Ji Juan, Duan Fanglei, Liao Qiong, Wang Hao, Liu Shiwei, Liu Yang, Huang Zongyao
Department of Pathology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, Affiliated Cancer Hospital of University of Electronic Science and Technology of China, Chengdu, China.
Department of Breast, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China.
Cancer Med. 2025 Aug;14(15):e71132. doi: 10.1002/cam4.71132.
Neoadjuvant therapy (NAT) is a standard breast cancer treatment, but patient response varies significantly. Predictive markers can guide treatment decisions, yet their interpretation suffers from inter-pathologist variability due to breast cancer's complex histology and heterogeneity. Artificial intelligence (AI) applied to image-based omics offers potential to enhance pathological interpretation precision and consistency.
This review synthesizes existing literature on the application of AI in breast cancer pathology. We specifically focused on identifying and summarizing research that utilizes diverse histopathological features-including morphological characteristics, molecular markers, gene expression profiles, and multidimensional omics data-to predict NAT response in breast cancer patients.
AI demonstrates significant capabilities in automatically recognizing histopathological patterns and predicting NAT efficacy. It shows promise as a tool for patient stratification in precision oncology. Research utilizing various pathological feature types (morphological, molecular, genomic, multi-omics) for NAT response prediction is actively evolving. While AI models integrating multi-omics features show potential, challenges remain in robustly predicting NAT outcomes.
AI-based pathology represents a prospective and powerful decision-support tool for predicting breast cancer NAT response. Despite existing challenges, particularly with complex multi-omics models, AI holds great potential to assist clinical oncologists in optimizing future cancer treatment management.
新辅助治疗（NAT）是乳腺癌的标准治疗方法，但患者反应差异很大。预测标志物可指导治疗决策，然而由于乳腺癌复杂的组织学特征和异质性，不同病理学家对其解读存在差异。应用于基于图像的组学的人工智能（AI）有潜力提高病理解读的准确性和一致性。
本综述综合了关于AI在乳腺癌病理学中应用的现有文献。我们特别关注识别和总结利用多种组织病理学特征（包括形态学特征、分子标志物、基因表达谱和多维组学数据）来预测乳腺癌患者NAT反应的研究。
AI在自动识别组织病理学模式和预测NAT疗效方面具有显著能力。它有望成为精准肿瘤学中患者分层的工具。利用各种病理特征类型（形态学、分子、基因组、多组学）预测NAT反应的研究正在积极发展。虽然整合多组学特征的AI模型显示出潜力，但在可靠预测NAT结果方面仍存在挑战。
基于AI的病理学是预测乳腺癌NAT反应的一种前瞻性且强大的决策支持工具。尽管存在现有挑战，特别是对于复杂的多组学模型，AI在协助临床肿瘤学家优化未来癌症治疗管理方面具有巨大潜力。
