CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study - Report - MDSpire

CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study

  • By

  • Weitao Huang

  • Xingjian Xu

  • Yongjun Ye

  • Yuguo Wei

  • Wenqiang Zheng

  • Xiaowei Han

  • Guozheng Zhang

  • July 1, 2026

  • 0 min

Share

Clinical Report: Utilizing Transfer Learning in CT Radiomics for MSU Detection

Overview

This study developed and validated radiomics and deep learning models for non-invasive detection of periarticular monosodium urate (MSU) crystal deposition using single-energy CT. The combined model achieved an accuracy of 0.889 in the validation cohort.

Background

Gout, caused by MSU crystal deposition, is associated with various metabolic comorbidities and is traditionally diagnosed through invasive methods. Non-invasive imaging techniques, particularly single-energy CT, are being explored for the detection of MSU deposits, especially in settings where dual-energy CT is unavailable.

Data Highlights

ModelAUCAccuracySensitivitySpecificity
Clinical0.820---
Radiomics0.912---
Deep Learning Radiomics (DLR)0.940---
Combined0.9420.8890.9050.837

Key Findings

  • Serum uric acid, age, bone erosion, and CT value were independently associated with MSU deposition.
  • The combined model achieved the highest accuracy of 0.889 in the validation cohort.
  • The DLR and combined models significantly outperformed the clinical model (DeLong P < 0.05).
  • No significant difference was found between the performance of the DLR and combined models.
  • This study is the first to combine hand-crafted radiomics with ResNet50-based transfer learning for MSU detection.

Clinical Implications

This study presents models that may enhance the non-invasive detection of MSU crystal deposition.

Conclusion

The study shows that single-energy CT-based radiomics and deep learning models can identify periarticular MSU deposition, with the combined model achieving an accuracy of 0.889.

Related Resources & Content

  1. Frontiers | CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study
  2. Multicenter Study Demonstrates Accurate Classification of Anhydrous Uric Acid Stones Using Noninvasive CT Radiomics and Clinical Models
  3. Frontiers in Oncology — Radiomics-based interpretable machine learning model from multiphasic CT imaging for predicting pathological grade in upper tract urothelial carcinoma: a multicenter study
  4. Evaluation of Radiomics Approaches and Dual-Energy Material Decomposition for Analyzing Abdominal Lymphoma in Contrast-Enhanced CT Scans
  5. Current guidance on gout diagnosis and imaging recommendations
  6. Dual‑Energy CT in Inflammatory Arthritis: A Comprehensive Review - PMC
  7. European Radiology — Utilizing Radiomics and Machine Learning for the Evaluation of Renal Tumor Subtypes via Multiphase CT in a Multicenter Study
  8. untitled
  9. Dual‑Energy CT in Inflammatory Arthritis: A Comprehensive Review - PMC
  10. Frontiers | CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study

Original Source(s)

CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study

  • by Weitao Huang, Xingjian Xu, Yongjun Ye, Yuguo Wei, Wenqiang Zheng, Xiaowei Han, Guozheng Zhang

  • July 1, 2026

Related Content

NPs Top US Jobs List Again

The nurse practitioner profession claims the No. 1 spot across three categories in the U.S. News & World Report 2026 Best Jobs rankings for the third consecutive year.

AI Scribes Lag Clinicians on Note Quality

A VHA study across 11 vendors finds AI-generated primary care notes score lower than clinician-written notes, with the largest deficits in thoroughness, organization, and usefulness

Allopurinol, gout, and cardiovascular risk