针对OCTA血管分割中细节丢失问题，提出LSENet增强局部特征表达。
Gaze into the Details: Locality-Sensitive Enhancement for OCTA Retinal Vessel Segmentation
- 用分块注意力替代跳连，捕捉局部血管细节
- 多尺度融合提升特征丰富度，减少断点
- 大核卷积与层级精修，适合临床高精度需求
现有OCTA血管分割方法多基于U-Net架构，但仅关注整体表征，难以应对OCTA图像中特有的低对比度问题，导致血管断裂与细节丢失。为此，本文提出LSENet，基于U-Net引入三个核心模块：Patch Information Enhance（PIE）模块以分块注意力替代标准跳连，增强局部信息；Multiscale Feature Fusion（MFF）模块从原始输入与前层提取可解释特征，为PIE提供多尺度信息；Connectivity Refinement Decoder（CRD）对各层级特征进行精修，并在最后卷积层使用大核降低碎片化。在OCTA-500、ROSE-1和ROSSA三个公开数据集上的实验表明，LSENet达到当前最优性能，且参数量更少。
原文摘要 · Abstract (English)
Existing deep learning frameworks for Optical Coherence Tomography Angiography (OCTA) vessel segmentation are largely derived from the U-Net architecture, which serves as the foundation for most current designs. However, most of these methods focus only on holistic representation, struggling to address the problem of low local contrast unique to OCTA, which leads to vessel discontinuities and loss of detail. To address these problems, we propose LSENet, which builds upon the U-Net architecture by introducing three core innovative modules: To address vessel discontinuities, we introduce the Patch Information Enhance module (PIE), which replaces standard skip connections to execute patch-wise attention. To mitigate detail loss, the Multiscale Feature Fusion module (MFF) is proposed to feed the PIE module rich, multi-scale information by extracting visually interpretable features from both the original input and preceding layers. Finally, the Connectivity Refinement Decoder (CRD) is designed to refine features from all levels and utilize a large kernel in the final convolutional layer to reduce fragmentation. Experiments on three public datasets (OCTA-500, ROSE-1, and ROSSA) demonstrate that our proposed LSENet achieves state-of-the-art performance while requiring fewer parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。