2
$\begingroup$

I have a task of segmentation of retinal blood vessels from fundus images an the same time detect malignant. so the output images should contain both segmented image and detected malignant. I am using Matlab.

original input image expected output image

I tried thresholding algorithm but for this kind of image I didn't get good results. But for the same algorithm when I applied for images for public available datasets such as STARE and DRIVE the segmented results compare to ground truth is almost the same

$\endgroup$

closed as too broad by Marcus Müller, MBaz, Stanley Pawlukiewicz, Peter K. May 1 at 12:31

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 1
    $\begingroup$ Hi! Welcome. So, what's your precise question? The shortest answer we can give would basically be doing your assignment, and that's probably a bit too broad. Try to narrow down your question to something specific! $\endgroup$ – Marcus Müller Apr 26 at 19:25
  • $\begingroup$ @MarcusMüller , the question is I tried thresholding algorithm but for this kind of image I didn't get good results. But for the same algorithm when I applied for images for public available datasets such as STARE and DRIVE the segmented results compare to ground truth is almost the same. $\endgroup$ – Ayubu Mbaga Apr 26 at 20:25
  • 1
    $\begingroup$ That makes the question way easier to identify and to help you! Can you show us what the result of thresholding looked like, and the original and thresholded images that you say look better? How did you choose the threshold? did you do any preprocessing steps before? $\endgroup$ – Marcus Müller Apr 27 at 7:33
  • 1
    $\begingroup$ Also, can you add the ground truth so we can tell where the malignant tumor is supposed to be? $\endgroup$ – havakok Apr 27 at 12:12