One label is all you need: Interpretable AI-enhanced histopathology for oncology

IF 12.1 1区 医学 Q1 ONCOLOGY Seminars in cancer biology Pub Date : 2023-12-01 DOI:10.1016/j.semcancer.2023.09.006
Thomas E. Tavolara, Ziyu Su, Metin N. Gurcan, M. Khalid Khan Niazi
{"title":"One label is all you need: Interpretable AI-enhanced histopathology for oncology","authors":"Thomas E. Tavolara,&nbsp;Ziyu Su,&nbsp;Metin N. Gurcan,&nbsp;M. Khalid Khan Niazi","doi":"10.1016/j.semcancer.2023.09.006","DOIUrl":null,"url":null,"abstract":"<div><p><span><span>Artificial Intelligence (AI)-enhanced histopathology presents unprecedented opportunities to benefit oncology through interpretable methods that require only one overall label per hematoxylin and eosin (H&amp;E) slide with no tissue-level annotations. We present a structured review of these methods organized by their degree of verifiability and by commonly recurring application areas in oncological characterization. First, we discuss morphological markers (tumor presence/absence, metastases, subtypes, grades) in which AI-identified regions of interest (ROIs) within whole slide images (WSIs) verifiably overlap with pathologist-identified ROIs. Second, we discuss </span>molecular markers<span> (gene expression, molecular subtyping) that are not verified via H&amp;E but rather based on overlap with positive regions on adjacent tissue. Third, we discuss genetic markers (mutations, mutational burden, microsatellite instability, chromosomal instability) that current technologies cannot verify if AI methods spatially resolve specific </span></span>genetic alterations. Fourth, we discuss the direct prediction of survival to which AI-identified histopathological features quantitatively correlate but are nonetheless not mechanistically verifiable. Finally, we discuss in detail several opportunities and challenges for these one-label-per-slide methods within oncology. Opportunities include reducing the cost of research and clinical care, reducing the workload of clinicians, personalized medicine, and unlocking the full potential of histopathology through new imaging-based biomarkers. Current challenges include explainability and interpretability, validation via adjacent tissue sections, reproducibility, data availability, computational needs, data requirements, domain adaptability, external validation, dataset imbalances, and finally commercialization and clinical potential. Ultimately, the relative ease and minimum upfront cost with which relevant data can be collected in addition to the plethora of available AI methods for outcome-driven analysis will surmount these current limitations and achieve the innumerable opportunities associated with AI-driven histopathology for the benefit of oncology.</p></div>","PeriodicalId":21594,"journal":{"name":"Seminars in cancer biology","volume":null,"pages":null},"PeriodicalIF":12.1000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seminars in cancer biology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1044579X23001281","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Artificial Intelligence (AI)-enhanced histopathology presents unprecedented opportunities to benefit oncology through interpretable methods that require only one overall label per hematoxylin and eosin (H&E) slide with no tissue-level annotations. We present a structured review of these methods organized by their degree of verifiability and by commonly recurring application areas in oncological characterization. First, we discuss morphological markers (tumor presence/absence, metastases, subtypes, grades) in which AI-identified regions of interest (ROIs) within whole slide images (WSIs) verifiably overlap with pathologist-identified ROIs. Second, we discuss molecular markers (gene expression, molecular subtyping) that are not verified via H&E but rather based on overlap with positive regions on adjacent tissue. Third, we discuss genetic markers (mutations, mutational burden, microsatellite instability, chromosomal instability) that current technologies cannot verify if AI methods spatially resolve specific genetic alterations. Fourth, we discuss the direct prediction of survival to which AI-identified histopathological features quantitatively correlate but are nonetheless not mechanistically verifiable. Finally, we discuss in detail several opportunities and challenges for these one-label-per-slide methods within oncology. Opportunities include reducing the cost of research and clinical care, reducing the workload of clinicians, personalized medicine, and unlocking the full potential of histopathology through new imaging-based biomarkers. Current challenges include explainability and interpretability, validation via adjacent tissue sections, reproducibility, data availability, computational needs, data requirements, domain adaptability, external validation, dataset imbalances, and finally commercialization and clinical potential. Ultimately, the relative ease and minimum upfront cost with which relevant data can be collected in addition to the plethora of available AI methods for outcome-driven analysis will surmount these current limitations and achieve the innumerable opportunities associated with AI-driven histopathology for the benefit of oncology.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
一个标签就是你所需要的:可解释的AI增强肿瘤学组织病理学。
人工智能(AI)增强的组织病理学为肿瘤学提供了前所未有的机会,通过可解释的方法,每个苏木精和伊红(H&E)载玻片只需要一个整体标签,而不需要组织水平的注释。我们对这些方法进行了结构化的综述,根据其可验证性程度和肿瘤学表征中常见的应用领域进行组织。首先,我们讨论了形态学标志物(肿瘤存在/不存在、转移、亚型、分级),其中AI识别的全玻片图像(WSI)中的感兴趣区域(ROI)与病理学家识别的ROI可验证地重叠。其次,我们讨论了分子标记(基因表达、分子亚型),这些标记不是通过H&E验证的,而是基于与相邻组织上阳性区域的重叠。第三,我们讨论了当前技术无法验证的遗传标记(突变、突变负担、微卫星不稳定性、染色体不稳定性),如果人工智能方法在空间上解决了特定的遗传变化。第四,我们讨论了AI识别的组织病理学特征与生存率的直接预测在数量上相关,但在机制上无法验证。最后,我们详细讨论了肿瘤学中这种每张幻灯片一个标签的方法的几个机遇和挑战。机会包括降低研究和临床护理成本,减少临床医生的工作量,个性化医疗,以及通过新的基于成像的生物标志物释放组织病理学的全部潜力。当前的挑战包括可解释性和可解释性、通过相邻组织切片的验证、再现性、数据可用性、计算需求、数据要求、领域适应性、外部验证、数据集失衡,以及最终的商业化和临床潜力。最终,除了用于结果驱动分析的大量可用人工智能方法外,收集相关数据的相对容易性和最低前期成本将克服当前的这些限制,并实现与人工智能驱动的组织病理学相关的无数机会,造福肿瘤学。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Seminars in cancer biology
Seminars in cancer biology 医学-肿瘤学
CiteScore
26.80
自引率
4.10%
发文量
347
审稿时长
15.1 weeks
期刊介绍: Seminars in Cancer Biology (YSCBI) is a specialized review journal that focuses on the field of molecular oncology. Its primary objective is to keep scientists up-to-date with the latest developments in this field. The journal adopts a thematic approach, dedicating each issue to an important topic of interest to cancer biologists. These topics cover a range of research areas, including the underlying genetic and molecular causes of cellular transformation and cancer, as well as the molecular basis of potential therapies. To ensure the highest quality and expertise, every issue is supervised by a guest editor or editors who are internationally recognized experts in the respective field. Each issue features approximately eight to twelve authoritative invited reviews that cover various aspects of the chosen subject area. The ultimate goal of each issue of YSCBI is to offer a cohesive, easily comprehensible, and engaging overview of the selected topic. The journal strives to provide scientists with a coordinated and lively examination of the latest developments in the field of molecular oncology.
期刊最新文献
Unravelling the complexities of resistance mechanism in pancreatic cancer: Insights from in vitro and ex-vivo model systems Convergent evolution of senescent fibroblasts in fibrosis and cancer with aging A systematic review of cardiovascular toxicities induced by cancer immune therapies: Underlying mechanisms, clinical manifestations and therapeutic approaches BubR1 and SIRT2: Insights into aneuploidy, aging, and cancer Origins and molecular effects of hypoxia in cancer
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1