Evaluation of an Artificial Intelligence System for Retinopathy of Prematurity Screening in Nepal and Mongolia.
Evaluation of an Artificial Intelligence System for Retinopathy of Prematurity Screening in Nepal and Mongolia.
复制标题
DOI：
10.1016/j.xops.2022.100165
复制
发表时间：
2022-12
影响因子：
--
通讯作者：
Chan, R. V. Paul
中科院分区：
文献类型：
--
作者：
Cole, Emily;Valikodath, Nita G.;Al-Khaled, Tala;Bajimaya, Sanyam;Sagun, K. C.;Chuluunbat, Tsengelmaa;Munkhuu, Bayalag;Jonas, Karyn E.;Chuluunkhuu, Chimgee;MacKeen, Leslie D.;Yap, Vivien;Hallak, Joelle;Ostmo, Susan;Wu, Wei-Chi;Coyner, Aaron S.;Singh, Praveer;Kalpathy-Cramer, Jayashree;Chiang, Michael F.;Campbell, J. Peter;Chan, R. V. Paul
评估深度学习（DL）算法在尼泊尔和蒙古早产儿视网膜病变（ROP）筛查中的性能。对前瞻性收集的临床数据进行回顾性分析。临床信息和眼底图像来自尼泊尔和蒙古的2个ROP筛查项目中的婴儿。使用尼泊尔的Forus 3 nethra neo（Forus Health）和RetCam Portable（Natus Medical，Inc.）在蒙古。使用ROP国际分类（ICROP）从病历中确定ROP的总体严重程度。使用参考标准诊断在每个图像中独立确定阳性疾病的存在。在RetCam的图像上训练ROP成像和信息学（i-ROP）DL算法，以分类疾病并分配1至9的血管严重程度评分（VSS）。阳性疾病或1型ROP的受试者工作特征曲线下面积和精确-召回曲线下面积以及VSS和ICROP疾病类别之间的关联。在这些数据集中，蒙古1型ROP的患病率（14.0%）高于尼泊尔（2.2%; P < 0.001）。在蒙古（RetCam图像），检查水平加疾病检测的受试者工作特征曲线下面积为0.968，精确度-召回率曲线下面积为0.823。在尼泊尔（Forus图像），这些值分别为0.999和0.993。ROPVSS与ICROP分级相关（P < 0.001）。在人口水平上，蒙古的VSS中位数（2.7;四分位距[IQR]，1.3-5.4]）高于尼泊尔（1.9; IQR，1.2-3.4; P < 0.001）。这些数据提供了初步证据，证明了i-ROP DL算法在尼泊尔和蒙古使用多相机系统进行新生儿ROP筛查的有效性，并可用于未来在低收入和中等收入国家临床实施基于人工智能的ROP筛查。
To evaluate the performance of a deep learning (DL) algorithm for retinopathy of prematurity (ROP) screening in Nepal and Mongolia. Retrospective analysis of prospectively collected clinical data. Clinical information and fundus images were obtained from infants in 2 ROP screening programs in Nepal and Mongolia. Fundus images were obtained using the Forus 3nethra neo (Forus Health) in Nepal and the RetCam Portable (Natus Medical, Inc.) in Mongolia. The overall severity of ROP was determined from the medical record using the International Classification of ROP (ICROP). The presence of plus disease was determined independently in each image using a reference standard diagnosis. The Imaging and Informatics for ROP (i-ROP) DL algorithm was trained on images from the RetCam to classify plus disease and to assign a vascular severity score (VSS) from 1 through 9. Area under the receiver operating characteristic curve and area under the precision-recall curve for the presence of plus disease or type 1 ROP and association between VSS and ICROP disease category. The prevalence of type 1 ROP was found to be higher in Mongolia (14.0%) than in Nepal (2.2%; P < 0.001) in these data sets. In Mongolia (RetCam images), the area under the receiver operating characteristic curve for examination-level plus disease detection was 0.968, and the area under the precision-recall curve was 0.823. In Nepal (Forus images), these values were 0.999 and 0.993, respectively. The ROP VSS was associated with ICROP classification in both datasets (P < 0.001). At the population level, the median VSS was found to be higher in Mongolia (2.7; interquartile range [IQR], 1.3–5.4]) as compared with Nepal (1.9; IQR, 1.2–3.4; P < 0.001). These data provide preliminary evidence of the effectiveness of the i-ROP DL algorithm for ROP screening in neonatal populations in Nepal and Mongolia using multiple camera systems and are useful for consideration in future clinical implementation of artificial intelligence–based ROP screening in low- and middle-income countries.
登录
查看更多内容
影响因子：
13.7
作者：
Campbell JP;Kim SJ;Brown JM;Ostmo S;Chan RVP;Kalpathy-Cramer J;Chiang MF;of the Imaging and Informatics in Retinopathy of Prematurity Consortium
通讯作者：
of the Imaging and Informatics in Retinopathy of Prematurity Consortium
影响因子：
1.8
作者：
Graham E Quinn;e-ROP Cooperative Group
通讯作者：
e-ROP Cooperative Group
影响因子：
13.7
作者：
Bellsmith, Kellyn N.;Brown, James;Campbell, J. Peter
通讯作者：
Campbell, J. Peter
影响因子：
13.7
作者：
Campbell, J. Peter;Ryan, Michael C.;Chiang, Michael F.
通讯作者：
Chiang, Michael F.
DOI：
10.1038/eye.2017.150
发表时间：
2018-01
期刊：
Eye (London, England)
影响因子：
--
作者：
Fleck BW;Williams C;Juszczak E;Cocker K;Stenson BJ;Darlow BA;Dai S;Gole GA;Quinn GE;Wallace DK;Ells A;Carden S;Butler L;Clark D;Elder J;Wilson C;Biswas S;Shafiq A;King A;Brocklehurst P;Fielder AR;BOOST II Retinal Image Digital Analysis (RIDA) Group
通讯作者：
BOOST II Retinal Image Digital Analysis (RIDA) Group