英国DeepMind公司Jeffrey De Fauw、Joseph R. Ledsam和英国Moorfields眼科医院、UCL眼科研究所Pearse A. Keane课题组合作取得一项新突破。他们的最新研究利用深度学习预测了与年龄相关的湿性黄斑变性（exAMD）转换。 相关论文发表在2020年5月18日出版的《自然-医学》杂志上。
在一只眼睛确诊为exAMD的患者中，研究人员利用人工智能（AI）系统来预测第二只眼睛发展为exAMD的时间。通过基于三维（3D）光学相干断层扫描图像和相应自动组织图相结合的模型，该系统预测了在临床可行的6个月时间范围内第二只研究可转换为exAMD，在55%准确性时实现按体积扫描的80％灵敏度，在34％准确性时灵敏度为90％。这种性能水平在78％准确性时对应灵敏度为41％的单眼真实阳性，以及56％准确性灵敏度为17％的单眼假阳性。
此外，研究人员发现自动组织分割可以识别高风险亚组转换之前的解剖学变化。该AI系统克服了专家预测时观察者之间的巨大差异，该系统比六分之五的专家表现好，并且展示了使用AI预测疾病进展的潜力。
研究人员表示，发展为与年龄相关的渗出型“湿性”黄斑变性是导致视力下降的主要原因。
附：英文原文
Title: Predicting conversion to wet age-related macular degeneration using deep learning
Author: Jason Yim, Reena Chopra, Terry Spitz, Jim Winkens, Annette Obika, Christopher Kelly, Harry Askham, Marko Lukic, Josef Huemer, Katrin Fasler, Gabriella Moraes, Clemens Meyer, Marc Wilson, Jonathan Dixon, Cian Hughes, Geraint Rees, Peng T. Khaw, Alan Karthikesalingam, Dominic King, Demis Hassabis, Mustafa Suleyman, Trevor Back, Joseph R. Ledsam, Pearse A. Keane, Jeffrey De Fauw
Issue&Volume: 2020-05-18
Abstract: Progression to exudative ‘wet’ age-related macular degeneration (exAMD) is a major cause of visual deterioration. In patients diagnosed with exAMD in one eye, we introduce an artificial intelligence (AI) system to predict progression to exAMD in the second eye. By combining models based on three-dimensional (3D) optical coherence tomography images and corresponding automatic tissue maps, our system predicts conversion to exAMD within a clinically actionable 6-month time window, achieving a per-volumetric-scan sensitivity of 80% at 55% specificity, and 34% sensitivity at 90% specificity. This level of performance corresponds to true positives in 78% and 41% of individual eyes, and false positives in 56% and 17% of individual eyes at the high sensitivity and high specificity points, respectively. Moreover, we show that automatic tissue segmentation can identify anatomical changes before conversion and high-risk subgroups. This AI system overcomes substantial interobserver variability in expert predictions, performing better than five out of six experts, and demonstrates the potential of using AI to predict disease progression.
DOI: 10.1038/s41591-020-0867-7
Source: https://www.nature.com/articles/s41591-020-0867-7
Nature Medicine：《自然—医学》，创刊于1995年。隶属于施普林格·自然出版集团，最新IF：87.241
官方网址：https://www.nature.com/nm/
投稿链接：https://mts-nmed.nature.com/cgi-bin/main.plex
本期文章：《自然—医学》：Online/在线发表
