Department of Electronics and Communication Engineering, Arunachala College of Engineering for Women, Manavilai, India.
Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, India.
Technol Health Care. 2024;32(6):3829-3846. doi: 10.3233/THC-230310.
Segmentation of retinal fragments like blood vessels, Optic Disc (OD), and Optic Cup (OC) enables the early detection of different retinal pathologies like Diabetic Retinopathy (DR), Glaucoma, etc.
Accurate segmentation of OD remains challenging due to blurred boundaries, vessel occlusion, and other distractions and limitations. These days, deep learning is rapidly progressing in the segmentation of image pixels, and a number of network models have been proposed for end-to-end image segmentation. However, there are still certain limitations, such as limited ability to represent context, inadequate feature processing, limited receptive field, etc., which lead to the loss of local details and blurred boundaries.
A multi-dimensional dense attention network, or MDDA-Net, is proposed for pixel-wise segmentation of OD in retinal images in order to address the aforementioned issues and produce more thorough and accurate segmentation results. In order to acquire powerful contexts when faced with limited context representation capabilities, a dense attention block is recommended. A triple-attention (TA) block is introduced in order to better extract the relationship between pixels and obtain more comprehensive information, with the goal of addressing the insufficient feature processing. In the meantime, a multi-scale context fusion (MCF) is suggested for acquiring the multi-scale contexts through context improvement.
Specifically, we provide a thorough assessment of the suggested approach on three difficult datasets. In the MESSIDOR and ORIGA data sets, the suggested MDDA-NET approach obtains accuracy levels of 99.28% and 98.95%, respectively.
The experimental results show that the MDDA-Net can obtain better performance than state-of-the-art deep learning models under the same environmental conditions.
视网膜碎片（如血管、视盘（OD）和视杯（OC））的分割可实现对不同视网膜病变（如糖尿病视网膜病变（DR）、青光眼等）的早期检测。
由于边界模糊、血管闭塞和其他干扰以及限制，OD 的准确分割仍然具有挑战性。如今，深度学习在图像像素分割方面发展迅速，已经提出了许多用于端到端图像分割的网络模型。然而，仍然存在某些限制，例如表示上下文的能力有限、特征处理不足、感受野有限等，这导致局部细节丢失和边界模糊。
为了解决上述问题，并产生更全面和准确的分割结果，提出了一种多维密集注意力网络（MDDA-Net），用于对视网膜图像中的 OD 进行像素级分割。为了在面对有限的上下文表示能力时获取强大的上下文，建议使用密集注意力块。引入三重注意力（TA）块，以更好地提取像素之间的关系，并获取更全面的信息，从而解决特征处理不足的问题。同时，建议使用多尺度上下文融合（MCF）通过上下文改进获取多尺度上下文。
具体来说，我们在三个困难数据集上对所提出的方法进行了全面评估。在 MESSIDOR 和 ORIGA 数据集上，所提出的 MDDA-Net 方法的准确率分别达到 99.28%和 98.95%。
实验结果表明，在相同的环境条件下，MDDA-Net 可以比最先进的深度学习模型获得更好的性能。
