|
Methods and References | Data set | Advantages | Disadvantages |
|
Extended median filter [23] | DRIVE | Simple to implement | Less accuracy |
Blood vessels segmentation based on simplified PCNN and fast 2D-otsu algorithm [24] | DRIVE | Performed better in small vessels with high accuracy | Cannot remove pathological regions with low specificity |
Clifford matched filter [25] | DRIVE | High accuracy | Low sensitivity |
Using MF/ant (matched filter/ant colony) [26] | DRIVE | High accuracy | Cannot remove pathological regions with low specificity |
Improved matched filter [29] | DRIVE | High accuracy | Low specificity |
Genetic algorithm matched filter optimization [30] | DRIVE | High sensitivity | Low accuracy |
Improved multi-scale matched filter using PSO algorithm [31] | DRIVE | High sensitivity | Low specificity and accuracy |
Segmentation of retinal vessels by the use of Gabor wavelet and linear mean-squared-error classifier [32] | DRIVE | ā | Very low accuracy |
Gabor filters with the imperialism competitive algorithm [37] | DRIVE | High sensitivity and specificity | Low accuracy |
Hybrid segmentation approach [38] | DRIVE | High accuracy | Very low sensitivity |
A hybrid method to enhance thick and thin vessels [39] | DRIVE | High sensitivity and specificity | Low accuracy |
A hybrid method for blood vessel segmentation [41] | DRIVE | ā | Very high accuracy, sensitivity, and specificity |
Frangi filter coupled with the probabilistic patch-based denoiser [44] | DRIVE | High sensitivity | Low accuracy |
A context spatial U-Net for accurate blood vessel segmentation [45] | DRIVE | High sensitivity and specificity | Low accuracy |
|