A transformer-based deep learning model for preoperative prediction of lympho-vascular invasion in laryngeal squamous cell carcinoma: a multicenter study

Background: To explore and compare the potential value of radiomics models based on contrast-enhanced computed tomography (CT) for noninvasive preoperative prediction of lymphovascular invasion (LVI) in laryngeal squamous cell carcinoma (LSCC). Materials and Methods: This multicenter diagnostic study retrospectively enrolled LSCC patients from three tertiary hospitals who underwent surgical treatment. Standardized preprocessing was performed on the CT images, followed by region-of-interest (ROI) segmentation and extraction of traditional radiomics features and deep learning features. Features were selected using least absolute shrinkage and selection operator (LASSO) regression. Traditional radiomics models and deep learning radiomics models (DLR) were established using logistic regression, random forest, and multilayer perceptron algorithms, respectively. A transformer-based hybrid model was developed by integrating radiomics and deep learning features. The predictive performance of the three types of models was evaluated and compared using the area under the curve (AUC), decision curve analysis (DCA), sample probability distribution histograms, confusion matrices, calibration curves, net reclassification index (NRI), and integrated discrimination improvement (IDI). Results: A total of 1,024 patients were allocated to the training set (center1, n = 291), internal validation set (n = 126), and external test sets (center 2, n = 437; center 3, n = 170). Three radiomics models and three DLR models were constructed, and the optimal performance was observed in the DLR_ Random Forest model (AUC: 0.812-0.867). The transformer hybrid model demonstrated superior predictive performance, with AUC values of 0.881, 0.843, 0.833, and 0.836 in the training, internal validation, and external test sets, respectively. Decision curve analysis indicated a higher net benefit for the transformer model, along with an improved NRI and IDI. Conclusion: Radiomics models based on CT images exhibit potential for noninvasive prediction of LVI in LSCC, with the transformer hybrid model achieving the highest diagnostic performance. This approach may provide clinicians with a preoperative decision support tool to optimize treatment strategies for patients with LSCC.