[论文解读] Efficient Kernel based Matched Filter Approach for Segmentation of Retinal Blood Vessels

Sushil Kumar Saroj, Vikas Ratna+2 more|arXiv (Cornell University)|Dec 7, 2020

Retinal Imaging and Analysis参考文献 32被引用 5

一句话总结

本文提出了一种高效的基于核的匹配滤波方法用于视网膜血管分割，采用自定义核以更准确匹配血管轮廓，从而提高精度。该方法在DRIVE数据集上实现了95.77%的准确率和98.50%的特异性，优于现有基于核的方法，归因于优化的核设计以及在匹配滤波响应（MFR）图像上采用Otsu阈值化处理。

ABSTRACT

Retinal blood vessels structure contains information about diseases like obesity, diabetes, hypertension and glaucoma. This information is very useful in identification and treatment of these fatal diseases. To obtain this information, there is need to segment these retinal vessels. Many kernel based methods have been given for segmentation of retinal vessels but their kernels are not appropriate to vessel profile cause poor performance. To overcome this, a new and efficient kernel based matched filter approach has been proposed. The new matched filter is used to generate the matched filter response (MFR) image. We have applied Otsu thresholding method on obtained MFR image to extract the vessels. We have conducted extensive experiments to choose best value of parameters for the proposed matched filter kernel. The proposed approach has examined and validated on two online available DRIVE and STARE datasets. The proposed approach has specificity 98.50%, 98.23% and accuracy 95.77 %, 95.13% for DRIVE and STARE dataset respectively. Obtained results confirm that the proposed method has better performance than others. The reason behind increased performance is due to appropriate proposed kernel which matches retinal blood vessel profile more accurately.

研究动机与目标

• 为解决现有基于核的方法在视网膜血管分割中因核轮廓不匹配而导致的性能不佳问题。
• 开发一种新型匹配滤波核，以准确反映视网膜血管的解剖轮廓。
• 通过优化核设计和在匹配滤波响应（MFR）图像上应用Otsu阈值化，提升分割精度和特异性。
• 在标准公开数据集（DRIVE和STARE）上验证所提方法，以确保性能评估的可靠性。

提出的方法

• 设计一种新型匹配滤波核，使其与视网膜血管的强度轮廓高度匹配。
• 将所提出的核应用于生成匹配滤波响应（MFR）图像，以增强类似血管的结构。
• 在MFR图像上应用Otsu阈值化方法以提取分割后的血管。
• 通过大量实验确定使性能最大化的最优核参数。
• 在两个基准数据集DRIVE和STARE上验证该方法，并采用标准评估指标。

实验结果

研究问题

• RQ1 自定义核设计是否能提升基于核的匹配滤波在视网膜血管分割中的精度？
• RQ2 所提核的轮廓与实际血管形态的匹配程度如何影响分割性能？
• RQ3 为使分割精度和特异性最大化，所提匹配滤波核的最优参数集是什么？
• RQ4 所提方法是否在标准视网膜血管分割基准上优于现有基于核的方法？

主要发现

• 所提方法在DRIVE数据集上实现了95.77%的准确率和98.50%的特异性，表现出优越性能。
• 在STARE数据集上，该方法实现了95.13%的准确率和98.23%的特异性，证实了其性能的一致性。
• 性能的提升归因于核对视网膜血管轮廓的精确匹配，从而增强了响应保真度。
• 通过广泛的参数调优，获得了最优核配置，显著提升了分割结果。