Multichannel deep learning prediction of major pathological response after neoadjuvant immunochemotherapy in lung cancer: a multicenter diagnostic study

作者：Zuhan Geng, Kuo Li, Peiyuan Mei, Zhenyu Gong, Ruiyang Yan, Yu Huang, Chi Zhang, Bowen Zhao, Mingqian Lu, Ran Yang, Guangyao Wu, Guanchao Ye, Yongde Liao · 发表于：International Journal of Surgery · 年份：2025 · DOI：10.1097/js9.0000000000002821 · 被引用次数：12 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment、Cancer Immunotherapy and Biomarkers

OBJECTIVES: This study aimed to develop a pretreatment CT-based multichannel predictor integrating deep learning features encoded by Transformer models for preoperative diagnosis of major pathological response (MPR) in non-small cell lung cancer (NSCLC) patients receiving neoadjuvant immunochemotherapy. MATERIAL AND METHODS: This multicenter diagnostic study retrospectively included 332 NSCLC patients from four centers. Pretreatment computed tomography images were preprocessed and segmented into region of interest cubes for radiomics modeling. These cubes were cropped into four groups of two-dimensional image modules. GoogLeNet architecture was trained independently on each group within a multichannel framework, with gradient-weighted class activation mapping and SHapley Additive exPlanations value for visualization. Deep learning features were carefully extracted and fused across the four image groups using the Transformer fusion model. After models training, model performance was evaluated via the area under the curve (AUC), sensitivity, specificity, F1 score, confusion matrices, calibration curves, decision curve analysis, integrated discrimination improvement, net reclassification improvement, and DeLong test. RESULTS: The dataset was allocated into training (n = 172, Center 1), internal validation (n = 44, Center 1), and external test (n = 116, Centers 2-4) cohorts. Four optimal deep learning models and the best Transformer fusion model were developed. In the external te...