Fan Shuxuan, Xie Jiping, Zheng Sunyi, Wang Jing, Zhang Bin, Zhang Zhanshuo, Wang Shuo, Cui Yuechen, Liu Jiaxin, Zheng Xinru, Ye Zhaoxiang, Cui Xiaonan, Yue Dongsheng
Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin's Clinical Research Center for Cancer, State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine, Tianjin Key Laboratory of Digestive Cancer, Key Laboratory of Cancer Prevention and Therapy, Department of Radiology, Tianjin, China.
Tianjin Medical University Cancer Institute and Hospital, Key Laboratory of Cancer Prevention and Therapy, National Clinical Research Center of Cancer, Department of Lung Cancer, Lung Cancer Center, Tianjin, China.
Eur J Radiol. 2025 Aug;189:112171. doi: 10.1016/j.ejrad.2025.112171. Epub 2025 May 19.
This study aims to develop and validate a multiregional radiomics model to predict pathological complete response (pCR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC), and further evaluate the performance of the model in different specific subgroups (N2 stage and anti-PD-1/PD-L1).
216 patients with NSCLC who underwent neoadjuvant chemoimmunotherapy followed by surgical intervention were included and assigned to training and validation sets randomly. From pre-treatment baseline CT, one intratumoral (T) and two peritumoral regions (P: 0-3 mm; P: 0-6 mm) were extracted. Five radiomics models were developed using machine learning algorithms to predict pCR, utilizing selected features from intratumoral (T), peritumoral (P, P), and combined intra- and peritumoral regions (T + P, T + P). Additionally, the predictive efficacy of the optimal model was specifically assessed for patients in the N2 stage and anti-PD-1/PD-L1 subgroups.
A total of 51.4 % (111/216) of patients exhibited pCR following neoadjuvant chemoimmunotherapy. Multivariable analysis identified that only the T + P radiomics signature served as independent predictor of pCR (P < 0.001). The multiregional radiomics model (T + P) exhibited superior predictive performance for pCR, achieving an area under the curve (AUC) of 0.75 in the validation cohort. Furthermore, this multiregional model maintained robust predictive accuracy in both N2 stage and anti-PD-1/PD-L1 subgroups, with an AUC of 0.829 and 0.833, respectively.
The proposed multiregional radiomics model showed potential in predicting pCR in NSCLC after neoadjuvant chemoimmunotherapy, and demonstrated good predictive performance in different specific subgroups. This capability may assist clinicians in identifying suitable candidates for neoadjuvant chemoimmunotherapy and promote the advancement in precision therapy.
本研究旨在开发并验证一种多区域放射组学模型，以预测非小细胞肺癌（NSCLC）新辅助化疗免疫治疗后的病理完全缓解（pCR），并进一步评估该模型在不同特定亚组（N2期和抗PD-1/PD-L1）中的性能。
纳入216例接受新辅助化疗免疫治疗后接受手术干预的NSCLC患者，并随机分配至训练集和验证集。从治疗前基线CT中，提取一个瘤内（T）区域和两个瘤周区域（P：0-3mm；P：0-6mm）。使用机器学习算法开发了五个放射组学模型来预测pCR，利用瘤内（T）、瘤周（P、P）以及瘤内和瘤周联合区域（T+P、T+P）中选择的特征。此外，还专门评估了最佳模型对N2期和抗PD-1/PD-L1亚组患者的预测疗效。
共有51.4%（111/216）的患者在新辅助化疗免疫治疗后出现pCR。多变量分析确定，只有T+P放射组学特征是pCR的独立预测因子（P<0.001）。多区域放射组学模型（T+P）对pCR表现出卓越的预测性能，在验证队列中的曲线下面积（AUC）达到0.75。此外，该多区域模型在N2期和抗PD-1/PD-L1亚组中均保持了稳健的预测准确性，AUC分别为0.829和0.833。
所提出的多区域放射组学模型在预测NSCLC新辅助化疗免疫治疗后的pCR方面显示出潜力，并在不同特定亚组中表现出良好的预测性能。这种能力可能有助于临床医生识别适合新辅助化疗免疫治疗的候选者，并推动精准治疗的进展。
