What would be an ideal environment/manner to judge the effectiveness of multiple segmentation algorithms? The goal is to determine which algorithms provide the best results for pre-clinical imaging. Our group has considered a GUI in MATLAB, and have different modules for different algorithms. Various papers have conducted such algorithm analyses in clinical scenarios, but none give an indication to their environment.
closed as primarily opinion-based by D.W.♦, David Richerby, Luke Mathieson, Juho, Tom van der Zanden Jul 8 '15 at 16:12
Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise. If this question can be reworded to fit the rules in the help center, please edit the question.
Google "image segmentation benchmark". You will find various data sets with ground truth, such as this one.