Chen Qingyu, Peng Yifan, Keenan Tiarnan, Dharssi Shazia, Agro N Elvira, Wong Wai T, Chew Emily Y, Lu Zhiyong
National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States.
National Eye Institute (NEI), National Institutes of Health (NIH), Bethesda, Maryland, United States.
AMIA Jt Summits Transl Sci Proc. 2019 May 6;2019:505-514. eCollection 2019.
Age-related Macular Degeneration (AMD) is a leading cause of blindness. Although the Age-Related Eye Disease Study group previously developed a 9-step AMD severity scale for manual classification of AMD severity from color fundus images, manual grading of images is time-consuming and expensive. Built on our previous work DeepSeeNet, we developed a novel deep learning model for automated classification of images into the 9-step scale. Instead of predicting the 9-step score directly, our approach simulates the reading center grading process. It first detects four AMD characteristics (drusen area, geographic atrophy, increased pigment, and depigmentation), then combines these to derive the overall 9-step score. Importantly, we applied multi-task learning techniques, which allowed us to train classification of the four characteristics in parallel, share representation, and prevent overfitting. Evaluation on two image datasets showed that the accuracy of the model exceeded the current state-of-the-art model by > 10%. Availability: https://github.com/ncbi-nlp/DeepSeeNet.
年龄相关性黄斑变性（AMD）是导致失明的主要原因。尽管年龄相关性眼病研究组先前制定了一个9级AMD严重程度量表，用于从彩色眼底图像中对手动分类AMD严重程度，但图像的手动分级既耗时又昂贵。基于我们之前的工作DeepSeeNet，我们开发了一种新颖的深度学习模型，用于将图像自动分类为9级量表。我们的方法不是直接预测9级评分，而是模拟阅读中心的分级过程。它首先检测四个AMD特征（玻璃膜疣面积、地图状萎缩、色素增加和色素脱失），然后将这些特征结合起来得出总体9级评分。重要的是，我们应用了多任务学习技术，这使我们能够并行训练四个特征的分类、共享表示并防止过拟合。在两个图像数据集上的评估表明，该模型的准确率比当前的最先进模型高出10%以上。可获取性：https://github.com/ncbi-nlp/DeepSeeNet 。
