Objective:

To develop and validate single−energy CT (135 kVp)−based radiomics and deep learning models for the non−invasive detection of periarticular monosodium urate (MSU) crystal deposition.

Approach:

• Feature Extraction: Hand-crafted radiomics features were extracted from lesion ROIs and selected using t-test, Pearson correlation, LASSO, and mRMR. Deep features were derived from the maximum cross-sectional ROI using a ResNet50 transfer learning framework, and fused features underwent the same selection.

Key Findings:

• Serum uric acid (OR 1.003), age (OR 1.017), bone erosion (OR 3.476), and CT value (OR 0.993) were independently associated with MSU deposition (all P < 0.05).
• AUCs for the validation cohort were 0.820 (clinical), 0.912 (radiomics), 0.940 (DLR), and 0.942 (combined).
• The combined model achieved accuracy 0.889, sensitivity 0.905, and specificity 0.837.
• DLR and combined models significantly outperformed the clinical model (DeLong P < 0.05), with no significant difference between them.

Interpretation:

The single-energy CT-based radiomics and deep learning radiomics models showed comparable performance for identifying periarticular MSU deposition, with no statistically significant difference.

Limitations:

• The reference standard was DECT-positive deposits, not the gold standard of MSU crystal detection in synovial fluid.
• DECT's limited sensitivity for non−tophaceous lesions may affect results.

Conclusion:

The combined clinical−imaging model achieved numerically higher performance but did not significantly outperform the deep learning radiomics model.