ignaciorlando / fundus-vessel-segmentation-tbme

In this work, 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. Standard segmentation priors such as a Potts model or total variation usually fail when dealing with thin and elongated structures. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real-time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. Our method, trained with state of the art features, is evaluated both quantitatively and qualitatively on four publicly available data sets: DRIVE, STARE, CHASEDB1 and HRF. Additionally, a quantitative comparison with respect to other strategies is included. The experimental results show that this approach outperforms other techniques when evaluated in terms of sensitivity, F1-score, G-mean and Matthews correlation coefficient. Additionally, it was observed that the fully connected model is able to better distinguish the desired structures than the local neighborhood based approach. Results suggest that this method is suitable for the task of segmenting elongated structures, a feature that can be exploited to contribute with other medical and biological applications.
47 stars 15 forks source link

Some problems about the source code #9

Closed Author123456 closed 6 years ago

Author123456 commented 6 years ago

Hi Nacho, It's my first message to a scientist, and I am so excited, and hope to get your reply.

Recently I am studying your paper, which really benefits me. I also read the paper (Retinal Vessel Segmentation Using the 2-D Gabor Wavelet and Supervised Classification 2006), and I find your source code also refers some code from the paper. Here I want to know how to get the source code of the paper (2006)? Would you like to give me a link? I want to study further. Thank you a lot.

David

ignaciorlando commented 6 years ago

Hi David,

Thanks for your interest! You will find the implementation of the 2-D Gabor Wavelet here: https://github.com/ignaciorlando/fundus-vessel-segmentation-tbme/blob/master/Features/Features/Soares2006.m

Best,

Nacho

Author123456 commented 6 years ago

Hi Nacho,

Thank your your reply! The code is just about 2-D Gabor Wavelet, and could you share more code about the classifying the vessel in the paper, or the whole source code of the paper. (The original link the author provided is somehow invalid.)

Thank you.

Best,

David