KLDD：视网膜图像分割中基于卡尔曼滤波的线性可变形扩散模型
KLDD: Kalman Filter based Linear Deformable Diffusion Model in Retinal Image Segmentation
AI总结：
针对 U-Net 易丢失视网膜细小血管的问题，本文提出 KLDD 模型，融合线性可变形卷积、卡尔曼滤波、注意力聚合与扩散模型，并在多个视网膜数据集上取得优于现有方法的分割性能。
摘要：
基于人工智能的血管分割在加强眼科疾病筛查和治疗方面正变得日益普遍。基于 U-Net 的深度学习结构已在血管分割中取得相对较好的性能。然而，小血管和毛细血管在经过传统 U-Net 下采样模块时，往往会在分割过程中丢失。为弥补这一不足，本文提出一种新颖的基于卡尔曼滤波的线性可变形扩散（Kalman filter based Linear Deformable Diffusion，KLDD）模型，用于视网膜血管分割。该模型采用扩散过程迭代细化分割结果，并在特征提取模块中利用可变形卷积的灵活感受野，以适应精细的管状血管结构。更具体地说，本文首先采用带有线性可变形卷积的特征提取器，从输入图像中捕获血管结构信息。为更好地优化可变形卷积的坐标位置，本文采用卡尔曼滤波来增强线性可变形卷积对血管结构的感知。随后，所提取的血管结构特征通过交叉注意力聚合模块（Cross-Attention Aggregation module，CAAM）和通道级软注意力模块（Channel-wise Soft Attention module，CSAM）被用作扩散模型中的条件元素。这些聚合机制旨在增强扩散模型生成血管结构的能力。实验在视网膜眼底图像数据集（DRIVE、CHASE_DB1）以及 OCTA-500 数据集的 3mm 和 6mm 数据上进行评估，结果表明本文提出的扩散模型优于其他方法。
英文摘要：
AI-based vascular segmentation is becoming increasingly common in enhancing the screening and treatment of ophthalmic diseases. Deep learning structures based on U-Net have achieved relatively good performance in vascular segmentation. However, small blood vessels and capillaries tend to be lost during segmentation when passed through the traditional U-Net downsampling module. To address this gap, this paper proposes a novel Kalman filter based Linear Deformable Diffusion (KLDD) model for retinal vessel segmentation. Our model employs a diffusion process that iteratively refines the segmentation, leveraging the flexible receptive fields of deformable convolutions in feature extraction modules to adapt to the detailed tubular vascular structures. More specifically, we first employ a feature extractor with linear deformable convolution to capture vascular structure information form the input images. To better optimize the coordinate positions of deformable convolution, we employ the Kalman filter to enhance the perception of vascular structures in linear deformable convolution. Subsequently, the features of the vascular structures extracted are utilized as a conditioning element within a diffusion model by the Cross-Attention Aggregation module (CAAM) and the Channel-wise Soft Attention module (CSAM). These aggregations are designed to enhance the diffusion model's capability to generate vascular structures. Experiments are evaluated on retinal fundus image datasets (DRIVE, CHASE_DB1) as well as the 3mm and 6mm of the OCTA-500 dataset, and the results show that the diffusion model proposed in this paper outperforms other methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
