Kande Giri Babu, Nalluri Madhusudana Rao, Manikandan R, Cho Jaehyuk, Veerappampalayam Easwaramoorthy Sathishkumar
Vasireddy Venkatadri Institute of Technology, Nambur, 522508, India.
School of Computing, Amrita Vishwa Vidyapeetham, Amaravati, 522503, India.
Sci Rep. 2025 Jan 27;15(1):3438. doi: 10.1038/s41598-024-84255-w.
Precise segmentation of retinal vasculature is crucial for the early detection, diagnosis, and treatment of vision-threatening ailments. However, this task is challenging due to limited contextual information, variations in vessel thicknesses, the complexity of vessel structures, and the potential for confusion with lesions. In this paper, we introduce a novel approach, the MSMA Net model, which overcomes these challenges by replacing traditional convolution blocks and skip connections with an improved multi-scale squeeze and excitation block (MSSE Block) and Bottleneck residual paths (B-Res paths) with spatial attention blocks (SAB). Our experimental findings on publicly available datasets of fundus images, specifically DRIVE, STARE, CHASE_DB1, HRF and DR HAGIS consistently demonstrate that our approach outperforms other segmentation techniques, achieving higher accuracy, sensitivity, Dice score, and area under the receiver operator characteristic (AUC) in the segmentation of blood vessels with different thicknesses, even in situations involving diverse contextual information, the presence of coexisting lesions, and intricate vessel morphologies.
视网膜血管的精确分割对于威胁视力疾病的早期检测、诊断和治疗至关重要。然而，由于上下文信息有限、血管厚度变化、血管结构复杂以及与病变混淆的可能性，这项任务具有挑战性。在本文中，我们介绍了一种新颖的方法，即MSMA Net模型，该模型通过用改进的多尺度挤压与激励块（MSSE块）替换传统卷积块和跳跃连接，并使用带有空间注意力块（SAB）的瓶颈残差路径（B-Res路径）来克服这些挑战。我们在公开可用的眼底图像数据集（特别是DRIVE、STARE、CHASE_DB1、HRF和DR HAGIS）上的实验结果一致表明，我们的方法优于其他分割技术，在不同厚度血管的分割中，即使在涉及不同上下文信息、存在共存病变和复杂血管形态的情况下，也能实现更高的准确率、灵敏度、Dice分数和受试者工作特征曲线下面积（AUC）。
