Automatic cyst detection in OCT retinal images combining region flooding and texture analysis

González, Ana; Remeseiro, Beatriz; Ortega, Marcos; Penedo, Manuel G.; Charlón, Pablo

doi:10.1109/cbms.2013.6627825

Cited by 25 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later, a fully automated approach was proposed in [2], where they combined a k-nearest neighbor (k-NN) classification and a graph cut segmentation. Very recently, several automated methods were presented, which followed the generally identical strategy [3][4][5]. The retina is first over-segmented using thresholding [3], Split-Bregman [4], or watershed [5], after which a classifier is trained or a set of heuristic rules are used to reject false positive detections.…”

Section: Introductionmentioning

confidence: 99%

“…Very recently, several automated methods were presented, which followed the generally identical strategy [3][4][5]. The retina is first over-segmented using thresholding [3], Split-Bregman [4], or watershed [5], after which a classifier is trained or a set of heuristic rules are used to reject false positive detections. More success has been reported in identifying fluid under the retina, which is typically solved by dual-surface segmentation, as the fluid pockets can be found subsequently by thresholding the resulting thickness between the two surfaces [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

Bogunović

Abràmoff

Sonka

2015

Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop

View full text Add to dashboard Cite

Abstract. Age-related macular degeneration (AMD) is a leading cause of blindness in developed countries. Its most damaging form is characterized by accumulation of fluid inside the retina, whose quantification is of utmost importance for evaluating the disease progression. In this paper we propose an automated method for retinal fluid segmentation from 3D images acquired with optical coherence tomography (OCT). It combines a machine learning approach with an effective segmentation framework based on geodesic graph cut. After an image preprocessing step, an artificial neural network is trained based on textural features to assign to each voxel a probability of belonging to a fluid. The obtained probability maps are used to compute minimal geodesic distances from a set of identified seed points to the remaining unassigned voxels. Finally, the segmentation is solved optimally and efficiently using graph cut optimization. The method is evaluated on a clinical longitudinal dataset consisting of 30 OCT scans from 10 patients taken at 3 different stages of treatment. Manual annotations from two retinal specialists were taken as the gold standard. The segmentation method achieved mean precision of 0.88 and recall of 0.83, with the combined F1 score of 0.85. The segmented fluid volumes were within the measured inter-observer variability. The results demonstrate that the proposed method is a promising step towards accurate quantification of retinal fluid.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

Bogunović

Abràmoff

Sonka

2015

Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop

View full text Add to dashboard Cite

show abstract

“…An approach for an automated methodology was presented by authors in [11] for cyst detection in OCT retinal images by using watershed algorithm for the detection of candidate regions in the images and after that the discard of all the possible regions to reduce eligible candidates, which due to some of the properties can be considered as cysts. Finally, a classifier used for the determination of their correspondence to cystic regions or not on the basis of texture features extracted from them.…”

Section: Related Workmentioning

confidence: 99%

Analysis of OCT Images for Detection of Choroidal Neovascularization in Retinal Pigment Epithelial Layer

Ayaz

Sahar

Zafar

et al. 2014

Neural Information Processing

View full text Add to dashboard Cite

Abstract. Choroidal Neovascularization (CNV) is an age related disease which deals with the Degeneration of Macular tissue. This degeneration causes acute drop in central vision as the age progresses. Therefore it is necessary to identify the changes caused by CNV for the Successful detection of this disease. In CNV the Retinal Pigment Epithelial (RPE) layer encounters changes in different attributes which can be identified with the help of Optical Coherence Tomography (OCT) Images. This paper focuses on analyzing the changes caused in the RPE layer due to CNV. The proposed system segments out RPE layer and observes the changes in RPE layer by calculating different features like Euler Number, Energy, Homogeneity and Correlation. The system is tested on locally gathered dateset of 50 images from different patients and has achieved an accuracy of 98%.

show abstract

“…Another study used an automatic method combining region°ooding and texture analysis to detect cysts. 19 Due to the recent developments in machine learning, more supervised and unsupervised methods have been proposed to segment retinal°uid regions.…”

Section: Introductionmentioning

confidence: 99%

Automated segmentation of intraretinal cystoid macular edema based on Gaussian mixture model

Niu

Chen

et al. 2019

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

We introduce a method based on Gaussian mixture model (GMM) clustering and level-set to automatically detect intraretina fluid on diabetic retinopathy (DR) from spectral domain optical coherence tomography (SD-OCT) images in this paper. First, each B-scan is segmented using GMM clustering. The original clustering results are refined using location and thickness information. Then, the spatial information among every consecutive five B-scans is used to search potential fluid. Finally, the improved level-set method is used to obtain the accurate boundaries. The high sensitivity and accuracy demonstrated here show its potential for detection of fluid.

show abstract

Automatic cyst detection in OCT retinal images combining region flooding and texture analysis

Cited by 25 publications

References 7 publications

Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

Geodesic Graph Cut Based Retinal Fluid Segmentation in Optical Coherence Tomography

Analysis of OCT Images for Detection of Choroidal Neovascularization in Retinal Pigment Epithelial Layer

Automated segmentation of intraretinal cystoid macular edema based on Gaussian mixture model

Contact Info

Product

Resources

About