Regarding using this solution to solve another type of semantic segmentation problem about retina-unet HOT 5 CLOSED

Yes, the technique is very flexible. We have indeed applied it to the ultrasound nerve segmentation challenge. We actually ranked quite well but we missed the "tricks" phase to make it to the top.
In that case we didn't break up the image into pieces but processed the whole thing. In the retina case we break it up into small blocks, so the segmentation in the individual block is actually quite compact. We're reasoning about specific architectures for branched structures, hopefully we'll be able to work on them in the future.

Our code for the ultrasound challenge was quite similar to https://github.com/jocicmarko/ultrasound-nerve-segmentation. To me it was surprising to see how well it performed, given that I could barely discern the nerve myself on several images.

from retina-unet.

@lantiga , tks for sharing the code, I want to ask how do you choose the preprocessing in this dataset ? why do you use grey scale instead of rgb ?

from retina-unet.

We use grayscale because retinal images (except the more cutting edge, very recent cameras) are originally grayscale and get colored after the fact. The information in there is inherently 1-channel.

As to the rest of pre-processing, the basic idea is to remove slower trends across patches.

from retina-unet.

@lantiga , what do you mean by trends across patches ?

from retina-unet.

Mostly removing low-frequency changes in contrast and normalizing the intensity locally so that each patch has similar intensity statistics wrt to the others and local changes are enhanced. See https://en.wikipedia.org/wiki/Adaptive_histogram_equalization for instance.

from retina-unet.