@文章{Gui889,作者= {Gui,先勇和巴扎罗娃,Alina和del Amor, Roc和Vieth, Michael和de Hertogh, Gert和Villanacci, Vincenzo和Zardo, Davide和Parigi, Tommaso Lorenzo和R{\ \o}yset, Elin Synn{\ \o}ve和Shivaji, Uday N和Monica, Melissa Anna Teresa和Mandelli, Giulio和Bhandari, Pradeep和Danese, Silvio和Ferraz, Jose G和Hayee, Bu{\textquoteright Hussain和Lazarev, Mark和Parra-Blanco, Adolfo和Pastorelli, Luca和Panaccione, Remo和Rath,Timo和Tontini, Gian Eugenio和Kiesslich, Ralf和Bisschops, Raf和Grisan, Enrico和Naranjo, Valery和Ghosh, Subrata和Iacucci, Marietta},标题={毕加索溃疡性结肠炎的组织学缓解指数(PHRI):开发一种用于监测粘膜愈合和预测临床结果的新型简化组织学评分及其在人工智能系统中的应用},卷={71},数={5},页数={889—898},年= {2022},doi = {10.1136/gutjnl-2021-326376},出版商= {BMJ出版集团},摘要={组织学缓解正在演变为UC的重要治疗目标。我们的目标是开发一种简单的组织学指标,与内窥镜检查相一致,与临床结果相关,适合应用于人工智能(AI)系统来评估炎症活动。方法采用一项前瞻性多中心研究,收集307例UC患者的614例活检,我们开发了帕丁顿国际虚拟色内窥镜评分(PICaSSO)组织学缓解指数(PHRI)。评估了与其他多个组织学指标的一致性以及阅读器间重复性的验证。最后,为了将PHRI实现到计算机辅助诊断系统中,我们训练并测试了一种基于CNN架构的新型深度学习策略,以检测中性粒细胞,计算PHRI,并使用138个活检组织的子集识别活跃的静态UC。结果PHRI与内镜评分(Mayo内镜评分和UC内镜严重程度指数和PICaSSO)以及临床结果(住院、结肠切除术和因UC发作而开始或改变药物治疗)密切相关。PHRI评分为1可以准确地对患者在12个月内的不良结局(住院、结肠切除术和因突发发作而优化治疗)的风险进行分层。读者之间的一致性很高(类内相关性为0.84)。我们初步的AI算法区分主动UC和静态UC的灵敏度为78%,特异性为91.7%,准确率为86%。Conclusions PHRI is a simple histological index in UC, and it exhibits the highest correlation with endoscopic activity and clinical outcomes. A PHRI-based AI system was accurate in predicting histological remission.Data are available on reasonable request. Computer algorithm code available on reasonable request.}, issn = {0017-5749}, URL = {//www.marcconsult.com/content/71/5/889}, eprint = {//www.marcconsult.com/content/71/5/889.full.pdf}, journal = {Gut} }