I will present part of my work of ophthalmic image analysis using machine/deep learning techniques as part of the closure event of the Deep Learning for Medical Image Analysis course that Enzo Ferrante is teaching at the University of Buenos Aires.
We designed a method to summarize hemodynamic parameters obtained by 0D simulations so that they can be applied for glaucoma detection. We observed certain correlation between glaucoma and these hemodynamic features.
We developed a simple linear regression model that is able to estimate the hyperparameters of a fully-connected CRF model for blood vessel segmentation in fundus images.
I will present my SIPAIM 2017 paper on blood vessel segmentation in retinal images using FC-CRF with feature parameters estimated using linear regression.
We use pretrained VGG-S and OverFeat architectures as feature extractors for glaucoma detection in fundus pictures. We were able to get almost 0.8 AUC without fine-tuning the networks!
We present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained fully connected conditional random field model.