JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Automatic Lugano staging for risk stratification in lymphoma: a multicenter PET radiomics and machine learning study with survival analysis

  • 0Department of Medical Radiation Engineering.
Nuclear Medicine Communications +

|

September 3, 2025

|

September 3, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed an automated machine learning model using radiomics from PET/CT scans for lymphoma staging. The model accurately differentiates early from advanced stages, improving diagnostic efficiency and patient prognosis.

Area Of Science

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Oncology

Background

  • Lymphoma staging is crucial for treatment and prognosis but relies on subjective PET/CT interpretation.
  • Manual interpretation is time-consuming, subjective, and prone to variability.
  • Automated staging can enhance diagnostic accuracy and clinical workflow.

Purpose Of The Study

  • To introduce a novel radiomics-based machine learning model for automated lymphoma staging.
  • To improve diagnostic accuracy and streamline clinical workflow in lymphoma management.
  • To evaluate the model's performance in distinguishing early-stage from advanced-stage lymphoma.

Main Methods

  • Retrospective analysis of PET/CT imaging data from 241 lymphoma patients.
  • Extraction of radiomics features from segmented nodal and extranodal lesions.
  • Training and evaluation of Logistic Regression, Random Forest, and XGBoost classifiers for staging.

Main Results

  • The logistic regression model with nodal and extranodal features achieved an AUC of 0.87 and sensitivity of 0.88.
  • Inclusion of extranodal features significantly improved classification accuracy (AUC: 0.87 vs. 0.75).
  • Advanced-stage patients showed a fourfold higher mortality risk; key radiomic features correlated with Lugano criteria.

Conclusions

  • PET radiomics features show potential for automated Lugano staging.
  • Incorporating extranodal features significantly enhances staging accuracy.
  • Automated staging can inform treatment decisions and improve patient outcomes.

Keywords: