Novel artificial intelligence system increases the detection of prostate cancer in whole slide images of core needle biopsies.
Novel artificial intelligence system increases the detection of prostate cancer in whole slide images of core needle biopsies.
复制标题
DOI：
10.1038/s41379-020-0551-y
复制
发表时间：
2020-10
期刊：
影响因子：
7.5
通讯作者：
Fuchs, Thomas J.
中科院分区：
文献类型：
--
作者：
Raciti, Patricia;Sue, Jillian;Ceballos, Rodrigo;Godrich, Ran;Kunz, Jeremy D.;Kapur, Supriya;Reuter, Victor;Grady, Leo;Kanan, Christopher;Klimstra, David S.;Fuchs, Thomas J.
前列腺癌（PrCa）是美国男性中第二常见的癌症。检测PrCa的金标准是前列腺穿刺活检。诊断可能具有挑战性，特别是对于小的，分化良好的癌症。最近，已经开发了机器学习算法，用于以高测试精度检测全载玻片图像（WSI）中的PrCa。然而，这些人工智能系统对病理诊断的影响尚不清楚。为了解决这个问题，我们研究了病理学家如何与Paige Prostate Alpha互动，Paige Prostate Alpha是一种最先进的PrCa检测系统，用于苏木精和伊红（H&E）染色的前列腺针芯活检的WSI。三名AP委员会认证的病理学家在8小时内评估了304例匿名前列腺针芯活检WSI。病理学家将每个WSI分类为良性或癌性。大约4周后，病理学家负责在Paige Prostate Alpha的帮助下重新审查每个WSI。对于每个WSI，Paige Prostate Alpha用于执行癌症检测，对于检测到癌症的WSI，系统标记检测到癌症的概率最高的区域。每个载玻片的原始诊断由泌尿生殖道病理学家提供，并纳入原始诊断评估期间要求的任何辅助研究。根据这一基本事实，病理学家和佩奇前列腺阿尔法进行了测量。在没有Paige Prostate Alpha的情况下，病理学家的平均灵敏度为74%，平均特异性为97%。使用Paige Prostate Alpha，病理学家的平均灵敏度显著增加至90%，特异性无统计学显著变化。使用Paige Prostate Alpha，病理学家更经常地正确分类较小，较低级别的肿瘤，并花费更少的时间分析每个WSI。未来的研究将调查当这样的系统用于在更接近模拟真实的实践的环境中检测其他形式的癌症时是否产生类似的益处。
Prostate cancer (PrCa) is the second most common cancer among men in the United States. The gold standard for detecting PrCa is the examination of prostate needle core biopsies. Diagnosis can be challenging, especially for small, well differentiated cancers. Recently, machine learning algorithms have been developed for detecting PrCa in whole slide images (WSIs) with high test accuracy. However, the impact of these artificial intelligence systems on pathologic diagnosis is not known. To address this, we investigated how pathologists interact with Paige Prostate Alpha, a state-of-the-art PrCa detection system in WSIs of prostate needle core biopsies stained with hematoxylin and eosin (H&E). Three AP-board certified pathologists assessed 304 anonymized prostate needle core biopsy WSIs in 8 hours. The pathologists classified each WSI as benign or cancerous. After approximately 4 weeks, pathologists were tasked with re-reviewing each WSI with the aid of Paige Prostate Alpha. For each WSI, Paige Prostate Alpha was used to perform cancer detection and, for WSIs where cancer was detected, the system marked the area where cancer was detected with the highest probability. The original diagnosis for each slide was rendered by genitourinary pathologists and incorporated any ancillary studies requested during the original diagnostic assessment. Against this ground truth, the pathologists and Paige Prostate Alpha were measured. Without Paige Prostate Alpha, pathologists had an average sensitivity of 74% and an average specificity of 97%. With Paige Prostate Alpha, the average sensitivity for pathologists significantly increased to 90% with no statistically significant change in specificity. With Paige Prostate Alpha, pathologists more often correctly classified smaller, lower grade tumors and spent less time analyzing each WSI. Future studies will investigate if similar benefit is yielded when such a system is used to in the detection of other forms of cancer in a setting that more closely emulates real practice.
登录
查看更多内容
影响因子：
3.5
作者：
Renshaw, AA;Cartagena, N;Gould, EW
通讯作者：
Gould, EW
影响因子：
4.6
作者：
Yang, Chen;Humphrey, Peter A.
通讯作者：
Humphrey, Peter A.
影响因子：
6.6
作者：
Brimo, Fadi;Schultz, Luciana;Epstein, Jonathan I.
通讯作者：
Epstein, Jonathan I.
影响因子：
2.8
作者：
Kronz, JD;Milord, R;Epstein, JI
通讯作者：
Epstein, JI
DOI：
10.1080/00365510701666031
发表时间：
2008-01-01
影响因子：
2.1
作者：
Trajman, A.;Luiz, R. R.
通讯作者：
Luiz, R. R.