CT-Based Bone Habitat Radiomics for Predicting Risk of Vertebral Fracture in Older Adults: A Longitudinal Study

Area of Science:

• Radiology
• Osteoporosis Research
• Medical Imaging Analysis

Background:

• Osteoporotic vertebral fractures (OVF) are a significant health concern for aging populations.
• Current methods for predicting OVF risk often overlook the intricate heterogeneity of vertebral trabecular bone.
• Habitat radiomics offers a novel approach to quantify bone heterogeneity from CT scans.

Purpose of the Study:

• To develop and validate a habitat radiomics model for predicting the risk of new osteoporotic vertebral fractures (OVF) in individuals over 50 years old.
• To assess the performance of habitat radiomics in capturing vertebral bone heterogeneity for fracture prediction.
• To compare the predictive capability of habitat radiomics against traditional CT value and radiomics models.

Main Methods:

• A retrospective longitudinal study involving individuals over 50 without prior OVF, followed up for new fractures.
• Extraction of radiomic features from vertebral trabecular bone using K-means clustering for sub-region segmentation.
• Development and validation of a habitat radiomics nomogram model for fracture risk prediction.

Main Results:

• The habitat radiomics model demonstrated superior predictive performance compared to CT value and traditional radiomics models (AUC = 0.702).
• Habitat radiomics risk score was identified as an independent predictor of vertebral fractures (HR = 1.092, P < 0.001).
• The habitat radiomics nomogram achieved a C-index of 0.803 in the training set and 0.748 in the validation set.

Conclusions:

• Habitat radiomics effectively predicts vertebral fractures by analyzing vertebral bone heterogeneity.
• This novel approach shows improved performance over conventional bone density prediction methods for OVF risk assessment.
• Habitat radiomics holds promise for enhancing early detection and prevention strategies for osteoporotic vertebral fractures.