Coupled Sparse Dictionary for Depth-Based Cup Segmentation from Single Color Fundus Image

Chakravarty, Arunava; Sivaswamy, Jayanthi

doi:10.1007/978-3-319-10404-1_93

Cited by 21 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benchmark results are for the training set and are taken from [12]. (b)Mean CDR estimation error compared to other methods (a) Method/Organ optic cup optic disc CSR 0.86 ± 0.06 0.95 ± 0.02 SR 0.85 ± 0.08 0.95 ± 0.02 [6] 0.74 ± 0.20 0.96 ± 0.02 [13] 0.77 ± 0.17 - [14] 0.80 ± 0.18 -(b) CDR estimation error Method error CSR 0.08 ± 0.1 PR 0.09 ± 0.12 SR 0.12 ± 0.1 Fig. 1: Example outputs of our proposed OD-OC segmentation method.…”

Section: Methodsmentioning

confidence: 99%

“…As a result, cup boundary is ill defined and in-homogeneous which makes the segmentation more difficult. Existing approaches of optic cup segmentation are based on level sets [8], superpixels classification [9] and sparse dictionary learning [14]. In another method [13], fusion of cup segmentations from multi-view fundus images was performed to improve the performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of Optic Disc and Optic Cup in Retinal Fundus Images Using Coupled Shape Regression

Sedai

Roy

Mahapatra

et al. 2016

Proceedings of the Ophthalmic Medical Image Analysis Third International Workshop

View full text Add to dashboard Cite

Abstract. Accurate segmentation of optic cup and disc in retinal fundus images is required to derive the cup-to-disc ratio (CDR) parameter which is the main indicator for Glaucoma assessment. In this paper, we propose a coupled regression method for accurate segmentation of optic cup and disc in retinal colour fundus image. The proposed coupled regression framework consists of a parameter regressor which directly predicts CDR from a given image, as well as an ensemble shape regressor which iteratively estimates the OD-OC boundary by taking into account the CDR estimated by the parameter regressor. The parameter regressor and the shape regressor are then coupled together within a feedback loop so that estimation of one reinforces the other. Both parameter regressor and the ensemble shape regressor are modeled using Boosted Regression Trees. The proposed optic cup and disc segmentation method is applied on an image set of 50 patients and demonstrates high segmentation accuracy. A comparative study shows that our proposed method outperforms state of the art methods for cup segmentation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Segmentation of Optic Disc and Optic Cup in Retinal Fundus Images Using Coupled Shape Regression

Sedai

Roy

Mahapatra

et al. 2016

Proceedings of the Ophthalmic Medical Image Analysis Third International Workshop

View full text Add to dashboard Cite

show abstract

“…The depth information is either obtained using modalities like OCT or stereo. There have been very few works presented on estimating depth from color fundus image [3], [12], [13] compared to the numerous works presented for depth estimation in generic scenes using deep learning [14]- [16]. The work presented in [3] proposed a method to calculate depth from stereo.…”

Section: Related Workmentioning

confidence: 99%

Fully Convolutional Networks for Monocular Retinal Depth Estimation and Optic Disc-Cup Segmentation

Shankaranarayana

Ram

Mitra

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Glaucoma is a serious ocular disorder for which the screening and diagnosis are carried out by the examination of the optic nerve head (ONH). The color fundus image (CFI) is the most common modality used for ocular screening. In CFI, the central region which is the optic disc and the optic cup region within the disc are examined to determine one of the important cues for glaucoma diagnosis called the optic cup-to-disc ratio (CDR). CDR calculation requires accurate segmentation of optic disc and cup. Another important cue for glaucoma progression is the variation of depth in ONH region. In this work, we first propose a deep learning framework to estimate depth from a single fundus image. For the case of monocular retinal depth estimation, we are also plagued by the labelled data insufficiency. To overcome this problem we adopt the technique of pretraining the deep network where, instead of using a denoising autoencoder, we propose a new pretraining scheme called pseudo-depth reconstruction, which serves as a proxy task for retinal depth estimation. Empirically, we show pseudo-depth reconstruction to be a better proxy task than denoising. Our results outperform the existing techniques for depth estimation on the INSPIRE dataset.To extend the use of depth map for optic disc and cup segmentation, we propose a novel fully convolutional guided network, where, along with the color fundus image the network uses the depth map as a guide. We propose a convolutional block called multimodal feature extraction block to extract and fuse the features of the color image and the guide image. We extensively evaluate the proposed segmentation scheme on three datasets-ORIGA, RIMONEr3 and DRISHTI-GS. The performance of the method is comparable and in many cases, outperforms the most recent state-of-the-art.

show abstract

“…In [10], depth estimation and cup extraction is done on a single image using a coupled sparse dictionary based supervised method. CDR estimation has been widely used for glaucoma detection in monocular retinal fundus images.…”

Section: Introductionmentioning

confidence: 99%

Geometrical Feature Extraction for Glaucoma Detection

Arulmary¹,

Victor²

2018

IJCA

View full text Add to dashboard Cite

Glaucoma affects most of the eyes of the people which leads to blindness. Glaucoma harms the optic nerve cells that transmit graphic information to the brain. Hence it is important to detect glaucoma in eyes. Cup-to-Disc Ratio (CDR) is commonly used as an important parameter for glaucoma screening, involving segmentation of the optic cup on fundus images. A novel approach is proposed using the intensity values and size of the cup and disc. The proposed method uses the radius of the cup and disc for feature extraction. The features are classified using Support Vector Machine (SVM) classifier. The proposed method uses RIM-ONE dataset for evaluation. It achieves 99% specificity at 82% sensitivity with 0.863 AUC.

show abstract

Coupled Sparse Dictionary for Depth-Based Cup Segmentation from Single Color Fundus Image

Cited by 21 publications

References 16 publications

Segmentation of Optic Disc and Optic Cup in Retinal Fundus Images Using Coupled Shape Regression

Segmentation of Optic Disc and Optic Cup in Retinal Fundus Images Using Coupled Shape Regression

Fully Convolutional Networks for Monocular Retinal Depth Estimation and Optic Disc-Cup Segmentation

Geometrical Feature Extraction for Glaucoma Detection

Contact Info

Product

Resources

About