• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

多模态组织病理学模型对激素受体阳性早期乳腺癌进行分层。

Multimodal histopathologic models stratify hormone receptor-positive early breast cancer.

作者信息

Boehm Kevin M, El Nahhas Omar S M, Marra Antonio, Waters Michele, Jee Justin, Braunstein Lior, Schultz Nikolaus, Selenica Pier, Wen Hannah Y, Weigelt Britta, Paul Evan D, Cekan Pavol, Erber Ramona, Loeffler Chiara M L, Guerini-Rocco Elena, Fusco Nicola, Frascarelli Chiara, Mane Eltjona, Munzone Elisabetta, Dellapasqua Silvia, Zagami Paola, Curigliano Giuseppe, Razavi Pedram, Reis-Filho Jorge S, Pareja Fresia, Chandarlapaty Sarat, Shah Sohrab P, Kather Jakob Nikolas

机构信息

Computational Oncology Service, Memorial Sloan Kettering Cancer Center, 323 E 61 St, New York, NY, USA.

Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY, USA.

出版信息

Nat Commun. 2025 Mar 2;16(1):2106. doi: 10.1038/s41467-025-57283-x.

DOI:10.1038/s41467-025-57283-x
PMID:40025017
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11873197/
Abstract

The Oncotype DX® Recurrence Score (RS) is an assay for hormone receptor-positive early breast cancer with extensively validated predictive and prognostic value. However, its cost and lag time have limited global adoption, and previous attempts to estimate it using clinicopathologic variables have had limited success. To address this, we assembled 6172 cases across three institutions and developed Orpheus, a multimodal deep learning tool to infer the RS from H&E whole-slide images. Our model identifies TAILORx high-risk cases (RS > 25) with an area under the curve (AUC) of 0.89, compared to a leading clinicopathologic nomogram with 0.73. Furthermore, in patients with RS ≤ 25, Orpheus ascertains risk of metastatic recurrence more accurately than the RS itself (0.75 vs 0.49 mean time-dependent AUC). These findings have the potential to guide adjuvant therapy for high-risk cases and tailor surveillance for patients at elevated metastatic recurrence risk.

摘要

Oncotype DX®复发评分(RS)是一种针对激素受体阳性早期乳腺癌的检测方法,具有广泛验证的预测和预后价值。然而,其成本和滞后时间限制了全球范围内的采用,并且以往使用临床病理变量来估计它的尝试取得的成功有限。为了解决这一问题,我们收集了三个机构的6172例病例,并开发了Orpheus,这是一种多模态深度学习工具,用于从苏木精和伊红(H&E)全切片图像推断RS。我们的模型识别出TAILORx高危病例(RS>25)的曲线下面积(AUC)为0.89,而领先的临床病理列线图的AUC为0.73。此外,在RS≤25的患者中,Orpheus比RS本身更准确地确定转移复发风险(平均时间依赖性AUC为0.75对0.49)。这些发现有可能指导高危病例的辅助治疗,并为转移复发风险升高的患者定制监测方案。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/2d3d267b1eff/41467_2025_57283_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/a52f3bfa1f5d/41467_2025_57283_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/28aea26e2495/41467_2025_57283_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/7f5846da1dbf/41467_2025_57283_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/7c520816d90f/41467_2025_57283_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/2d3d267b1eff/41467_2025_57283_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/a52f3bfa1f5d/41467_2025_57283_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/28aea26e2495/41467_2025_57283_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/7f5846da1dbf/41467_2025_57283_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/7c520816d90f/41467_2025_57283_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a9bf/11873197/2d3d267b1eff/41467_2025_57283_Fig5_HTML.jpg

相似文献

1
Multimodal histopathologic models stratify hormone receptor-positive early breast cancer.多模态组织病理学模型对激素受体阳性早期乳腺癌进行分层。
Nat Commun. 2025 Mar 2;16(1):2106. doi: 10.1038/s41467-025-57283-x.
2
Development of a Nomogram to Predict the Recurrence Score of 21-Gene Prediction Assay in Hormone Receptor-Positive Early Breast Cancer.建立预测激素受体阳性早期乳腺癌 21 基因检测复发评分的列线图。
Clin Breast Cancer. 2020 Apr;20(2):98-107.e1. doi: 10.1016/j.clbc.2019.07.010. Epub 2019 Aug 21.
3
Oncotype DX breast cancer recurrence score can be predicted with a novel nomogram using clinicopathologic data.利用临床病理数据,通过一种新型列线图可以预测Oncotype DX乳腺癌复发评分。
Breast Cancer Res Treat. 2017 May;163(1):51-61. doi: 10.1007/s10549-017-4170-3. Epub 2017 Feb 27.
4
Nomogram Development for Assessing Oncotype DX Recurrence Scores in Breast Cancer: A Chinese Population Study.用于评估乳腺癌中Oncotype DX复发评分的列线图构建:一项中国人群研究
Cancer Med. 2025 Mar;14(6):e70818. doi: 10.1002/cam4.70818.
5
Development of a nomogram to predict recurrence scores obtained using Oncotype DX in Japanese patients with breast cancer.开发一个列线图模型,用于预测日本乳腺癌患者使用 Oncotype DX 获得的复发评分。
Breast Cancer. 2024 Nov;31(6):1018-1027. doi: 10.1007/s12282-024-01616-z. Epub 2024 Jul 17.
6
Recurrence score-predicted value derived from estrogen receptor, tumor-infiltrating lymphocytes, progesterone receptor, and Ki-67 may substitute for the Oncotype DX recurrence score in estrogen receptor (ER)+/human epidermal growth factor receptor 2 (HER2)- breast cancer.由雌激素受体、肿瘤浸润淋巴细胞、孕激素受体和Ki-67得出的复发评分预测值,可能在雌激素受体(ER)阳性/人表皮生长因子受体2(HER2)阴性乳腺癌中替代Oncotype DX复发评分。
Ann Diagn Pathol. 2025 Feb;74:152410. doi: 10.1016/j.anndiagpath.2024.152410. Epub 2024 Nov 16.
7
Is oncotype DX recurrence score (RS) of prognostic value once HER2-positive and. low-ER expression patients are removed?在去除 HER2 阳性和低雌激素受体表达的患者后,Oncotype DX 复发评分(RS)是否具有预后价值?
Breast J. 2013 Jul-Aug;19(4):357-64. doi: 10.1111/tbj.12126. Epub 2013 May 23.
8
Oncotype DX Predictive Nomogram for Recurrence Score Output: The Novel System ADAPTED01 Based on Quantitative Immunochemistry Analysis.Oncotype DX 复发评分预测诺莫图输出:基于定量免疫化学分析的新型 ADAPTED01 系统。
Clin Breast Cancer. 2020 Oct;20(5):e600-e611. doi: 10.1016/j.clbc.2020.04.012. Epub 2020 May 5.
9
Nomogram update based on TAILORx clinical trial results - Oncotype DX breast cancer recurrence score can be predicted using clinicopathologic data.基于 TAILORx 临床试验结果的列线图更新 - 可以使用临床病理数据预测 Oncotype DX 乳腺癌复发评分。
Breast. 2019 Aug;46:116-125. doi: 10.1016/j.breast.2019.05.006. Epub 2019 May 10.
10
A Nomogram for Predicting the Oncotype DX Recurrence Score in Women with T1-3N0-1miM0 Hormone Receptor‒Positive, Human Epidermal Growth Factor 2 (HER2)‒Negative Breast Cancer.用于预测 T1-3N0-1miM0 激素受体阳性、人表皮生长因子 2(HER2)阴性乳腺癌女性的 Oncotype DX 复发评分的列线图。
Cancer Res Treat. 2019 Jul;51(3):1073-1085. doi: 10.4143/crt.2018.357. Epub 2018 Nov 1.

引用本文的文献

1
Artificial intelligence-driven pathomics in hepatocellular carcinoma: current developments, challenges and perspectives.人工智能驱动的肝细胞癌病理组学:当前进展、挑战与展望
Discov Oncol. 2025 Jul 28;16(1):1424. doi: 10.1007/s12672-025-03254-z.
2
Deep Learning on Histopathological Images to Predict Breast Cancer Recurrence Risk and Chemotherapy Benefit.基于组织病理学图像的深度学习预测乳腺癌复发风险及化疗获益
medRxiv. 2025 May 16:2025.05.15.25327686. doi: 10.1101/2025.05.15.25327686.
3
Deep learning assessment of metastatic relapse risk from digitized breast cancer histological slides.

本文引用的文献

1
The spatially informed mFISHseq assay resolves biomarker discordance and predicts treatment response in breast cancer.空间信息引导的多重荧光原位杂交测序分析解决了乳腺癌生物标志物的不一致性,并预测了治疗反应。
Nat Commun. 2025 Jan 2;16(1):226. doi: 10.1038/s41467-024-55583-2.
2
From whole-slide image to biomarker prediction: end-to-end weakly supervised deep learning in computational pathology.从全切片图像到生物标志物预测:计算病理学中的端到端弱监督深度学习
Nat Protoc. 2025 Jan;20(1):293-316. doi: 10.1038/s41596-024-01047-2. Epub 2024 Sep 16.
3
Regression-based Deep-Learning predicts molecular biomarkers from pathology slides.
基于数字化乳腺癌组织切片的深度学习转移性复发风险评估
Nat Commun. 2025 Jul 1;16(1):5876. doi: 10.1038/s41467-025-60824-z.
4
Computational pathology for breast cancer: Where do we stand for prognostic applications?乳腺癌的计算病理学:在预后应用方面我们处于什么水平?
Breast. 2025 Jun;81:104464. doi: 10.1016/j.breast.2025.104464. Epub 2025 Mar 26.
5
Multimodal data integration in early-stage breast cancer.早期乳腺癌的多模态数据整合
Breast. 2025 Apr;80:103892. doi: 10.1016/j.breast.2025.103892. Epub 2025 Jan 28.
6
Explainable AI for computational pathology identifies model limitations and tissue biomarkers.用于计算病理学的可解释人工智能可识别模型局限性和组织生物标志物。
ArXiv. 2024 Nov 18:arXiv:2409.03080v2.
基于回归的深度学习从病理切片中预测分子生物标志物。
Nat Commun. 2024 Feb 10;15(1):1253. doi: 10.1038/s41467-024-45589-1.
4
Early breast cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up.早期乳腺癌:ESMO 诊断、治疗及随访临床实践指南
Ann Oncol. 2024 Feb;35(2):159-182. doi: 10.1016/j.annonc.2023.11.016. Epub 2023 Dec 13.
5
Association of tumor-infiltrating lymphocytes with recurrence score in hormone receptor-positive/HER2-negative breast cancer: Analysis of four prospective studies.激素受体阳性/人表皮生长因子受体2阴性乳腺癌中肿瘤浸润淋巴细胞与复发评分的关联:四项前瞻性研究分析
Eur J Cancer. 2023 Dec;195:113399. doi: 10.1016/j.ejca.2023.113399. Epub 2023 Oct 26.
6
Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study.基于Transformer 的结直肠癌组织学生物标志物预测:一项大规模多中心研究。
Cancer Cell. 2023 Sep 11;41(9):1650-1661.e4. doi: 10.1016/j.ccell.2023.08.002. Epub 2023 Aug 30.
7
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis.StudioGAN:用于图像合成的生成对抗网络分类法与基准测试
IEEE Trans Pattern Anal Mach Intell. 2023 Dec;45(12):15725-15742. doi: 10.1109/TPAMI.2023.3306436. Epub 2023 Nov 3.
8
A visual-language foundation model for pathology image analysis using medical Twitter.一种使用医学推特进行病理学图像分析的视觉语言基础模型。
Nat Med. 2023 Sep;29(9):2307-2316. doi: 10.1038/s41591-023-02504-3. Epub 2023 Aug 17.
9
Vision Transformers for Computational Histopathology.基于视觉Transformer 的计算病理技术
IEEE Rev Biomed Eng. 2024;17:63-79. doi: 10.1109/RBME.2023.3297604. Epub 2024 Jan 12.
10
NCCN Guidelines® Insights: Breast Cancer, Version 4.2023.NCCN 指南®洞察:乳腺癌,第 4.2023 版。
J Natl Compr Canc Netw. 2023 Jun;21(6):594-608. doi: 10.6004/jnccn.2023.0031.