Can I use 3-channel RGB image instead of only channel G?

[ReginaYann]

Thank you for sharing your code!
However, you mentioned you chose channel G (which contains the most vescular infomation) as input image, is your model also efficient and powerful enough when I used raw 3-channel RGB image as input? I tried to put the 3-channel image from DRIVE dataset, but the final dice indice seemed not as high as your result in you paper.

[Yaolei-Qi]

Thank you very much! Certainly, you can input it directly. But, for the vascular task, preprocessing tends to yield better results, but inputting the RGB image directly is also a viable option. We have plans to update the 2D code to accommodate RGB images in the future.