AbstractA deep learning model using attention-based multiple instance learning (aMIL) and self-supervised learning (SSL) was developed to perform pathologic classification of neuroblastic tumors and assess MYCN-amplification status using H&E-stained whole slide images from the largest reported cohort to date.

摘要开发了一种使用基于注意力的多实例学习（aMIL）和自我监督学习（SSL）的深度学习模型，用于对神经母细胞肿瘤进行病理分类，并使用迄今为止报道的最大队列的H＆E染色的全幻灯片图像评估MYCN扩增状态。

The model showed promising performance in identifying diagnostic category, grade, mitosis-karyorrhexis index (MKI), and MYCN-amplification with validation on an external test dataset, suggesting potential for AI-assisted neuroblastoma classification..

该模型在识别诊断类别，等级，有丝分裂核破裂指数（MKI）和MYCN扩增方面表现出良好的性能，并在外部测试数据集上进行了验证，表明AI辅助神经母细胞瘤分类的潜力。。

IntroductionNeuroblastoma is a neuroblastic tumor (NT) and the most common extracranial pediatric solid tumor, affecting nearly 800 children in the United States annually1. To select optimal treatment strategies, patients are risk-stratified according to prognostic clinical, pathologic, and molecular variables including age, stage, histopathology, and MYCN-amplification2,3.

引言神经母细胞瘤是一种神经母细胞瘤（NT）和最常见的颅外小儿实体瘤，每年影响美国近800名儿童1。。

Approximately 40% of patients with neuroblastoma are classified as high-risk, which carries a 60% overall 3-year likelihood of event-free survival4. MYCN-amplification is present in 20% of NTs and, except for completely resected stage L1 tumors, typically places the patient in the high-risk category5.The pathologic classification of NTs is a major contributor to risk stratification.

大约40%的神经母细胞瘤患者被归类为高风险患者，总的3年无事件生存率为60%4。MYCN扩增存在于20%的NTs中，除了完全切除的L1期肿瘤外，通常将患者置于高风险类别5。NTs的病理分类是风险分层的主要因素。

The International Neuroblastoma Pathology Committee (INPC) uses combinations of four features—age, diagnostic category (neuroblastoma, ganglioneuroblastoma intermixed, ganglioneuroma, or ganglioneuroblastoma nodular), grade of differentiation, and mitosis-karyorrhexis index (MKI)—to classify tumors as favorable or unfavorable histology6.

国际神经母细胞瘤病理学委员会（INPC）使用四个特征的组合-年龄，诊断类别（神经母细胞瘤，神经节神经母细胞瘤混合，神经节神经瘤或神经节神经母细胞瘤结节），分化程度和有丝分裂核流变指数（MKI）-将肿瘤分类为有利或不利的组织学6。

INPC classification has significant prognostic ability unto itself, as those with unfavorable histology have a four times higher likelihood of relapse compared to those with favorable histology2.Histology from hematoxylin and eosin (H&E)-stained slides can also serve as a rich data source for deep learning models, which can be used to identify nuanced motifs in tumor morphology and produce precise risk stratification criteria7,8,9.

INPC分类本身具有显着的预后能力，因为组织学不良的患者复发的可能性是组织学良好的患者的四倍2。苏木精和曙红（H＆E）染色载玻片的组织学也可以作为深度学习模型的丰富数据来源，可用于识别肿瘤形态中的细微差别，并产生精确的风险分层标准7,8,9。

Machine learning algorithms have been used to analyze NT digitized histology as early as 2009, with models that segmented cells and extracted texture features from histology images to predict tumor grade10. More recently, convolutional neural networks (CNNs) ha.

早在2009年，机器学习算法就已被用于分析NT数字化组织学，其模型可以分割细胞并从组织学图像中提取纹理特征以预测肿瘤分级10。最近，卷积神经网络（CNN）ha。

Data availability

数据可用性

Restrictions apply to the availability of the datasets, but all requests will be promptly evaluated based on institutional and departmental policies to determine whether the data requested are subject to intellectual property or patient privacy obligations. The University of Chicago, Children’s Oncology Group, and Lurie Children’s Hospital datasets can only be shared for non-commercial academic purposes and will require a data user agreement..

限制适用于数据集的可用性，但将根据机构和部门政策立即评估所有请求，以确定请求的数据是否受知识产权或患者隐私义务的约束。芝加哥大学儿童肿瘤小组和卢里儿童医院的数据集只能用于非商业学术目的，需要数据用户协议。。

Code availability

代码可用性

This code relies extensively on the open-source software package Slideflow, version 2.3.1, which is available at https://github.com/slideflow/slideflow. The code used for this experiment can be found at https://github.com/siddhir/NB_histology.

此代码广泛依赖于开源软件包Slideflow，版本2.3.1，可在https://github.com/slideflow/slideflow.用于此实验的代码可以在https://github.com/siddhir/NB_histology.

ReferencesCampbell, K. et al. A comprehensive analysis of neuroblastoma incidence, survival, and racial and ethnic disparities from 2001 to 2019. Pediatr. Blood Cancer 71, e30732 (2024).Article

参考文献Campbell，K。等人。2001年至2019年神经母细胞瘤发病率，生存率以及种族和种族差异的综合分析。。血癌71，e30732（2024）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Irwin, M. S. et al. Revised neuroblastoma risk classification system: a report from the Children’s Oncology Group. J. Clin. Oncol. 39, 3229–3241 (2021).Article

Irwin，M.S.等人修订了神经母细胞瘤风险分类系统：儿童肿瘤学小组的报告。J、 临床。Oncol公司。393229-3241（2021）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Sokol, E. et al. Age, diagnostic category, tumor grade, and mitosis-karyorrhexis index are independently prognostic in neuroblastoma: an INRG project. J. Clin. Oncol. 38, 1906–1918 (2020).Article

Sokol，E.等人。年龄，诊断类别，肿瘤分级和有丝分裂核破裂指数是神经母细胞瘤的独立预后因素：INRG项目。J、 临床。Oncol公司。381906-1918（2020）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Pinto, N. R. et al. Advances in risk classification and treatment strategies for neuroblastoma. J. Clin. Oncol. 33, 3008–3017 (2015).Article

Pinto，N.R.等人。神经母细胞瘤风险分类和治疗策略的进展。J、 临床。Oncol公司。。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Thompson, D. et al. Identification of patient subgroups with markedly disparate rates of MYCN amplification in neuroblastoma: a report from the International Neuroblastoma Risk Group project. Cancer 122, 935–945 (2016).Article

Thompson，D.等人，《神经母细胞瘤中MYCN扩增率明显不同的患者亚组的鉴定：国际神经母细胞瘤风险小组项目的报告》。癌症122935-945（2016）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Shimada, H. et al. The international neuroblastoma pathology classification (the Shimada system). Cancer 86, 364–372 (1999).Article

Shimada，H.等人，《国际神经母细胞瘤病理分类》（Shimada系统）。癌症86364-372（1999）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Qaiser, T. et al. Usability of deep learning and H&E images predict disease outcome-emerging tool to optimize clinical trials. npj Precis. Oncol. 6, 1–12 (2022).

Qaiser，T。等人。深度学习和H＆E图像的可用性预测疾病结果新兴工具，以优化临床试验。npj精度。Oncol公司。6，1-12（2022）。

Google Scholar

谷歌学者

Hu, J. et al. Prediction of clinicopathological features, multi-omics events and prognosis based on digital pathology and deep learning in HR+/HER2− breast cancer. J. Thorac. Dis. 15, https://doi.org/10.21037/jtd-23-445 (2023).Liang, J. et al. Deep learning supported discovery of biomarkers for clinical prognosis of liver cancer.

Hu，J.等人。基于数字病理学和HR+/HER2-乳腺癌深度学习的临床病理特征，多组学事件和预后预测。J、 胸部。Dis。15岁，https://doi.org/10.21037/jtd-23-445（2023年）。Liang，J。等人。深度学习支持发现肝癌临床预后的生物标志物。

Nat. Mach. Intell. 5, 408–420 (2023).Article .

纳特，去吧。英特尔。5, 408–420 (2023).第条。

Google Scholar

谷歌学者

Kong, J. et al. Computer-aided evaluation of neuroblastoma on whole-slide histology images: classifying grade of neuroblastic differentiation. Pattern Recognit. 42, 1080–1092 (2009).Article

Kong，J.等。全玻片组织学图像上神经母细胞瘤的计算机辅助评估：神经母细胞分化的分类等级。模式识别。421080-1092（2009）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gheisari, S., Catchpoole, D. R., Charlton, A. & Kennedy, P. J. Convolutional deep belief network with feature encoding for classification of neuroblastoma histological images. J. Pathol. Inform. 9, 17 (2018).Article

Gheisari，S.，Catchpoole，D.R.，Charlton，A。＆Kennedy，P.J。卷积深度信念网络，具有用于神经母细胞瘤组织学图像分类的特征编码。J、 病理学。通知。9，17（2018）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wang, X. et al. Transformer-based unsupervised contrastive learning for histopathological image classification. Med. Image Anal. 81, 102559 (2022).Article

Wang，X。等。基于变压器的无监督对比学习用于组织病理学图像分类。医学图像肛门。81102559（2022）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. Proceedings of the 35th International Conference on Machine Learning, vol 80, pp. 2127–2136 (2018).Dolezal, J. M. et al. Slideflow: deep learning for digital histopathology with real-time whole-slide visualization.

Ilse，M.，Tomczak，J。＆Welling，M。基于注意力的深度多实例学习。第35届国际机器学习会议论文集，第80卷，第2127-2136页（2018）。Dolezal，J.M.等人，《Slideflow：数字组织病理学的深度学习，实时全幻灯片可视化》。

BMC Bioinform. 25, 134 (2024).Article .

BMC生物信息。25134（2024）。文章。

Google Scholar

谷歌学者

Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850–862 (2024).Article

Chen，R.J.等人，迈向计算病理学的通用基础模型。《自然医学》30850-862（2024）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Deng, J. et al. ImageNet: a large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition 248–255 https://doi.org/10.1109/CVPR.2009.5206848 (2009).Filiot, A. et al. Scaling self-supervised learning for histopathology with masked image modeling.

Deng，J。等人。ImageNet：一个大规模的分层图像数据库。https://doi.org/10.1109/CVPR.2009.5206848（2009年）。Filiot，A.等人。使用掩蔽图像建模缩放组织病理学的自我监督学习。

Published online September 14, 2023. https://doi.org/10.1101/2023.07.21.23292757Dolezal, J. M. et al. Deep learning generates synthetic cancer histology for explainability and education. npj Precis. Oncol. 7, 1–13 (2023)..

2023年9月14日在线发布。https://doi.org/10.1101/2023.07.21.23292757Dolezal深度学习产生合成癌症组织学，用于解释和教育。npj精度。Oncol公司。7，1-13（2023年）。。

Google Scholar

谷歌学者

Luttikhuis, M. E. et al. Neuroblastomas with chromosome 11q loss and single copy MYCN comprise a biologically distinct group of tumours with adverse prognosis. Br. J. Cancer 85, 531–537 (2001).Article

Luttikhuis，M.E.等人。染色体11q丢失和单拷贝MYCN的神经母细胞瘤是一组生物学上不同的肿瘤，预后不良。《癌症杂志》85531-537（2001）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Download referencesAcknowledgementsThis work was supported in part by the Burroughs Wellcome Fund Early Scientific Training Program to Prepare for Research Excellence Post-Graduation (BEST-PREP; S.R.), University of Chicago Pritzker School of Medicine Summer Research Program (S.R.). Also supported by the National Institutes of Health P30CA014599 which provided funding for the analysis and supports the Human Tissue Research Core at the University of Chicago.

下载参考文献致谢这项工作得到了Burroughs Wellcome基金早期科学培训计划的部分支持，该计划旨在为毕业后的卓越研究做好准备（BEST-PREP；S.R.），芝加哥大学普利茨克医学院夏季研究计划（S.R.）。。

Research reported in this publication was supported by the Children’s Oncology Group, the National Cancer Institute of the National Institutes of Health under award numbers U10CA180886, U24CA196173, and U10CA180899. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute of Health.

。内容完全由作者负责，不一定代表国家卫生研究院的官方观点。

We would like to thank Dr. Lynn Yee for facilitating the inter-institutional exchange of H&E-stained slides.Author informationAuthors and AffiliationsDepartment of Medicine, University of Chicago, Chicago, IL, USASiddhi Ramesh, Emma Dyer, Sara Kochanny & Alexander T. PearsonDepartment of Pediatrics, The Children’s Hospital of Philadelphia, Philadelphia, PA, USAMonica PomavilleAnatomic Pathology Department of Oklahoma University Medical Center, Oklahoma City, OK, USAKristina DoytchevaGeisinger Cancer Institute, Danville, PA, USAJames DolezalPritzker School of Medicine, University of Chicago, Chicago, IL, USARachel TerhaarIntermountain Primary Children’s Hospital, Huntsman Cancer Institute, Spencer Fox Eccles School of Medicine at the University of Utah, Salt Lake City, UT, USACasey J.

我们要感谢Lynn Yee博士促进H＆E染色载玻片的机构间交流。作者信息作者和附属机构芝加哥大学医学系，伊利诺伊州芝加哥市，USASiddhi Ramesh，Emma Dyer，Sara Kochanny和Alexander T.PearsonDepartment of Pediatrics，The Children’s Hospital of Philadelphia，Philadelphia，PA，USAMonica POMAVILLE解剖病理学系俄克拉荷马大学医学中心，俄克拉荷马州俄克拉荷马市，USAKristina DoytchevaGeisinger癌症研究所，丹维尔，宾夕法尼亚州，USAHAMES DolezalPritzker医学院，芝加哥大学，伊利诺伊州，USARCHEL TerhaarIntermountain小学儿童医院，亨茨曼癌症研究所，斯宾塞福克斯埃克尔斯犹他大学医学院，犹他州盐湖城，USACaseyJ。

MehrhoffCancer and Blood Disorders Center, Seattle Children’s Hospital, Seattle, WA, USAKritika PatelDivision of Hematology/Oncology and Bone Marrow Transplant, Dep.

华盛顿州西雅图市西雅图儿童医院Mehrhoff癌症和血液疾病中心，USAKritika PatelDivision血液学/肿瘤学和骨髓移植，Dep。

PubMed Google ScholarEmma DyerView author publicationsYou can also search for this author in

PubMed Google ScholarEmma DyerView作者出版物您也可以在

PubMed Google ScholarMonica PomavilleView author publicationsYou can also search for this author in

PubMed Google ScholarMonica PomavilleView作者出版物您也可以在

PubMed Google ScholarKristina DoytchevaView author publicationsYou can also search for this author in

PubMed Google ScholarKristina DoytchevaView作者出版物您也可以在

PubMed Google ScholarJames DolezalView author publicationsYou can also search for this author in

PubMed谷歌学者James DolezalView作者出版物您也可以在

PubMed Google ScholarSara KochannyView author publicationsYou can also search for this author in

PubMed Google ScholarSara KochannyView作者出版物您也可以在

PubMed Google ScholarRachel TerhaarView author publicationsYou can also search for this author in

PubMed Google ScholarRachel TerhaarView作者出版物您也可以在

PubMed Google ScholarCasey J. MehrhoffView author publicationsYou can also search for this author in

PubMed谷歌学术期刊J.MehrhoffView作者出版物您也可以在

PubMed Google ScholarKritika PatelView author publicationsYou can also search for this author in

PubMed Google ScholarKritika PatelView作者出版物您也可以在

PubMed Google ScholarJacob BrewerView author publicationsYou can also search for this author in

PubMed Google ScholarJacob BrewerView作者出版物您也可以在

PubMed Google ScholarBenjamin KusswurmView author publicationsYou can also search for this author in

PubMed Google ScholarBenjamin Kusswormview作者出版物您也可以在

PubMed Google ScholarArlene NaranjoView author publicationsYou can also search for this author in

PubMed Google ScholarArlene NaranjoView作者出版物您也可以在

PubMed Google ScholarHiroyuki ShimadaView author publicationsYou can also search for this author in

PubMed谷歌学者ShimadaView作者出版物您也可以在

PubMed Google ScholarNicole A. CiprianiView author publicationsYou can also search for this author in

PubMed Google ScholarNicole A.CiprianiView作者出版物您也可以在

PubMed Google ScholarAliya N. HusainView author publicationsYou can also search for this author in

PubMed Google ScholarAliya N.HusainView作者出版物您也可以在

PubMed Google ScholarPeter PytelView author publicationsYou can also search for this author in

PubMed Google ScholarPeter PytelView作者出版物您也可以在

PubMed Google ScholarElizabeth A. SokolView author publicationsYou can also search for this author in

PubMed Google ScholarElizabeth A.SokolView作者出版物您也可以在

PubMed Google ScholarSusan L. CohnView author publicationsYou can also search for this author in

PubMed Google ScholarSusan L.CohnView作者出版物您也可以在

PubMed Google ScholarRani E. GeorgeView author publicationsYou can also search for this author in

PubMed Google ScholarRani E.GeorgeView作者出版物您也可以在

PubMed Google ScholarAlexander T. PearsonView author publicationsYou can also search for this author in

PubMed Google ScholarAlexander T.PearsonView作者出版物您也可以在

PubMed Google ScholarMark A. ApplebaumView author publicationsYou can also search for this author in

PubMed Google ScholarMark A.ApplebaumView作者出版物您也可以在

PubMed Google ScholarContributionsSiddhi Ramesh (S.R.): conceptualization, methodology, investigation, formal analysis, and writing—reviewing and editing. Emma Chancellor Dyer (E.C.D.): writing–original draft, visualization, software. Monica Pomaville (M.P.): writing—data curation, reviewing and editing.

PubMed谷歌学术贡献Siddhi Ramesh（S.R.）：概念化，方法论，调查，形式分析以及写作评论和编辑。艾玛·戴尔（E.C.D.）：写作-原稿，可视化，软件。莫妮卡·波马维尔（M.P.）：撰写数据管理，审查和编辑。

Kristina Doytcheva (K.D.): writing—histology review, reviewing and editing. James Dolezal (J.D.): writing—reviewing and editing. Sara Kochanny (S.K.): writing—data curation, reviewing and editing. Rachel Terhaar (R.T.): writing—data curation, reviewing and editing. Casey J Mehrhoff (C.J.M.): writing—data curation, reviewing and editing.

克里斯蒂娜·多伊切娃（K.D.）：撰写组织学评论，评论和编辑。詹姆斯·多莱扎尔（J.D.）：写作、评论和编辑。Sara Kochanny（S.K.）：撰写数据管理，审查和编辑。Rachel Terhaar（R.T.）：撰写数据管理，审查和编辑。Casey J Mehrhoff（C.J.M.）：撰写数据管理，审查和编辑。

Kritika Patel (K.P.): writing—data curation, reviewing and editing. Jacob Brewer (J.B.): writing—formal analysis, reviewing and editing. Benjamin Kusswurm (B.K.): writing—formal analysis, reviewing and editing. Hiroyuki Shimada (H.S.): writing—data curation, reviewing and editing. Arlene Naranjo (A.N.): writing—data curation, reviewing and editing.

Kritika Patel（K.P.）：撰写数据管理，审查和编辑。雅各布·布鲁尔（J.B.）：撰写正式分析，评论和编辑。本杰明·库斯沃姆（B.K.）：撰写正式分析，评论和编辑。Hiroyuki Shimada（H.S.）：撰写数据管理，审查和编辑。。

Peter Pytel (P.P.): writing—histology review, reviewing and editing. Nicole A CIpriani (N.C.): writing—histology review, reviewing and editing. Aliya N Husain (A.H.): writing—histology review, reviewing and editing. Elizabeth A Sokol (E.A.S.): writing—data curation, reviewing and editing. Susan L Cohn (S.L.C.): writing—data curation, reviewing and editing.

彼得·皮特尔（P.P.）：撰写组织学评论，评论和编辑。Nicole A CIpriani（N.C.）：撰写组织学评论，评论和编辑。。伊丽莎白·索科尔（E.A.S.）：撰写数据管理，审查和编辑。苏珊·科恩（S.L.C.）：撰写数据管理，审查和编辑。

Rani E George (R.E.G.): writing—data curation, reviewing and editing. Alexander T Pearson (A.T.P.): writing—methodology, reviewing and editing. Mark A Applebaum (M.A.A.): writing—conceptualization, methodology, formal analysis, Writing—reviewing and editing.Corresponding authorCorrespondence to.

Rani E George（R.E.G.）：撰写数据管理，审查和编辑。亚历山大·皮尔逊（A.T.P.）：写作方法，评论和编辑。Mark A Applebaum（文学硕士）：写作概念化，方法论，形式分析，写作评论和编辑。对应作者对应。

Mark A. Applebaum.Ethics declarations

标记A.Applebaum。道德宣言

Competing interests

相互竞争的利益

S.R. is the Chief Scientific Officer of Slideflow Labs. J.D. is the Chief Executive Officer of Slideflow Labs. B.K. is a current employee of YouTube. J.B. is an employee of Milliman. S.L.C. reports consulting fees from US WorldMeds. A.T.P. reports consulting fees from Prelude Biotherapeutics, LLC, Ayala Pharmaceuticals, Elvar Therapeutics, Abbvie, and Privo, and contracted research with Kura Oncology, Abbvie, and EMD Serono.

S、 R.是Slideflow实验室的首席科学官。J、 D.是Slideflow实验室的首席执行官。B、 K.是YouTube的现任员工。J、 B.是Milliman的员工。S、 。A、 T.P.报告了Prelude Biotherapeutics，LLC，Ayala Pharmaceuticals，Elvar Therapeutics，Abbvie和Privo的咨询费，并与Kura Oncology，Abbvie和EMD Serono签订了研究合同。

A.T.P. is on the Scientific Advisory Board of Slideflow Labs. All other authors report no competing interests..

A、 。所有其他作者均报告没有利益冲突。。

Additional informationPublisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Rights and permissions

Additional informationPublisher的注释Springer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。权限和权限

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

开放获取本文是根据知识共享署名非商业性NoDerivatives 4.0国际许可证授权的，该许可证允许以任何媒介或格式进行任何非商业性使用，共享，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出您是否修改了许可材料。

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

根据本许可证，您无权共享源自本文或其部分的改编材料。本文中的图像或其他第三方材料包含在文章的知识共享许可证中，除非该材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可证中，并且您的预期用途未被法律法规允许或超出允许的用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by-nc-nd/4.0/..

Reprints and permissionsAbout this articleCite this articleRamesh, S., Dyer, E., Pomaville, M. et al. Artificial intelligence-based morphologic classification and molecular characterization of neuroblastic tumors from digital histopathology.

转载和许可本文引用本文Ramesh，S.，Dyer，E.，Pomaville，M。等人。基于数字组织病理学的神经母细胞肿瘤的基于人工智能的形态学分类和分子表征。

npj Precis. Onc. 8, 255 (2024). https://doi.org/10.1038/s41698-024-00745-0Download citationReceived: 09 May 2024Accepted: 25 October 2024Published: 08 November 2024DOI: https://doi.org/10.1038/s41698-024-00745-0Share this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

npj精度。Onc。8255（2024）。https://doi.org/10.1038/s41698-024-00745-0Downloadhttps://doi.org/10.1038/s41698-024-00745-0Share本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供