谷歌健康人工智能實現(xiàn)對乳腺癌的篩查
谷歌健康Shravya Shetty、Daniel Tse、Scott Mayer McKinney等研究人員建立了能夠?qū)θ橄侔┻M行篩查的人工智能系統(tǒng)。2020年1月1日，國際知名學術期刊《自然》在線發(fā)表了這一成果。
研究人員提出了一種人工智能（AI）系統(tǒng)，該系統(tǒng)能夠在乳腺癌預測方面超越人類專家。為了評估其在臨床環(huán)境中的性能，研究人員選擇了來自英國的大型代表性數(shù)據(jù)集和來自美國的大型豐富數(shù)據(jù)集。研究人員發(fā)現(xiàn)假陽性相對值降低了5.7％和1.2％（美國和英國），假陰性相對值降低了9.4％和2.7％。研究人員提供了可將該系統(tǒng)從英國推廣到美國的證據(jù)。在對六位放射科醫(yī)生的獨立研究中，人工智能系統(tǒng)的表現(xiàn)優(yōu)于所有人類專家：人工智能系統(tǒng)在接收器工作特性曲線下的面積（AUC-ROC）比一般放射線醫(yī)師的AUC-ROC相對幅度大了11.5％。研究人員進行了模擬，其中AI系統(tǒng)參與了在英國使用的雙重判斷過程，結(jié)果發(fā)現(xiàn)AI系統(tǒng)保持了不遜色的性能并將第二重判斷的工作量減少了88％。AI系統(tǒng)的強大評估為臨床試驗鋪平了道路，從而可提高乳腺癌篩查的準確性和效率。
據(jù)了解，乳腺鉬靶篩查的目的是在疾病較早的階段識別乳腺癌，從而更成功地進行治療。盡管全世界都存在篩查程序，但乳房X光照片的判斷存在較高的假陽性和假陰性。
附：英文原文
Title: International evaluation of an AI system for breast cancer screening
Author: Scott Mayer McKinney, Marcin Sieniek, Varun Godbole, Jonathan Godwin, Natasha Antropova, Hutan Ashrafian, Trevor Back, Mary Chesus, Greg C. Corrado, Ara Darzi, Mozziyar Etemadi, Florencia Garcia-Vicente, Fiona J. Gilbert, Mark Halling-Brown, Demis Hassabis, Sunny Jansen, Alan Karthikesalingam, Christopher J. Kelly, Dominic King, Joseph R. Ledsam, David Melnick, Hormuz Mostofi, Lily Peng, Joshua Jay Reicher, Bernardino Romera-Paredes, Richard Sidebottom, Mustafa Suleyman, Daniel Tse, Kenneth C. Young, Jeffrey De Fauw, Shravya Shetty
Issue&Volume: 2020-01-01
Abstract: Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.
DOI: 10.1038/s41586-019-1799-6
Source: https://www.nature.com/articles/s41586-019-1799-6
聲明：本文版權歸原作者所有，轉(zhuǎn)載文章僅為傳播更多信息，如作者信息標記有誤，或侵犯您的版權，請聯(lián)系我們，我們將在及時修改或刪除內(nèi)容，聯(lián)系郵箱：marketing@360worldcare.com
