CT radiomics with transfer learning features for detecting DECT−positive periarticular monosodium urate crystal deposition: a single−center retrospective study - Scorecard - 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 Scorecard: Utilizing Transfer Learning in CT Radiomics for the Identification of DECT-Positive Periarticular Monosodium Urate Crystal Deposits: A Retrospective Analysis from a Single Center

At a Glance

CategoryDetail
ConditionPeriarticular Monosodium Urate Crystal Deposition
Key MechanismsSingle-energy CT radiomics and deep learning models for non-invasive detection.
Target PopulationPatients with suspected periarticular MSU deposition.
Care SettingRadiology departments utilizing single-energy CT imaging.

Key Highlights

  • Study included 605 patients with suspected periarticular MSU deposition.
  • Combined model achieved accuracy of 0.889, sensitivity of 0.905, and specificity of 0.837.
  • Deep learning radiomics model outperformed clinical model significantly.
  • Reference standard for MSU deposition was defined by dual-energy CT (DECT).
  • Single-energy CT is more widely accessible compared to DECT.

Guideline-Based Recommendations

Diagnosis

  • Detection of MSU crystals in synovial fluid or tophus aspirate remains the gold standard.

Management

  • Utilization of imaging modalities like single-energy CT for non-invasive assessment.

Monitoring & Follow-up

  • Regular assessment of serum uric acid levels and imaging as needed.

Risks

  • Invasive procedures like arthrocentesis are operator-dependent and not well accepted.

Patient & Prescribing Data

Patients with suspected periarticular MSU deposition.

Imaging plays a crucial role in early or atypical presentations of gout.

Clinical Best Practices

  • Incorporate radiomics and deep learning models in imaging protocols.
  • Consider patient-specific factors such as age and serum uric acid levels.

Related Resources & Content

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

From uric acid to tophi: multistage molecular and cellular mechanisms of tophi formation

Who Decides When a Doctor Steps Back?

Cognitive decline, credentialing, and why “I’ll know” often isn’t enough.

Evaluating the Quality and Content of Videos on Gout Available on Online Platforms: A Cross-Sectional Analysis