Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China (X.C., Q.Y., J.P., Z.H., Q.L., Y.N., F.L., H.J., K.X.).
Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China (X.C., Q.Y., J.P., Z.H., Q.L., Y.N., F.L., H.J., K.X.).
Acad Radiol. 2023 Dec;30(12):3022-3031. doi: 10.1016/j.acra.2023.06.029. Epub 2023 Sep 28.
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.
准确的喉癌分期可以为制定适当的治疗决策提供信息。我们基于静脉期 CT 图像开发了一个放射组学模型、一个深度学习（DL）模型和一个联合模型（结合放射组学特征和 DL 特征），并探讨了这些模型在将喉癌患者分为Ⅰ-Ⅱ期和Ⅲ-Ⅳ期的分层能力，同时将这些模型与放射科医生进行了比较。
319 例经病理证实的喉癌患者被随机分为训练集（n=223）和测试集（n=96）。在训练集中，通过 Spearman 相关分析和递归特征消除（RFE）筛选出组内和组间相关系数（ICC）>0.75 的放射组学特征；然后应用支持向量机（SVM）分类器开发放射组学模型。使用 ResNet 18 构建 DL 模型，通过裁剪最大肿瘤 ROI 切片中的 2D 感兴趣区（ROI），并将该网络的最后一个全连接层作为 DL 特征提取器。最后，通过合并放射组学特征和提取的 DL 特征来开发联合模型以预测分期。
在测试集中，放射组学模型、DL 模型和联合模型的曲线下面积（AUC）分别为 0.704（95%置信区间[CI]：0.588-0.820）、0.724（95%CI：0.613-0.835）和 0.849（95%CI：0.755-0.943）。联合模型在区分Ⅰ-Ⅱ期和Ⅲ-Ⅳ期方面优于放射组学模型和 DL 模型（p=0.031 和 p=0.020）。只有联合模型的表现显著优于放射科医生（p<0.050）。
联合模型可以通过更准确的术前分期来帮助制定喉癌患者的治疗策略。
