Research Article
Learning-Based Visual Saliency Model for Detecting Diabetic Macular Edema in Retinal Image
Figure 1
We collected eye-tracking data on 100 retinal images with diabetic macular edema from 10 ophthalmologists. Gaze tracking paths and fixation locations are recorded in (b). A continuous ground truth (b) is found by convolving a Gaussian over the fixation locations of all users.
(a) Original image |
(b) Eye tracking |
(c) Ground truth |