scholarly journals Self-relabeling for noise-tolerant retina vessel segmentation through label reliability estimation

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Jiacheng Li ◽  
Ruirui Li ◽  
Ruize Han ◽  
Song Wang

Abstract Background Retinal vessel segmentation benefits significantly from deep learning. Its performance relies on sufficient training images with accurate ground-truth segmentation, which are usually manually annotated in the form of binary pixel-wise label maps. Manually annotated ground-truth label maps, more or less, contain errors for part of the pixels. Due to the thin structure of retina vessels, such errors are more frequent and serious in manual annotations, which negatively affect deep learning performance. Methods In this paper, we develop a new method to automatically and iteratively identify and correct such noisy segmentation labels in the process of network training. We consider historical predicted label maps of network-in-training from different epochs and jointly use them to self-supervise the predicted labels during training and dynamically correct the supervised labels with noises. Results We conducted experiments on the three datasets of DRIVE, STARE and CHASE-DB1 with synthetic noises, pseudo-labeled noises, and manually labeled noises. For synthetic noise, the proposed method corrects the original noisy label maps to a more accurate label map by 4.0–$$9.8\%$$ 9.8 % on $$F_1$$ F 1 and 10.7–$$16.8\%$$ 16.8 % on PR on three testing datasets. For the other two types of noise, the method could also improve the label map quality. Conclusions Experiment results verified that the proposed method could achieve better retinal image segmentation performance than many existing methods by simultaneously correcting the noise in the initial label map.

Eye ◽  
2021 ◽  
Author(s):  
Duriye Damla Sevgi ◽  
Sunil K. Srivastava ◽  
Charles Wykoff ◽  
Adrienne W. Scott ◽  
Jenna Hach ◽  
...  

The retinal abnormalities and diagnosis of Diabetic Retinopathy (DR), Glaucoma are accomplished by extraction of vessel network in human retinal images. An accurate segmentation is required for the pathological analysis. Various researchers proposed many automated systems for vessel segmentation, still this process needs an improvement due to the presence of abnormalities, different magnitude, dimension of the vessels, non-uniform lighting and variable structure of the retina. The proposed work is a new method for retinal vessel segmentation, which consists of three phases, (i) The vessels network is enhanced by using Contrast Limited Adaptive Histogram Equalization(CLAHE) and Median filtering techniques (ii) the smoothened image is segmented based on mathematical morphology and maximum principal curvature followed by cleaning operation to remove the small objects, (iii) the segmented image is compared with hand labeled Ground Truth image and is evaluated with the True Positive, False Positive , True Negative and False Negative parameters. The performance of this work is tested with the images existing in DRIVE database. This work achieves 0.965 Accuracy, 0.752 Sensitivity and 0.989 Specificity.


Sign in / Sign up

Export Citation Format

Share Document