Uncertainty-Aware Artery/Vein Classification on Retinal Images

Galdrán, Adrián; Meyer, Maria Inês; Costa, Pedro; Mendonça, Marcelo; Campilho, Aurélio

doi:10.1109/isbi.2019.8759380

Cited by 46 publications

(50 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, convolutional neural networks (CNNs) are widely used as the building blocks of deep learning models due to their segmentation performance. Many attempts have been made to prove CNN's ability for retinal vessel segmentation and even they exceeded in segmentation performance as compared to humans and traditional approaches [12–26]. All these techniques utilised deep learning for retinal vessel segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…Similarly, a deep learning structure called the Gaussian net (GNET) model combined with a saliency model, was proposed in [13] for retinal vessel segmentation. To classify the arteries and veins a UNet based method was proposed in [12] that takes into account such uncertainty and the authors formulated the arteries/veins classification task as a four‐class segmentation problem, and a CNN model was trained to classify pixels into the background, arteries, or uncertain classes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CPGAN: Conditional patch‐based generative adversarial network for retinal vesselsegmentation

Rammy

Abbas²,

Hassan

et al. 2020

IET image process

View full text Add to dashboard Cite

Retinal blood vessels, the diagnostic bio‐marker of ophthalmologic and diabetic retinopathy, utilise thick and thin vessels for diagnostic and monitoring purposes. The existing deep learning methods attempt to segment the retinal vessels using a unified loss function. However, a difference in spatial features of thick and thin vessels and a biased distribution creates an imbalanced thickness, rendering the unified loss function to be useful only for thick vessels. To address this challenge, a patch‐based generative adversarial network‐based technique is proposed which iteratively learns both thick and thin vessels in fundoscopic images. It introduces an additional loss function that allows the generator network to learn thin and thick vessels, while the discriminator network assists in segmenting out both vessels as a combined objective function. Compared with state‐of‐the‐art techniques, the proposed model demonstrates the enhanced accuracy, sensitivity, specificity, and area under the receiver operating characteristic curves on STARE, DRIVE, and CHASEDB1 datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

CPGAN: Conditional patch‐based generative adversarial network for retinal vesselsegmentation

Rammy

Abbas²,

Hassan

et al. 2020

IET image process

View full text Add to dashboard Cite

show abstract

“…One possible solution to this problem is to estimate the uncertainty in the model's predictions (Kendall and Gal 2017). Recently, uncertainty estimation in medical imaging has attracted much interest (Awate, Garg, and Jena 2019;Galdran et al 2019;Garifullin, Lensu, and Uusitalo 2020;Tanno et al 2017;Wang et al 2019). These methods can be divided in two main approaches: domain knowledge and Bayesian approaches.…”

Section: Introductionmentioning

confidence: 99%

“…Some methods pre-process the segmentation masks to include an "uncertain" class using domain knowledge. For instance, for the task of segmenting arteries and veins in retinal images, crossings in the vasculature and thin blood vessels can be labeled as uncertain (Galdran et al 2019). However, most existing methods aim to estimate the uncertainty directly from data without any additional domain knowledge information.…”

Section: Introductionmentioning

confidence: 99%

Epistemic and Heteroscedastic Uncertainty Estimation in Retinal Blood Vessel Segmentation

Costa

Smailagic

Cardoso

et al. 2021

UPjeng

View full text Add to dashboard Cite

Current state-of-the-art medical image segmentation methods require high quality datasets to obtain good performance. However, medical specialists often disagree on diagnosis, hence, datasets contain contradictory annotations. This, in turn, leads to difficulties in the optimization process of Deep Learning models and hinder performance. We propose a method to estimate uncertainty in Convolutional Neural Network (CNN) segmentation models, that makes the training of CNNs more robust to contradictory annotations. In this work, we model two types of uncertainty, heteroscedastic and epistemic, without adding any additional supervisory signal other than the ground-truth segmentation mask. As expected, the uncertainty is higher closer to vessel boundaries, and on top of thinner and less visible vessels where it is more likely for medical specialists to disagree. Therefore, our method is more suitable to learn from datasets created with heterogeneous annotators. We show that there is a correlation between the uncertainty estimated by our method and the disagreement in the segmentation provided by two different medical specialists. Furthermore, by explicitly modeling the uncertainty, the Intersection over Union of the segmentation network improves 5.7 percentage points.

show abstract

“…This uncertainty is due to the difficulty found by the specialists to label some vessel pixels in retinal images, mainly because of the limitations of acquisition devices. In this context, Galdran et al [22] proposed a CNN trained to classify the pixels into one of four classes (background, artery, vein, and uncertain), thus providing an automatic segmentation of the vasculature tree.…”

Section: Introductionmentioning

confidence: 99%

Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation

2020

View full text Add to dashboard Cite

Several systemic diseases affect the retinal blood vessels, thus their assessment allows an accurate clinical diagnosis. This assessment entails the estimation of the arteriolar-to-venular ratio (AVR), a predictive biomarker of cerebral atrophy and cardiovascular events in adults. In this context, different automatic and semi-automatic image-based approaches for artery/vein (A/V) classification and AVR estimation have been proposed in the literature, to the point of having become a hot research topic in the last decades. Most of these approaches use a wide variety of image properties, often redundant and/or irrelevant, requiring a training process that limit their generalization ability when applied to other datasets. This paper presents a new automatic method for A/V classification that just uses the local contrast between blood vessels and their surrounding background, computes a graph that represents the vascular structure, and applies a multilevel thresholding to obtain a preliminary classification. Next, a novel graph propagation approach was developed to obtain the final A/V classification and to compute the AVR. Our approach has been tested on two public datasets (INSPIRE and DRIVE), obtaining high classification accuracy rates, specially in the main vessels, and AVR ratios very similar to those provided by human experts. Therefore, our fully automatic method provides reliable results without any training step, which makes it suitable for use with different retinal image datasets and as part of any clinical routine.

show abstract

Uncertainty-Aware Artery/Vein Classification on Retinal Images

Cited by 46 publications

References 18 publications

CPGAN: Conditional patch‐based generative adversarial network for retinal vesselsegmentation

CPGAN: Conditional patch‐based generative adversarial network for retinal vesselsegmentation

Epistemic and Heteroscedastic Uncertainty Estimation in Retinal Blood Vessel Segmentation

Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation

Contact Info

Product

Resources

About