Prediction of pathological risk subtypes of thymic anterior mediastinal cysts and thymic epithelial tumors based on CT radiomics and deep learning methods: a retrospective study.
Authors
Affiliations (7)
Affiliations (7)
- Department of Thoracic Surgery, Tianjin Chest Hospital, No. 261, Taierzhuang South Road, Jinnan District, Tianjin, 300222, China.
- Chest Hospital, Tianjin University, Tianjin, China.
- Clinical School of Thoracic, Tianjin Medical University, Tianjin, China.
- School of Basic Medical Sciences, Tianjin Medical University, Tianjin, China.
- Department of Thoracic Surgery, Tianjin Chest Hospital, No. 261, Taierzhuang South Road, Jinnan District, Tianjin, 300222, China. [email protected].
- Chest Hospital, Tianjin University, Tianjin, China. [email protected].
- Clinical School of Thoracic, Tianjin Medical University, Tianjin, China. [email protected].
Abstract
This study aims to develop a non-invasive model for preoperatively predicting the pathological risk classification of thymic anterior mediastinal cysts and thymic epithelial tumors using CT-based radiomics and deep learning. Accurate risk stratification before surgery can support personalized treatment planning and improve clinical outcomes. A retrospective analysis was conducted on 144 patients with pathologically confirmed thymic anterior mediastinal cysts or thymic epithelial tumors who underwent preoperative thin-slice chest CT between January 2014 and December 2023. Regions of interest were manually segmented, and 1834 handcrafted radiomics features-including geometric, intensity, and texture features-were extracted using Pyradiomics. Deep learning features were derived from a ResNet50 network with transfer learning and cosine annealing learning rate adjustment. Radiomics and deep features were fused into a deep learning radiomics (DLR) feature set. Feature selection was performed before model training. The models were evaluated in training (n = 101) and test (n = 43) cohorts. The radiomics model achieved an AUC of 0.876 in the training cohort and 0.800 in the test cohort. The deep learning model yielded AUCs of 0.838 and 0.831, respectively. The combined DLR model showed superior performance, with an AUC of 0.964 in the training cohort and 0.820 in the test cohort, outperforming unimodal models in classification accuracy and robustness. In this study, a model for predicting pathological risk classification of thymic anterior mediastinal cysts and thymic epithelial tumors was developed by combining radiomics and deep learning, and its superior prediction was confirmed in verification. The results show that the model is capable of preoperatively assessing the pathological risk classification of patients, which provides strong support for the need of individual treatment strategies.