Mishra Zubin, Wang Ziyuan, Sadda SriniVas R, Hu Zhihong
Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USA.
School of Medicine, Case Western Reserve University, Cleveland, OH 44106, USA.
Appl Sci (Basel). 2023 Jul 2;13(14). doi: 10.3390/app13148555. Epub 2023 Jul 24.
Stargardt disease is the most common form of juvenile-onset macular dystrophy. Spectral-domain optical coherence tomography (SD-OCT) imaging provides an opportunity to directly measure changes to retinal layers due to Stargardt atrophy. Generally, atrophy segmentation and prediction can be conducted using mean intensity feature maps generated from the relevant retinal layers. In this paper, we report an approach using advanced OCT-derived features to augment and enhance data beyond the commonly used mean intensity features for enhanced prediction of Stargardt atrophy with an ensemble deep learning neural network. With all the relevant retinal layers, this neural network architecture achieves a median Dice coefficient of 0.830 for six-month predictions and 0.828 for twelve-month predictions, showing a significant improvement over a neural network using only mean intensity, which achieved Dice coefficients of 0.744 and 0.762 for six-month and twelve-month predictions, respectively. When using feature maps generated from different layers of the retina, significant differences in performance were observed. This study shows promising results for using multiple OCT-derived features beyond intensity for assessing the prognosis of Stargardt disease and quantifying the rate of progression.
斯塔加特病是青少年黄斑营养不良最常见的形式。光谱域光学相干断层扫描（SD-OCT）成像为直接测量斯塔加特萎缩引起的视网膜层变化提供了机会。一般来说，萎缩分割和预测可以使用从相关视网膜层生成的平均强度特征图来进行。在本文中，我们报告了一种方法，即使用先进的OCT衍生特征来增强和扩充数据，超越常用的平均强度特征，以通过集成深度学习神经网络增强对斯塔加特萎缩的预测。利用所有相关视网膜层，该神经网络架构在六个月预测中的中位骰子系数为0.830，在十二个月预测中的中位骰子系数为0.828，与仅使用平均强度的神经网络相比有显著改进，后者在六个月和十二个月预测中的骰子系数分别为0.744和0.762。当使用从视网膜不同层生成的特征图时，观察到性能存在显著差异。这项研究显示了使用强度以外的多个OCT衍生特征来评估斯塔加特病预后和量化进展速率的前景良好的结果。
