Evaluation of a Deep Learning-Derived Quantitative Retinopathy of Prematurity Severity Scale.
Evaluation of a Deep Learning-Derived Quantitative Retinopathy of Prematurity Severity Scale.
复制标题
DOI：
10.1016/j.ophtha.2020.10.025
复制
发表时间：
2021-07
期刊：
影响因子：
13.7
通讯作者：
of the Imaging and Informatics in Retinopathy of Prematurity Consortium
中科院分区：
文献类型：
--
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
通过评估早产儿视网膜病变 (ROP) 与临床 ROP 诊断的相关性以及测量临床医生应用新量表的一致性，评估定量深度学习衍生的血管严重程度评分在早产儿视网膜病变 (ROP) 中的临床效用。使用两种为血管严重程度分配定量尺度的方法分析现有的后极眼底图像数据库和相应的检眼镜检查。图像来自 ROP 影像与信息学联盟中患者的临床检查。 4 名眼科医生和 1 名研究协调员按照 1-9 级评估血管严重程度。使用深度学习算法将定量血管严重程度评分 (1-9) 应用于每张图像。开发了包含 499 张图像的数据库，用于评估观察者间的一致性。使用多元线性回归评估深度学习衍生的血管严重程度评分的分布，以及第 3 阶段区域（I、II、III）、阶段（0、1、2、3）和范围（<3、3-6、>6 个时钟小时）的临床评估。 1-9 血管严重程度量表观察者间一致性的加权 kappa 和 Pearson 相关系数。对于深度学习分析，总共分析了 6344 项临床检查。较高的深度学习衍生的血管严重程度评分与更多的后部疾病、更高的疾病分期和更高的 3 期疾病程度相关（全部 P<0.001）。对于给定的 ROP 阶段，I 区的血管严重程度评分高于 II 区或 III 区 (P<.001)。对于第 3 阶段给定的时钟小时数，I 区的严重性评分高于 II 区（I 区 P=0.03，II 区 P<0.001）。多变量回归发现区域、阶段和范围均与严重程度评分独立相关（全部 P<0.001）。对于观察者间一致性，使用 1-9 血管严重程度量表时，平均（±标准差 [SD]）加权 kappa 为 0.67 (±0.06)，皮尔逊相关系数 (±SD) 为 0.88 (±.04)。 ROP 的血管严重程度量表似乎适合临床采用，与区域、分期、第 3 期范围以及附加疾病相对应，并有助于使用深度学习等客观技术来提高 ROP 诊断的一致性。
To evaluate the clinical utility of a quantitative deep-learning derived vascular severity score for retinopathy of prematurity (ROP) by assessing its correlation with clinical ROP diagnosis and by measuring clinician agreement in applying a novel scale. Analysis of existing database of posterior pole fundus images and corresponding ophthalmoscopic examinations using two methods of assigning a quantitative scale to vascular severity. Images were from clinical exams of patients in the Imaging & Informatics in ROP consortium. 4 ophthalmologists and 1 study coordinator evaluated vascular severity on a 1-9 scale. A quantitative vascular severity score (1-9) was applied to each image using a deep learning algorithm. A database of 499 images was developed for assessment of inter-observer agreement. Distribution of deep learning derived vascular severity scores with the clinical assessment of zone (I,II,III), stage (0,1,2,3) and extent (<3, 3-6, >6 clock hours) of stage 3 evaluated using multivariable linear regression. Weighted kappa and Pearson correlation coefficients for inter-observer agreement on 1-9 vascular severity scale. For deep learning analysis, a total of 6344 clinical examinations were analyzed. A higher deep learning derived vascular severity score was associated with more posterior disease, higher disease stage, and higher extent of stage 3 disease (P<.001 for all). For a given ROP stage, the vascular severity score was higher in zone I than zone II or III (P<.001). For a given number of clock hours of stage 3, the severity score was higher in zone I than zone II (P=.03 in zone I and P<.001 in zone II). Multivariable regression found zone, stage, and extent were all independently associated with the severity score (P<.001 for all). For inter-observer agreement, mean (±Standard Deviation [SD]) weighted kappa was 0.67 (±0.06) and Pearson Correlation coefficient (±SD) was 0.88 (±.04) on the use of a 1-9 vascular severity scale. A vascular severity scale for ROP appears feasible for clinical adoption, corresponds with zone, stage, extent of stage 3, and plus disease, and facilitates the use of objective technology such as deep learning to improve consistency of ROP diagnosis.
登录
查看更多内容
影响因子：
4.1
作者：
Redd, Travis K.;Campbell, John Peter;Chiang, Michael F.
通讯作者：
Chiang, Michael F.
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.
影响因子：
4.2
作者：
Gupta MP;Chan RVP;Anzures R;Ostmo S;Jonas K;Chiang MF;Imaging & Informatics in ROP Research Consortium
通讯作者：
Imaging & Informatics in ROP Research Consortium
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