Department of Electronics and Communication Engineering, Udaya School of Engineering, Vellamodi, India.
Department of Electronics and Communication Engineering, C.S.I. Institute of Technology, Thovalai, India.
Med Biol Eng Comput. 2023 Aug;61(8):2091-2113. doi: 10.1007/s11517-023-02860-9. Epub 2023 Jun 20.
Long-term exposure to diabetes mellitus leads to the formation of diabetic retinopathy (DR), which can cause vision loss in working-age adults. Early stage diagnosis of DR is highly essential for preventing vision loss and preserving vision in people with diabetes. The motivation behind the severity grade classification of DR is to develop an automated system that can assist ophthalmologists and healthcare professionals in the diagnosis and management of DR. However, existing methods suffer from variability in image quality, similar structures of the normal and lesion regions, high dimensional features, variability in disease manifestations, small datasets, high training loss, model complexity, and overfitting, which leads to high misclassification errors in the severity grading system. Hence, there is a need to develop an automated system using improved deep learning techniques to provide a reliable and consistent grading of DR severity with high classification accuracy using fundus images. To solve these issues, we proposes a Deformable Ladder Bi attention U-shaped encoder-decoder network and Deep Adaptive Convolutional Neural Network (DLBUnet-DACNN) for accurate severity classification of DR. The DLBUnet performs lesion segmentation that can be divided into three parts: the encoder, the central processing module and the decoder. In the encoder part, deformable convolution is used instead of convolution to learn different shapes of the lesion by understanding the offset location. Afterwards, Ladder Atrous Spatial Pyramidal Pooling (LASPP) using variable dilation rates is introduced in the central processing module. LASPP enhance the tiny lesion features and variable dilation rates avoid gridding effects and can learn better global context information. Then the decoder part uses a bi-attention layer contains spatial and channel attention, which can learn contour and edges of the lesion accurately. Finally, the severity of DR is classified using a DACNN by extracting the discriminative features from the segmentation results. Experiments are conducted on the Messidor-2, Kaggle, and Messidor datasets. Our proposed method DLBUnet-DACNN achieves better results in terms of accuracy of 98.2, recall of 0.987, kappa coefficient of 0.993, precision of 0.98, F1-score of 0.981, Matthews Correlation Coefficient (MCC) of 0.93 and Classification Success Index (CSI) of 0.96 when compared to existing methods.
长期暴露于糖尿病会导致糖尿病视网膜病变（DR）的形成，从而导致工作年龄段成年人视力丧失。早期诊断 DR 对于预防视力丧失和保护糖尿病患者的视力至关重要。DR 严重程度分级分类的动机是开发一种能够协助眼科医生和医疗保健专业人员诊断和管理 DR 的自动化系统。然而，现有的方法存在图像质量变化、正常和病变区域结构相似、高维特征、疾病表现变化、小数据集、高训练损失、模型复杂性和过拟合等问题，这导致严重程度分级系统中的分类错误率很高。因此，需要开发一种使用改进的深度学习技术的自动化系统，以便使用眼底图像提供可靠且一致的 DR 严重程度分级，并具有高分类准确性。为了解决这些问题，我们提出了一种可变形梯级双注意 U 形编码器-解码器网络和深度自适应卷积神经网络（DLBUnet-DACNN），用于准确分级 DR 的严重程度。DLBUnet 执行病变分割，可分为三个部分：编码器、中央处理模块和解码器。在编码器部分，使用可变形卷积代替卷积，通过了解偏移位置来学习病变的不同形状。然后，在中央处理模块中引入具有可变扩张率的梯级空洞空间金字塔池化（LASPP）。LASPP 增强微小病变特征，可变扩张率避免网格效应，并能更好地学习全局上下文信息。然后，解码器部分使用包含空间和通道注意力的双注意层，可准确学习病变的轮廓和边缘。最后，通过从分割结果中提取鉴别特征，使用 DACNN 对 DR 的严重程度进行分类。在 Messidor-2、Kaggle 和 Messidor 数据集上进行了实验。与现有方法相比，我们提出的方法 DLBUnet-DACNN 在准确性为 98.2、召回率为 0.987、kappa 系数为 0.993、精度为 0.98、F1 分数为 0.981、马修斯相关系数（MCC）为 0.93 和分类成功指数（CSI）为 0.96 方面取得了更好的结果。
