注的皮质骨来训练每个分割深度学习模型。通过灰度共生矩阵（GLCM）提取纹理特征，并使用XGBoost与每个分割模型将其分类为CKD或非CKD。为了进行比较，使用制造商提供的分割来提取皮质骨几何结构、微结构和有限元分析（FEA）结果。使用测试数据集和一个单独的独立验证队列来确认模型性能，该队列包括来自另外42名个体（18名非CKD患者，24名5D期CKD患者）的HRpQCT成像。对于分割，骨干部位在测试数据集上表现出强大的性能，在CKD患者中，桡骨和胫骨部位两者的平均交并比（Mean IoU）分别为0.96和0.95及准确率为0.97。从胫骨骨干区域开发的模型4在对测试和独立验证数据集进行分类方面表现出色，F1分数分别为0.99和0.96，曲线下面积（AUC）分别为0.99和0.94，灵敏度为0.99，特异性分别为0.99和0.92。在所有解剖部位，传统CT结果中的单一参数（包括骨密度和皮质骨孔隙率）均不能始终如一地将CKD与非CKD区分开来。将HRpQCT与深度学习和机器学习相结合，这种创新方法能够对严重恶化的骨内膜表面进行精确自动分割，并且与标准DXA和HRpQCT结果相比，增强了对CKD相关皮质骨变化的敏感性。
