Loosely coupled level sets for simultaneous 3D retinal layer segmentation in optical coherence tomography

Novosel, Jelena; Thepass, Gijs; Lemij, Hans G; Boer, Johannes F. de; Vermeer, Koenraad A.; Vliet, Lucas J. van

doi:10.1016/j.media.2015.08.008

Cited by 52 publications

(28 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, to visualize the RNFBs, en face images oriented along the RNFL were extracted. In the first step, 3D macular SD-OCT scans were automatically segmented using coupled level sets [3] since the built-in segmentation of RNFL by the scanner was not accurate for some of the B-scans. Then, the en face image showing the best visibility of the RNFB trajectories was selected for further processing.…”

Section: Methodsmentioning

confidence: 99%

Automatic estimation of retinal nerve fiber bundle orientation in SD-OCT images using a structure-oriented smoothing filter

et al. 2017

Self Cite

View full text Add to dashboard Cite

Optical coherence tomography (OCT) yields high-resolution, three-dimensional images of the retina. A better understanding of retinal nerve fiber bundle (RNFB) trajectories in combination with visual field data may be used for future diagnosis and monitoring of glaucoma. However, manual tracing of these bundles is a tedious task. In this work, we present an automatic technique to estimate the orientation of RNFBs from volumetric OCT scans. Our method consists of several steps, starting from automatic segmentation of the RNFL. Then, a stack of en face images around the posterior nerve fiber layer interface was extracted. The image showing the best visibility of RNFB trajectories was selected for further processing. After denoising the selected en face image, a semblance structure-oriented filter was applied to probe the strength of local linear structure in a discrete set of orientations creating an orientation space. Gaussian filtering along the orientation axis in this space is used to find the dominant orientation. Next, a confidence map was created to supplement the estimated orientation. This confidence map was used as pixel weight in normalized convolution to regularize the semblance filter response after which a new orientation estimate can be obtained. Finally, after several iterations an orientation field corresponding to the strongest local orientation was obtained. The RNFB orientations of six macular scans from three subjects were estimated. For all scans, visual inspection shows a good agreement between the estimated orientation fields and the RNFB trajectories in the en face images. Additionally, a good correlation between the orientation fields of two scans of the same subject was observed. Our method was also applied to a larger field of view around the macula. Manual tracing of the RNFB trajectories shows a good agreement with the automatically obtained streamlines obtained by fiber tracking.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic estimation of retinal nerve fiber bundle orientation in SD-OCT images using a structure-oriented smoothing filter

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…The segmentation of retinal layers in OCT has been tackled in a number of ways, such as dynamic programming [13], graph-based shortest path algorithms [4], graph-based minimum s-t cut formulations [8] and level sets [3,14]. Machine-learning based approaches have also been proposed, where the retinal layer and boundary probability maps are detected using a trained classifier.…”

Section: Introductionmentioning

confidence: 99%

Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images Using Bayesian Deep Learning

Sedai

Antony

Mahapatra

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is commonly used to analyze retinal layers for assessment of ocular diseases. In this paper, we propose a method for retinal layer segmentation and quantification of uncertainty based on Bayesian deep learning. Our method not only performs end-to-end segmentation of retinal layers, but also gives the pixel wise uncertainty measure of the segmentation output. The generated uncertainty map can be used to identify erroneously segmented image regions which is useful in downstream analysis. We have validated our method on a dataset of 1487 images obtained from 15 subjects (OCT volumes) and compared it against the state-of-the-art segmentation algorithms that does not take uncertainty into account. The proposed uncertainty based segmentation method results in comparable or improved performance, and most importantly is more robust against noise.

show abstract

“…For clinical diagnosis of retinal diseases various segmentation algorithms have been developed, such as locally adaptable level sets [19], voxel classification methods [20] or graph based segmentation (GBS) [21]. Although these algorithms work well for retinal segmentation, they do not necessarily perform well for highly corrugated interfaces and thin (varnish) layers as being present in cultural heritage objects.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of thin corrugated layers in high-resolution OCT images

Callewaert¹,

Dik²,

Kalkman³

2017

Opt. Express

View full text Add to dashboard Cite

Abstract:In this paper we present a novel method for the segmentation of thin corrugated layers in high resolution optical coherence tomography (OCT) images. First, we make an initial segmentation, for example with graph based segmentation that, for highly corrugated interfaces, leads to many segmentation errors. Second, we resegment the initial outcome, based on the OCT attenuation coefficient image with our matching layer attenuation coefficient segmentation (MLAS) algorithm. This algorithm repositions the initial segmentation such that it finds the point where the attenuation coefficient is close to the mean centerline attenuation. The algorithm does not utilize any sample specific prior knowledge in the attenuation coefficient based segmentation step. For simulated and measured data of strongly corrugated samples, such as is the case for varnish layers on paintings and furniture, the MLAS algorithm performs much better than the conventional segmentation. Finally, we show 3D segmentation of 190 mm 3 OCT volume of a thin corrugated varnish layer. Our technique can aid in the rapid characterization of layer stratigraphy and deepen our understanding of their condition.

show abstract

Loosely coupled level sets for simultaneous 3D retinal layer segmentation in optical coherence tomography

Cited by 52 publications

References 36 publications

Automatic estimation of retinal nerve fiber bundle orientation in SD-OCT images using a structure-oriented smoothing filter

Automatic estimation of retinal nerve fiber bundle orientation in SD-OCT images using a structure-oriented smoothing filter

Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images Using Bayesian Deep Learning

Segmentation of thin corrugated layers in high-resolution OCT images

Contact Info

Product

Resources

About