A Combined Model Integrating Radiomics and Deep Learning Based on Contrast-Enhanced CT for Preoperative Staging of Laryngeal Carcinoma

Rationale and Objectives Accurate staging of laryngeal carcinoma can inform appropriate treatment decision-making. We developed a radiomics model, a deep learning (DL) model, and a combined model (incorporating radiomics features and DL features) based on the venous-phase CT images and explored the performance of these models in stratifying patients with laryngeal carcinoma into stage I–II and stage III–IV, and also compared these models with radiologists. Materials and Methods Three hundreds and nineteen patients with pathologically confirmed laryngeal carcinoma were randomly divided into a training set (n = 223) and a test set (n = 96). In the training set, the radiomics features with inter- and intraclass correlation coefficients (ICCs) > 0.75 were screened by Spearman correlation analysis and recursive feature elimination (RFE); then support vector machine (SVM) classifier was applied to develop the radiomics model. The DL model was built using ResNet 18 by the cropped 2D regions of interest (ROIs) in the maximum tumor ROI slices and the last fully connected layer of this network served as the DL feature extractor. Finally, a combined model was developed by pooling the radiomics features and extracted DL features to predict the staging. Results The area under the curves (AUCs) for radiomics model, DL model, and combined model in the test set were 0.704 (95% confidence interval [CI]: 0.588–0.820), 0.724 (95% CI: 0.613–0.835), and 0.849 (95% CI: 0.755–0.943), respectively. The combined model outperformed the radiomics model and the DL model in discriminating stage I–II from stage III–IV (p = 0.031 and p = 0.020, respectively). Only the combined model performed significantly better than radiologists (p < 0.050 for both). Conclusion The combined model can help tailor the therapeutic strategy for laryngeal carcinoma patients by enabling more accurate preoperative staging. Accurate staging of laryngeal carcinoma can inform appropriate treatment decision-making. We developed a radiomics model, a deep learning (DL) model, and a combined model (incorporating radiomics features and DL features) based on the venous-phase CT images and explored the performance of these models in stratifying patients with laryngeal carcinoma into stage I–II and stage III–IV, and also compared these models with radiologists. Three hundreds and nineteen patients with pathologically confirmed laryngeal carcinoma were randomly divided into a training set (n = 223) and a test set (n = 96). In the training set, the radiomics features with inter- and intraclass correlation coefficients (ICCs) > 0.75 were screened by Spearman correlation analysis and recursive feature elimination (RFE); then support vector machine (SVM) classifier was applied to develop the radiomics model. The DL model was built using ResNet 18 by the cropped 2D regions of interest (ROIs) in the maximum tumor ROI slices and the last fully connected layer of this network served as the DL feature extractor. Finally, a combined model was developed by pooling the radiomics features and extracted DL features to predict the staging. The area under the curves (AUCs) for radiomics model, DL model, and combined model in the test set were 0.704 (95% confidence interval [CI]: 0.588–0.820), 0.724 (95% CI: 0.613–0.835), and 0.849 (95% CI: 0.755–0.943), respectively. The combined model outperformed the radiomics model and the DL model in discriminating stage I–II from stage III–IV (p = 0.031 and p = 0.020, respectively). Only the combined model performed significantly better than radiologists (p < 0.050 for both). The combined model can help tailor the therapeutic strategy for laryngeal carcinoma patients by enabling more accurate preoperative staging.