Heisler Morgan, Ju Myeong Jin, Bhalla Mahadev, Schuck Nathan, Athwal Arman, Navajas Eduardo V, Beg Mirza Faisal, Sarunic Marinko V
Simon Fraser University, Department of Engineering Science, 8888 University Drive, Burnaby, BC, V5A 1S6, Canada.
University of British Columbia, Faculty of Medicine, 317 - 2194 Health Sciences Mall, Vancouver, BC, V6T 1Z3, Canada.
Biomed Opt Express. 2018 Oct 10;9(11):5353-5367. doi: 10.1364/BOE.9.005353. eCollection 2018 Nov 1.
Automated measurements of the human cone mosaic requires the identification of individual cone photoreceptors. The current gold standard, manual labeling, is a tedious process and can not be done in a clinically useful timeframe. As such, we present an automated algorithm for identifying cone photoreceptors in adaptive optics optical coherence tomography (AO-OCT) images. Our approach fine-tunes a pre-trained convolutional neural network originally trained on AO scanning laser ophthalmoscope (AO-SLO) images, to work on previously unseen data from a different imaging modality. On average, the automated method correctly identified 94% of manually labeled cones when compared to manual raters, from twenty different AO-OCT images acquired from five normal subjects. Voronoi analysis confirmed the general hexagonal-packing structure of the cone mosaic as well as the general cone density variability across portions of the retina. The consistency of our measurements demonstrates the high reliability and practical utility of having an automated solution to this problem.
对人锥细胞镶嵌的自动测量需要识别单个锥光感受器。当前的金标准——手动标记，是一个繁琐的过程，且无法在临床可用的时间范围内完成。因此，我们提出了一种用于在自适应光学光学相干断层扫描（AO-OCT）图像中识别锥光感受器的自动算法。我们的方法对最初在AO扫描激光检眼镜（AO-SLO）图像上训练的预训练卷积神经网络进行微调，以处理来自不同成像模态的未见数据。与手动评分者相比，从五名正常受试者获取的二十张不同AO-OCT图像中，该自动方法平均能正确识别94%的手动标记锥细胞。Voronoi分析证实了锥细胞镶嵌的一般六边形排列结构以及视网膜各部分锥细胞密度的一般变化。我们测量结果的一致性证明了针对此问题的自动解决方案具有高可靠性和实际效用。
