Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images
Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images
复制标题
DOI：
10.3390/app10113833
复制
发表时间：
2020-06-01
影响因子：
2.7
通讯作者：
Alajlan, Naif
中科院分区：
文献类型：
--
作者：
Almubarak, Haidar;Bazi, Yakoub;Alajlan, Naif
在本文中，我们提出了一种方法来定位视神经乳头和分割视盘/杯视网膜眼底图像。该方法基于简单的两阶段Mask-RCNN，与代表文献中最先进技术的复杂方法相比。在第一阶段，我们检测并裁剪视神经乳头周围，然后将裁剪后的图像作为第二阶段的输入。第二阶段网络使用加权损失进行训练以产生最终分割。为了进一步改善第一阶段的检测，我们提出了一种新的微调策略，将第一阶段的裁剪输出与原始训练图像相结合，为区域建议网络锚使用不同的尺度来训练新的检测网络。我们在视网膜眼底图像青光眼分析（REFUGE），Magrabi和MESSIDOR数据集上评估了该方法。我们使用REFUGE训练子集来训练模型。我们的方法实现了0.0430平均绝对误差的垂直杯盘比（MAE vCDR）的REFUGE测试集相比，0.0414使用复杂的和多个集成网络的方法。使用所提出的方法训练的模型可以很好地转移到REFUGE之外的数据集，在MESSIDOR和Magrabi数据集上分别实现了0.0785和0.077的MAE vCDR，而无需重新训练。在检测精度方面，与文献中报告的检测率相比，所提出的新微调策略将MESSIDOR数据集的检测率从96.7%提高到98.04%，将Magrabi数据集的检测率从93.6%提高到100%。
In this paper, we propose a method for localizing the optic nerve head and segmenting the optic disc/cup in retinal fundus images. The approach is based on a simple two-stage Mask-RCNN compared to sophisticated methods that represent the state-of-the-art in the literature. In the first stage, we detect and crop around the optic nerve head then feed the cropped image as input for the second stage. The second stage network is trained using a weighted loss to produce the final segmentation. To further improve the detection in the first stage, we propose a new fine-tuning strategy by combining the cropping output of the first stage with the original training image to train a new detection network using different scales for the region proposal network anchors. We evaluate the method on Retinal Fundus Images for Glaucoma Analysis (REFUGE), Magrabi, and MESSIDOR datasets. We used the REFUGE training subset to train the models in the proposed method. Our method achieved 0.0430 mean absolute error in the vertical cup-to-disc ratio (MAE vCDR) on the REFUGE test set compared to 0.0414 obtained using complex and multiple ensemble networks methods. The models trained with the proposed method transfer well to datasets outside REFUGE, achieving a MAE vCDR of 0.0785 and 0.077 on MESSIDOR and Magrabi datasets, respectively, without being retrained. In terms of detection accuracy, the proposed new fine-tuning strategy improved the detection rate from 96.7% to 98.04% on MESSIDOR and from 93.6% to 100% on Magrabi datasets compared to the reported detection rates in the literature.