CT-Based Subchondral Bone Microstructural Analysis for Knee Osteoarthritis

A dataset supporting a method for analyzing subchondral trabecular microstructure in knee osteoarthritis using routine clinical CT scans. The dataset likely contains parameters derived from CT scans via a distillation learning model trained on high-resolution MRI data. It was authored by Yuqi Hu and last updated on April 10, 2026.

Use Cases

• Training machine learning models for trabecular parameter estimation based on CT scans mentioned in the description
• Benchmarking cross-modal distillation learning techniques based on MR-CT registration described
• Developing patient-level osteoarthritis diagnostic classifiers based on aggregated biomarker parameters
• Studying the relationship between subchondral bone microstructure and osteoarthritis progression based on the described biomarkers

Strengths

• The associated method achieved strong agreement (ICC = 0.742) with MR-derived references for trabecular biomarkers
• The method enabled patient-level osteoarthritis diagnosis with an AUC of 0.883, outperforming CT-only prediction
• Dataset is openly licensed under CC-BY-4.0

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The dataset is very small (68.2 KB), indicating limited scope

Provenance

Source

figshare

Collection Method

Likely derived from a clinical knee imaging cohort using a distillation learning method (CT-SMA)

Freshness

Last updated 2026-04-10 07:49:15