Transformer-Based Multi-Region Segmentation and Radiomic Analysis of HR-pQCT Imaging

2026-03-09

AI Summary

This study addresses the limitations of current osteoporosis diagnostic approaches, which often overlook bone microstructure and surrounding soft tissue information and fail to fully exploit the potential of high-resolution peripheral quantitative computed tomography (HR-pQCT) imaging. To overcome these gaps, the authors propose a fully automated analysis framework that, for the first time, applies Transformer-based architectures such as SegFormer to multi-region segmentation of HR-pQCT images, followed by refined post-processing for precise soft tissue delineation. From these segmentations, 939 radiomic features are extracted and used to train six classifiers for binary osteoporosis classification. Experimental results demonstrate a mean segmentation F1-score of 95.36%, with tendon-related radiomic features achieving 80.08% accuracy and an AUROC of 0.85. At the patient level, the model attains an AUROC of 0.875, confirming that soft tissue–derived radiomic features offer superior discriminative power compared to conventional bone parameters.

Technology Category

Computer Vision: SegmentationMachine Learning: Feature Construction/ReformulationKnowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

Web Mining and Content Analysis: Robustness and generalizability of Web mining methodsUser Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systemsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Osteoporosis is a skeletal disease typically diagnosed using dual-energy X-ray absorptiometry (DXA), which quantifies areal bone mineral density but overlooks bone microarchitecture and surrounding soft tissues. High-resolution peripheral quantitative computed tomography (HR-pQCT) enables three-dimensional microstructural imaging with minimal radiation. However, current analysis pipelines largely focus on mineralized bone compartments, leaving much of the acquired image data underutilized. We introduce a fully automated framework for binary osteoporosis classification using radiomics features extracted from anatomically segmented HR-pQCT images. To our knowledge, this work is the first to leverage a transformer-based segmentation architecture, i.e., the SegFormer, for fully automated multi-region HR-pQCT analysis. The SegFormer model simultaneously delineated the cortical and trabecular bone of the tibia and fibula along with surrounding soft tissues and achieved a mean F1 score of 95.36%. Soft tissues were further subdivided into skin, myotendinous, and adipose regions through post-processing. From each region, 939 radiomic features were extracted and dimensionally reduced to train six machine learning classifiers on an independent dataset comprising 20,496 images from 122 HR-pQCT scans. The best image level performance was achieved using myotendinous tissue features, yielding an accuracy of 80.08% and an area under the receiver operating characteristic curve (AUROC) of 0.85, outperforming bone-based models. At the patient level, replacing standard biological, DXA, and HR-pQCT parameters with soft tissue radiomics improved AUROC from 0.792 to 0.875. These findings demonstrate that automated, multi-region HR-pQCT segmentation enables the extraction of clinically informative signals beyond bone alone, highlighting the importance of integrated tissue assessment for osteoporosis detection.

Problem

• osteoporosis
• HR-pQCT
• radiomics
• soft tissue
• bone microarchitecture

Innovation

• SegFormer
• multi-region segmentation
• radiomic analysis
• HR-pQCT
• soft tissue characterization