Xie Shu-Han, Xu Hui, Zhang Hai, Xu Jin-Xin, Huang Shi-Jie, Liu Wen-Yi, Tang Zi-Lu, Xu Rong-Yu, Ke Sun-Kui, Xie Jin-Biao, Feng Qing-Yi, Kang Ming-Qiang
Department of Thoracic Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian, China.
The Graduate School of Fujian Medical University, Fuzhou, Fujian, China.
Front Immunol. 2025 Aug 6;16:1603249. doi: 10.3389/fimmu.2025.1603249. eCollection 2025.
Current medical examinations and biomarkers struggle to assess the efficacy of chemoimmunotherapy (nICT) for locally advanced esophageal squamous cell carcinoma (ESCC). This study aimed to develop a machine learning model integrating habitat imaging and deep learning (DL) to predict the treatment response of ESCC patients to nICT.
The study retrospectively collected 309 ESCC patients from 6 medical centers, divided into training and external validation cohorts. For habitat imaging analysis, intratumoral subregions were clustered using the K-means clustering method. DL features from intratumoral and peritumoral subregions were extracted by Vision Transformer (ViT) respectively and then subjected to feature selection. Subsequently, 11 machine learning models were constructed for predictive model. The model's performance was evaluated using the area under the curve (AUC), decision curve analysis (DCA), calibration curve, and accuracy.
A total of 18 DL features were selected. The model of ExtraTrees, which was optimal, demonstrated superior performance with AUCs of 0.917 in training cohort and 0.831 in external validation cohort. Similarly, ExtraTrees showed good predictive capabilities in patients undergoing 2 cycles of nICT with AUC of 0.862 in validation cohort. This model also showed good calibration for prediction probability and satisfied clinical value on DCAs. Finally, the SHapley Additive exPlanations method elucidated the model's precise predictions.
The ExtraTrees model leveraging habitat imaging and ViT offered a non-invasive and accurate method to predict pathological response to nICT, guiding personalized treatment strategies, and decreasing the risk of immune-related adverse effects.
目前的医学检查和生物标志物难以评估化疗免疫疗法（新辅助化疗，nICT）对局部晚期食管鳞状细胞癌（ESCC）的疗效。本研究旨在开发一种整合瘤内成像和深度学习（DL）的机器学习模型，以预测ESCC患者对nICT的治疗反应。
本研究回顾性收集了来自6个医学中心的309例ESCC患者，分为训练队列和外部验证队列。对于瘤内成像分析，使用K均值聚类方法对瘤内亚区域进行聚类。分别通过视觉Transformer（ViT）从瘤内和瘤周亚区域提取DL特征，然后进行特征选择。随后，构建了11个机器学习模型用于预测模型。使用曲线下面积（AUC）、决策曲线分析（DCA）、校准曲线和准确性来评估模型的性能。
共选择了18个DL特征。最优的ExtraTrees模型表现出卓越的性能，训练队列中的AUC为0.917，外部验证队列中的AUC为0.831。同样，ExtraTrees在接受2个周期nICT的患者中显示出良好的预测能力，验证队列中的AUC为0.862。该模型在预测概率方面也显示出良好的校准，并且在DCA上具有满意的临床价值。最后，SHapley加法解释方法阐明了模型的精确预测。
利用瘤内成像和ViT的ExtraTrees模型提供了一种非侵入性且准确的方法来预测对nICT的病理反应，指导个性化治疗策略，并降低免疫相关不良反应的风险。
