Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment.

Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment.
复制标题

深度学习(一种机器学习技术)的准确性,使用超宽眼底眼镜检查来检测Rhegmatogen opental视网膜脱离。

DOI:
10.1038/s41598-017-09891-x
复制
发表时间:
2017-08-25
期刊:
影响因子:
4.6
通讯作者:
Ishitobi N
Ishitobi N
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Ohsugi H;Tabuchi H;Enno H;Ishitobi N

文献摘要

参考文献

被引文献

相似文献

孔源性视网膜脱离(RRD)是一种可能导致失明的严重疾病;然而,通过及时和适当的治疗,它是可以治愈的。因此,RRD的早期诊断和治疗至关重要。在本研究中,我们应用深度学习(一种机器学习技术)使用超广角眼底图像来检测 RRD,并研究其性能。本研究总共使用了来自 407 名 RRD 患者的 411 幅图像(329 幅用于训练,82 幅用于分级)和来自 238 名非 RRD 患者的 420 幅图像(336 幅用于训练,84 幅用于分级)。深度学习模型表现出 97.6% 的高灵敏度 [95% CI, 94.2–100%] 和 96.5% 的高特异性 (95% CI, 90.2–100%),曲线下面积为 0.988 (95% CI, 0.981–0.995)。该模型可以通过使用超广角眼底检眼镜准确诊断 RRD,从而改善没有眼科诊所的偏远地区的医疗保健。 RRD 的早期诊断可以预防失明。
Rhegmatogenous retinal detachment (RRD) is a serious condition that can lead to blindness; however, it is highly treatable with timely and appropriate treatment. Thus, early diagnosis and treatment of RRD is crucial. In this study, we applied deep learning, a machine-learning technology, to detect RRD using ultra–wide-field fundus images and investigated its performance. In total, 411 images (329 for training and 82 for grading) from 407 RRD patients and 420 images (336 for training and 84 for grading) from 238 non-RRD patients were used in this study. The deep learning model demonstrated a high sensitivity of 97.6% [95% confidence interval (CI), 94.2–100%] and a high specificity of 96.5% (95% CI, 90.2–100%), and the area under the curve was 0.988 (95% CI, 0.981–0.995). This model can improve medical care in remote areas where eye clinics are not available by using ultra–wide-field fundus ophthalmoscopy for the accurate diagnosis of RRD. Early diagnosis of RRD can prevent blindness.
DOI: 10.1007/s11263-015-0816-y
发表时间: 2015-12-01
影响因子: 19.5
作者:
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者: Fei-Fei, Li
DOI: 10.1007/s00417-011-1619-7
发表时间: 2011-08-01
影响因子: 2.7
作者:
Heussen, Nicole;Feltgen, Nicolas;Heimann, Heinrich
通讯作者: Heimann, Heinrich
DOI: 10.1038/srep38897
发表时间: 2016-12-12
期刊: Scientific reports
影响因子: 4.6
作者:
Pinaya WH;Gadelha A;Doyle OM;Noto C;Zugman A;Cordeiro Q;Jackowski AP;Bressan RA;Sato JR
通讯作者: Sato JR
DOI: 10.1001/jama.2016.17216
发表时间: 2016-12-13
影响因子: 120.7
作者:
Gulshan, Varun;Peng, Lily;Webster, R.
通讯作者: Webster, R.
DOI: 10.1016/s0021-5155(00)00377-4
发表时间: 2001-03-01
影响因子: 2.4
作者:
Miki, D;Hida, T;Hirakata, A
通讯作者: Hirakata, A