A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images
By José Ignacio Orlando, Elena Prokofyeva, Matthew B. Blaschko. IEEE Transactions on Biomedical Engineering, 2017
471 citations recorded by the source corpus.
Goal: 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. Methods: 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. Results: Our method, trained with state of the art features, is evaluated both quantitatively and qualitatively on four publicly available datasets: DRIVE, STARE, CHASEDB1, and HRF. Additionally, a quantitative comparison with respect to other strategies is included. Conclusion: 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. Significance: 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.
Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/5fe24f2bb81d4695ae6dca46318dba6d52523d11
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Erik J. Bekkers
- Kwang-Ting Cheng
- B. T. H. Romeny
- Xin Yang
- Zengqiang Yan
- Josien P. W. Pluim
- Jiong Zhang
- Zhiqiang Shen
In Ophthalmology
- Kwang-Ting Cheng
- Xin Yang
- Zengqiang Yan
- Remco Duits
- Erik J. Bekkers
- Josien P. W. Pluim
- Gary G. Yen
- Yao Zhou
In Radiology, Nuclear Medicine and Imaging
- Kwang-Ting Cheng
- Xin Yang
- Zengqiang Yan
- Remco Duits
- Erik J. Bekkers
- Josien P. W. Pluim
- Arvid Lundervold
- Gary G. Yen
Citations in the corpus
- Robust Retinal Vessel Segmentation via Locally Adaptive Derivative Frames in Orientation Scores (2016, background): “[39] at the same specificity level of 0.”
- Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation (2018, methodology): “losses and the method in [32] are summarized in Table V.”
- A Three-Stage Deep Learning Model for Accurate Retinal Vessel Segmentation (2019, methodology): “Since FOV masks are not provided and there exists no uniform generation method, the masks provided in [25] and [31] are used for”
- Computer Methods and Programs in Biomedicine (unknown): “Fully-Connected Conditional Random Field (FCCRF) is used in [40,59] to segment retinal vessels in color fundus photography.”
- SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation (2020, unknown): “[16] 2017 0.”