Deep transfer learning radiomics combined with explainable machine learning for preoperative thymoma risk prediction based on CT.

Authors

Wu S,Fan L,Wu Y,Xu J,Guo Y,Zhang H,Xu Z

Affiliations (6)

  • Department of Radiology, The First Affiliated Hospital of Wannan Medical College, Wuhu, Anhui 241001, China.
  • School of Medical Imageology, Wannan Medical College, Wuhu, Anhui 241002, China.
  • Department of Ultrasound, WuHu Hospital, East China Normal University (The Second People's Hospital, WuHu), Wuhu, Anhui 241001, China.
  • Department of Radiology, WuHu Hospital, East China Normal University (The Second People's Hospital, WuHu), Wuhu, Anhui 241001, China.
  • Department of Radiology, WuHu Hospital, East China Normal University (The Second People's Hospital, WuHu), Wuhu, Anhui 241001, China. Electronic address: [email protected].
  • School of Medical Imageology, Wannan Medical College, Wuhu, Anhui 241002, China. Electronic address: [email protected].

Abstract

To develop and validate a computerized tomography (CT)‑based deep transfer learning radiomics model combined with explainable machine learning for preoperative risk prediction of thymoma. This retrospective study included 173 pathologically confirmed thymoma patients from our institution in the training group and 93 patients from two external centers in the external validation group. Tumors were classified according to the World Health Organization simplified criteria as low‑risk types (A, AB, and B1) or high‑risk types (B2 and B3). Radiomics features and deep transfer learning features were extracted from venous‑phase contrast‑enhanced CT images by using a modified Inception V3 network. Principal component analysis and least absolute shrinkage and selection operator regression identified 20 key predictors. Six classifiers-decision tree, gradient boosting machine, k‑nearest neighbors, naïve Bayes, random forest (RF), and support vector machine-were trained on five feature sets: CT imaging model, radiomics feature model, deep transfer learning feature model, combined feature model, and combined model. Interpretability was assessed with SHapley Additive exPlanations (SHAP), and an interactive web application was developed for real‑time individualized risk prediction and visualization. In the external validation group, the RF classifier achieved the highest area under the receiver operating characteristic curve (AUC) value of 0.956. In the training group, the AUC values for the CT imaging model, radiomics feature model, deep transfer learning feature model, combined feature model, and combined model were 0.684, 0.831, 0.815, 0.893, and 0.910, respectively. The corresponding AUC values in the external validation group were 0.604, 0.865, 0.880, 0.934, and 0.956, respectively. SHAP visualizations revealed the relative contribution of each feature, while the web application provided real‑time individual prediction probabilities with interpretative outputs. We developed a CT‑based deep transfer learning radiomics model combined with explainable machine learning and an interactive web application; this model achieved high accuracy and transparency for preoperative thymoma risk stratification, facilitating personalized clinical decision‑making.

Topics

Journal 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.