Suppr超能文献

病理学图像库——病理学标准化的参考图像数据库。

Pathology Imagebase-a reference image database for standardization of pathology.

机构信息

Department of Oncology and Pathology, Karolinska Institutet, Stockholm, Sweden.

Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, USA.

出版信息

Histopathology. 2017 Nov;71(5):677-685. doi: 10.1111/his.13313. Epub 2017 Sep 13.

Abstract

AIMS

Despite efforts to standardize histopathology practice through the development of guidelines, the interpretation of morphology is still hampered by subjectivity. We here describe Pathology Imagebase, a novel mechanism for establishing an international standard for the interpretation of pathology specimens.

METHODS AND RESULTS

The International Society of Urological Pathology (ISUP) established a reference image database through the input of experts in the field. Three panels were formed, one each for prostate, urinary bladder and renal pathology, consisting of 24 international experts. Each of the panel members uploaded microphotographs of cases into a non-public database. The remaining 23 experts were asked to vote from a multiple-choice menu. Prior to and while voting, panel members were unable to access the results of voting by the other experts. When a consensus level of at least two-thirds or 16 votes was reached, cases were automatically transferred to the main database. Consensus was reached in a total of 287 cases across five projects on the grading of prostate, bladder and renal cancer and the classification of renal tumours and flat lesions of the bladder. The full database is available to all ISUP members at www.isupweb.org. Non-members may access a selected number of cases.

CONCLUSIONS

It is anticipated that the database will assist pathologists in calibrating their grading, and will also promote consistency in the diagnosis of difficult cases.

摘要

目的

尽管通过制定指南努力使组织病理学实践标准化,但形态学的解释仍然受到主观性的阻碍。我们在此描述病理学图像库(Pathology Imagebase),这是一种为病理学标本解释建立国际标准的新机制。

方法和结果

国际泌尿病理学会(ISUP)通过该领域专家的输入建立了参考图像数据库。成立了三个小组,分别用于前列腺、膀胱和肾脏病理学,每个小组由 24 名国际专家组成。每个小组成员将病例的显微照片上传到非公开数据库。其余 23 名专家被要求从多项选择题菜单中进行投票。在投票之前和投票过程中,小组成员无法访问其他专家的投票结果。当达到至少三分之二或 16 票的共识水平时,病例将自动转移到主数据库。在五个项目中总共就前列腺、膀胱和肾癌的分级以及肾脏肿瘤和平膀胱病变的分类达成了共识,共有 287 例病例。完整的数据库可在 www.isupweb.org 上供所有 ISUP 成员使用。非成员可以访问选定数量的病例。

结论

预计该数据库将有助于病理学家校准分级,还将促进对疑难病例诊断的一致性。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验