近日，复旦大学徐鹏举团队研究出肝癌联合靶向治疗和免疫治疗治疗反应的自动分类。该项研究成果发表在2025年9月17日出版的《分子细胞生物学报》上。

考虑到绝大多数晚期HCC患者失去了肝脏切除术的机会，无法提供肿瘤组织样本，课题组利用临床和图像数据构建了多模态卷积神经网络(CNN) -Transformer模型，用于预测和分析肿瘤对tki免疫治疗的反应。一种基于两阶段三维U-Net框架的肝脏肿瘤自动分割系统，首先对肝脏实质进行分割，然后精确定位肿瘤。这种方法有效地解决了临床数据的可变性，并显著减少了人工干预带来的偏倚。

在此基础上，该课题组建立了一个仅以预处理临床信息为主题的临床模型，一个仅以预处理磁共振成像数据为主题的CNN模型，以及一个先进的多模态CNN - transformer模型，该模型以成像和临床参数为主题，以训练队列为主题（n = 181），然后以独立队列为主题（n = 30）。在验证队列中，曲线下面积（95%置信区间）值分别为0.720（0.710-0.731）、0.695（0.683-0.707）和0.785(0.760-0.810)，表明多模态模型在验证过程中显著优于单模态基线模型。最后，手术肿瘤标本的单细胞测序揭示了与治疗反应相关的肿瘤生态系统多样性，为预测模型提供了初步的生物学验证。

综上所述，该多模式模型有效地整合了HCC患者的影像学和临床特征，在预测肿瘤对tki免疫治疗的反应方面具有优越的性能，为优化个性化治疗策略提供了可靠的工具。

据介绍，酪氨酸激酶抑制剂（TKIs）联合免疫治疗方案目前被广泛用于治疗晚期肝细胞癌（HCC），但其临床疗效仅限于一小部分患者。

附：英文原文

Title: Automating classification of treatment responses to combined targeted therapy and immunotherapy in HCC

Author: Quan, Bing, Dai, Mingrong, Zhang, Peiling, Chen, Shiping, Cai, Jialiang, Shao, Yujie, Xu, Pengju, Li, Peizhao, Yu, Lei

Issue&Volume: 2025-09-17

Abstract: Tyrosine kinase inhibitors (TKIs) combined with immunotherapy regimens are now widely used for treating advanced hepatocellular carcinoma (HCC), but their clinical efficacy is limited to a subset of patients. Considering that the vast majority of advanced HCC patients lose the opportunity for liver resection and thus cannot provide tumor tissue samples, we leveraged the clinical and image data to construct a multimodal convolutional neural network (CNN)–Transformer model for predicting and analyzing tumor response to TKI–immunotherapy. An automatic liver tumor segmentation system, based on a two-stage 3D U-Net framework, delineates lesions by first segmenting the liver parenchyma and then precisely localizing the tumor. This approach effectively addresses the variability in clinical data and significantly reduces bias introduced by manual intervention. Thus, we developed a clinical model using only pre-treatment clinical information, a CNN model using only pre-treatment magnetic resonance imaging data, and an advanced multimodal CNN–Transformer model that fused imaging and clinical parameters using a training cohort (n = 181) and then validated them using an independent cohort (n = 30). In the validation cohort, the area under the curve (95% confidence interval) values were 0.720 (0.710–0.731), 0.695 (0.683–0.707), and 0.785 (0.760–0.810), respectively, indicating that the multimodal model significantly outperformed the single-modality baseline models across validations. Finally, single-cell sequencing with the surgical tumor specimens reveals tumor ecosystem diversity associated with treatment response, providing a preliminary biological validation for the prediction model. In summary, this multimodal model effectively integrates imaging and clinical features of HCC patients, has a superior performance in predicting tumor response to TKI–immunotherapy, and provides a reliable tool for optimizing personalized treatment strategies.

DOI: 10.1093/jmcb/mjaf031

Source: https://academic.oup.com/jmcb/advance-article/doi/10.1093/jmcb/mjaf031/8256843searchresult=1