4.7 Article

Weak label based Bayesian U-Net for optic disc segmentation in fundus images

Journal

ARTIFICIAL INTELLIGENCE IN MEDICINE
Volume 126, Issue -, Pages -

Publisher

ELSEVIER
DOI: 10.1016/j.artmed.2022.102261

Keywords

Optic disc segmentation; Bayesian U-Net; Expectation-maximization; Weak labels; Fundus image

Ask authors/readers for more resources

In this study, a weak label based Bayesian U-Net method exploiting Hough transform is proposed for optic disc segmentation in fundus images. By building a probabilistic graphical model and using the state-of-the-art U-Net framework, this method achieves accurate disc segmentation without the need for pixel-level annotation.
Fundus images have been widely used in routine examinations of ophthalmic diseases. For some diseases, the pathological changes mainly occur around the optic disc area; therefore, detection and segmentation of the optic disc are critical pre-processing steps in fundus image analysis. Current machine learning based optic disc segmentation methods typically require manual segmentation of the optic disc for the supervised training. However, it is time consuming to annotate pixel-level optic disc masks and inevitably induces inter-subject variance. To address these limitations, we propose a weak label based Bayesian U-Net exploiting Hough transform based annotations to segment optic discs in fundus images. To achieve this, we build a probabilistic graphical model and explore a Bayesian approach with the state-of-the-art U-Net framework. To optimize the model, the expectation-maximization algorithm is used to estimate the optic disc mask and update the weights of the Bayesian U-Net, alternately. Our evaluation demonstrates strong performance of the proposed method compared to both fully- and weakly-supervised baselines.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available