Artificial Intelligence for Automated Overlay of Fundus Camera and Scanning Laser Ophthalmoscope Images.
Artificial Intelligence for Automated Overlay of Fundus Camera and Scanning Laser Ophthalmoscope Images.
复制标题
DOI：
10.1167/tvst.9.2.56
复制
发表时间：
2020-10
影响因子：
3
通讯作者：
Freeman WR
中科院分区：
文献类型：
--
作者：
Cavichini M;An C;Bartsch DG;Jhingan M;Amador-Patarroyo MJ;Long CP;Zhang J;Wang Y;Chan AX;Madala S;Nguyen T;Freeman WR
本研究的目的是评估使用数学变形和人工智能（AI）对齐在不同平台上拍摄的两种类型的视网膜图像的能力;彩色眼底（CF）照片和红外扫描激光检眼镜（IR SLO）图像。我们收集了109对匹配的CF和IR SLO图像。开发了一种利用两个独立网络的AI算法。使用风格传递网络（STYLE）来分割血管结构。使用配准网络将分割的图像与每个图像对齐。这两个网络都没有使用地面实况数据集。传统的图像变形算法被用作控制。软件将图像对显示为由交替子图像组成的5 × 5棋盘格网格。该技术允许人类观察者和5名蒙面分级者在每个图像的25个字段中通过AI和常规扭曲评估血管对准确定。我们的新AI方法在生成血管对齐方面上级传统的扭曲，这是由蒙面的人类分级者判断的（P < 0.0001）。采用AI方法后，平均好/优匹配数从90.5%提高到94.4%。AI允许比传统的数学变形更准确地覆盖CF和IR SLO图像。这是开发AI的第一步，该AI可以通过利用血管标志来覆盖所有类型的眼底图像。能够对齐和叠加来自多个仪器和制造商的成像数据将允许更好地分析这种复杂的数据，帮助理解疾病和预测治疗。
The purpose of this study was to evaluate the ability to align two types of retinal images taken on different platforms; color fundus (CF) photographs and infrared scanning laser ophthalmoscope (IR SLO) images using mathematical warping and artificial intelligence (AI). We collected 109 matched pairs of CF and IR SLO images. An AI algorithm utilizing two separate networks was developed. A style transfer network (STN) was used to segment vessel structures. A registration network was used to align the segmented images to each. Neither network used a ground truth dataset. A conventional image warping algorithm was used as a control. Software displayed image pairs as a 5 × 5 checkerboard grid composed of alternating subimages. This technique permitted vessel alignment determination by human observers and 5 masked graders evaluated alignment by the AI and conventional warping in 25 fields for each image. Our new AI method was superior to conventional warping at generating vessel alignment as judged by masked human graders (P < 0.0001). The average number of good/excellent matches increased from 90.5% to 94.4% with AI method. AI permitted a more accurate overlay of CF and IR SLO images than conventional mathematical warping. This is a first step toward developing an AI that could allow overlay of all types of fundus images by utilizing vascular landmarks. The ability to align and overlay imaging data from multiple instruments and manufacturers will permit better analysis of this complex data helping understand disease and predict treatment.
登录
查看更多内容
影响因子：
--
作者：
Bandello F;Sacconi R;Querques L;Corbelli E;Cicinelli MV;Querques G
通讯作者：
Querques G
影响因子：
10.6
作者：
Staal, J;Abràmoff, MD;van Ginneken, B
通讯作者：
van Ginneken, B
影响因子：
13.7
作者：
Fleckenstein, Monika;Mitchell, Paul;Ferrara, Daniela
通讯作者：
Ferrara, Daniela
影响因子：
0.8
作者：
Vidinova, C. N.;Gouguchkova, P. T.;Vidinov, K. N.
通讯作者：
Vidinov, K. N.
DOI：
10.1111/opo.12283
发表时间：
2016-05
期刊：
Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians (Optometrists)
影响因子：
--
作者：
Ly A;Nivison-Smith L;Assaad N;Kalloniatis M
通讯作者：
Kalloniatis M