Garberis I, Gaury V, Saillard C, Drubay D, Elgui K, Schmauch B, Jaeger A, Herpin L, Linhart J, Sapateiro M, Bernigole F, Kamoun A, Filiot A, Tchita O, Dubois R, Auffret M, Guillou L, Bousaid I, Azoulay M, Lemonnier J, Sefta M, Everhard S, Sarrazin A, Reboud J-F, Brulport F, Dachary J, Pistilli B, Delaloge S, Courtiol P, André F, Aubert V, Lacroix-Triki M
INSERM U981, Gustave Roussy, Paris-Saclay University, Villejuif, France.
Owkin, Paris, France.
Nat Commun. 2025 Jul 1;16(1):5876. doi: 10.1038/s41467-025-60824-z.
Accurate risk stratification is critical for guiding treatment decisions in early breast cancer. We present an artificial intelligence (AI)-based tool that analyzes digitized tumor slides to predict 5-year metastasis-free survival (MFS) in patients with estrogen receptor-positive, HER2-negative (ER + /HER2 - ) early breast cancer (EBC). Our deep learning model, RlapsRisk BC, independently predicts MFS and provides significant prognostic value beyond traditional clinico-pathological variables (C-index 0.81 vs 0.76, p < 0.05). Applying a 5% MFS event probability threshold stratifies patients into low- and high-risk groups. After dichotomization, combining RlapsRisk BC with clinico-pathological factors increases cumulative sensitivity (0.69 vs 0.63) and dynamic specificity (0.80 vs 0.76) compared to clinical factors alone. Expert analysis of high-impact regions identified by the model highlights well-established morphological features, supporting its interpretability and biological relevance.
准确的风险分层对于指导早期乳腺癌的治疗决策至关重要。我们提出了一种基于人工智能（AI）的工具，该工具通过分析数字化肿瘤切片来预测雌激素受体阳性、人表皮生长因子受体2阴性（ER + /HER2 - ）早期乳腺癌（EBC）患者的5年无转移生存率（MFS）。我们的深度学习模型RlapsRisk BC能够独立预测MFS，并提供超越传统临床病理变量的显著预后价值（C指数为0.81对0.76，p < 0.05）。应用5%的MFS事件概率阈值可将患者分为低风险和高风险组。二分法后，将RlapsRisk BC与临床病理因素相结合，与单独的临床因素相比，可提高累积敏感性（0.69对0.63）和动态特异性（0.80对0.76）。对模型识别出的高影响区域进行专家分析，突出了已确立的形态学特征，支持了其可解释性和生物学相关性。
