基于多尺度残差卷积神经网络的视杯视盘联合分割

Joint optic disc and cup segmentation based on residual multi-scale fully convolutional neural network

青光眼是不可逆性失明的首要原因,早期症状不明显,容易被忽视,因此青光眼早期筛查尤为重要。杯盘比是临床上用于青光眼筛查的重要指标,所以精准分割视杯视盘是计算杯盘比的关键。本文提出了一种基于全卷积多尺度残差神经网络的视杯视盘分割方法。首先,对眼底图像进行对比度增强,并引入极坐标变换。随后,构造W-Net作为主体网络,用带残差多尺度全卷积模块来替代标准卷积单元,输入端口加入图像金字塔来构造多尺度输入,侧输出层作为早期的分类器生成局部预测输出。最后,提出了一种新的多标签损失函数来指导网络分割。实验采用REFUGE数据集验证,最终视杯、视盘分割的平均交并比分别为0.9040、0.9553,重叠误差分别为0.1780、0.0665。结果表明,该方法不仅实现了视杯视盘联合分割,而且有效提高了其分割精度。该方法将有助于大规模青光眼早期筛查的推广。

Glaucoma is the leading cause of irreversible blindness,but its early symptoms are not obvious and are easily overlooked,so early screening for glaucoma is particularly important.The cup to disc ratio is an important indicator for clinical glaucoma screening,and accurate segmentation of the optic cup and disc is the key to calculating the cup to disc ratio.In this paper,a full convolutional neural network with residual multi-scale convolution module was proposed for the optic cup and disc segmentation.First,the fundus image was contrast enhanced and polar transformation was introduced.Subsequently,W-Net was used as the backbone network,which replaced the standard convolution unit with the residual multi-scale full convolution module,the input port was added to the image pyramid to construct the multiscale input,and the side output layer was used as the early classifier to generate the local prediction output.Finally,a new multi-tag loss function was proposed to guide network segmentation.The mean intersection over union of the optic cup and disc segmentation in the REFUGE dataset was 0.9040 and 0.9553 respectively,and the overlapping error was 0.1780 and 0.0665 respectively.The results show that this method not only realizes the joint segmentation of cup and disc,but also improves the segmentation accuracy effectively,which could be helpful for the promotion of large-scale early glaucoma screening.