Back to all papers

Machine learning-based differentiation of benign and malignant adrenal lesions using 18F-FDG PET/CT: a two-stage classification and SHAP interpretation study.

November 7, 2025pubmed logopapers

Authors

Wang Y,Su Y,Li J,Xie D,Liu Z,Cai Y,Sun C,Zhang J,Jeong J,Yi H,Yuan Y

Affiliations (9)

  • Department of Nuclear Medicine, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China.
  • Postgraduate Training Base Alliance of Wenzhou Medical University, ZheJiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China.
  • Department of Nuclear Medicine, Aksu Prefecture First People's Hospital, Aksu, Xinjiang, 843000, China.
  • Department of Mathematics and Statistics, Chonnam National University, Gwangju, 61186, Republic of Korea.
  • Department of Mathematics and Statistics, Chonnam National University, Gwangju, 61186, Republic of Korea. [email protected].
  • Department of Nuclear Medicine, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China. [email protected].
  • Key Laboratory of Head and Neck Cancer Translational Research of Zhejiang Province, Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China. [email protected].
  • School of Mental Health, Wenzhou Medical University, Wenzhou, 325000, China. [email protected].
  • Department of Mathematics and Statistics, Chonnam National University, Gwangju, 61186, Republic of Korea. [email protected].

Abstract

Accurately distinguishing benign from malignant adrenal lesions remains a clinical challenge, especially in oncology patients with indeterminate imaging findings. This study aimed to develop and interpret machine learning (ML) models for classifying adrenal lesions based on 18 F-FDG PET/CT imaging and clinical parameters. A retrospective cohort of 255 patients undergoing 18 F-FDG PET/CT was analyzed. Imaging features-including adrenal SUVmax, SUVpeak, tumor diameter, CT attenuation, and tumor-to-liver SUVmax ratio (T/L SUVmax)-along with clinical variables were extracted. Two classification tasks were constructed: (1) differentiation of benign and malignant adrenal lesions; and (2) subtyping of malignant lesions into lung cancer metastases or lymphoma. Seven ML models were trained and evaluated using 10-fold cross-validation. SHAP (SHapley Additive exPlanations) analysis was applied to elucidate feature contributions. For the benign/malignant classification, ensemble models (Random Forest, Bagging, XGBoost) achieved outstanding performance (AUC > 0.99), with Bagging yielding 100% recall. T/L SUVmax, adrenal SUVmax, and CT attenuation emerged as top predictors. In malignancy subtyping, the artificial neural network (ANN) attained the highest AUC (0.887) and F1-score (0.851). SHAP analysis highlighted distinct metabolic patterns, with lymphoma showing higher SUVmax and T/L ratios, and lung metastases associated with higher CT values. Machine learning models based on PET/CT-derived features enable highly accurate and interpretable classification of adrenal lesions. Integrating metabolic and anatomical parameters improves diagnostic precision, while SHAP analysis offers clinical transparency, supporting personalized decision-making in adrenal lesion management.

Topics

Machine LearningPositron Emission Tomography Computed TomographyFluorodeoxyglucose F18Adrenal Gland NeoplasmsJournal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.