Hong Yuan, Wang Hanlin, Zhang Qi, Zhang Peng, Cheng Kang, Cao Guodong, Zhang Renquan, Chen Bo
Department of General Surgery, The First Affiliated Hospital of Anhui Medical University, Hefei 230022, China.
Department of Thoracic Surgery, The First Affiliated Hospital of Anhui Medical University, Hefei 230022, China.
Diagnostics (Basel). 2025 Jul 8;15(14):1730. doi: 10.3390/diagnostics15141730.
: The rapid advancement of radiomics and artificial intelligence (AI) technology has provided novel tools for the diagnosis of esophageal cancer. This study innovatively combines muscle imaging features with conventional esophageal imaging features to construct deep learning diagnostic models. : This retrospective study included 1066 patients undergoing radical esophagectomy. Preoperative computed tomography (CT) images covering esophageal, stomach, and muscle (bilateral iliopsoas and erector spinae) regions were segmented automatically with manual adjustments. Diagnostic models were developed using deep learning (2D and 3D neural networks) and traditional machine learning (11 algorithms with PyRadiomics-derived features). Multimodal features underwent Principal Component Analysis (PCA) for dimension reduction and were fused for final analysis. : Comparative analysis of 1066 patients' CT imaging revealed the muscle-based model outperformed the esophageal plus stomach model in predicting N2 staging (0.63 ± 0.11 vs. 0.52 ± 0.11, = 0.03). Subsequently, multimodal fusion models were established for predicting pathological subtypes, T staging, and N staging. The logistic regression (LR) fusion model showed optimal performance in predicting pathological subtypes, achieving accuracy (ACC) of 0.919 in the training set and 0.884 in the validation set. For predicting T staging, the support vector machine (SVM) model demonstrated the highest accuracy, with training and validation accuracies of 0.909 and 0.907, respectively. The multilayer perceptron (MLP) fusion model achieved the best performance among all models tested for N staging prediction, although the accuracy remained moderate (ACC = 0.704 in the training set and 0.685 in the validation set), indicating potential for further optimization. Fusion models significantly outperformed single-modality models. : Based on CT imaging data from 1066 patients, this study systematically constructed predictive models for pathological subtypes, T staging, and N staging of esophageal cancer. Comparative analysis of models using esophageal, esophageal plus stomach, and muscle modalities demonstrated that muscle imaging features contribute to diagnostic accuracy. Multimodal fusion models consistently showed superior performance.
放射组学和人工智能（AI）技术的快速发展为食管癌的诊断提供了新工具。本研究创新性地将肌肉成像特征与传统食管成像特征相结合，构建深度学习诊断模型。：这项回顾性研究纳入了1066例行根治性食管切除术的患者。术前覆盖食管、胃和肌肉（双侧髂腰肌和竖脊肌）区域的计算机断层扫描（CT）图像通过手动调整进行自动分割。使用深度学习（2D和3D神经网络）和传统机器学习（11种基于PyRadiomics衍生特征的算法）开发诊断模型。对多模态特征进行主成分分析（PCA）以降维，并融合进行最终分析。：对1066例患者的CT成像进行比较分析发现，基于肌肉的模型在预测N2分期方面优于食管加胃模型（0.63±0.11对0.52±0.11，P = 0.03）。随后，建立了用于预测病理亚型、T分期和N分期的多模态融合模型。逻辑回归（LR）融合模型在预测病理亚型方面表现最佳，在训练集中的准确率（ACC）为0.919，在验证集中为0.884。对于预测T分期，支持向量机（SVM）模型显示出最高准确率，训练和验证准确率分别为0.909和0.907。在所有测试的N分期预测模型中，多层感知器（MLP）融合模型表现最佳，尽管准确率仍处于中等水平（训练集中ACC = 0.704，验证集中ACC = 0.685），表明有进一步优化的潜力。融合模型明显优于单模态模型。：基于1066例患者的CT成像数据进行系统构建食管癌病理亚型、T分期和N分期的预测模型。对使用食管、食管加胃和肌肉模态的模型进行比较分析表明，肌肉成像特征有助于提高诊断准确性。多模态融合模型始终表现出卓越的性能。
