Automated Segmentation of the Optic Nerve Head for Glaucoma Diagnosis

Chrástek, Radim; Wolf, Matthias; Donath, Klaus; Niemann, Heinrich; Hothorn, Torsten; Lausen, Berthold; Laemmer, Robert; Mardin, Christian Y.; Michelson, Georg

doi:10.1007/978-3-642-18993-7_69

Cited by 42 publications

(64 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These methods subtract the estimated retinal background from the original image to gain a homogeneously illuminated fundus image. The estimation of a background can be done by average intensity filtering within a large neighborhood (Chrástek et al, 2005;Hoover et al, 2000) or polynomial surface fitting (Narasimha-Iyer et al, 2006).…”

Section: Illumination Correctionmentioning

confidence: 99%

“…In the literature, some methods restrict the segmented ONH rim to be circular or elliptical using e.g. Hough transform (Blanco et al, 2006;Zhu et al, 2009) while other techniques allow higher variabil-ity of the ONH shape using parametric or free-form deformable models (Chrástek et al, 2005;Li and Chutatape, 2003;Xu et al, 2007). The performance of the proposed segmentation techniques strongly rely on proper initialization with the location of the ONH: Proposed algorithms utilize ONH templatematching, intensity assumptions or the convergence of the vessel tree (Chrástek et al, 2005;Hoover and Goldbaum, 2003;Lowell et al, 2004;Youssif et al, 2008).…”

Section: Optic Nerve Head Normalizationmentioning

confidence: 99%

See 1 more Smart Citation

Glaucoma risk index:Automated glaucoma detection from color fundus images

Bock

Meier

Nyúl

et al. 2010

Medical Image Analysis

Self Cite

312

170

View full text Add to dashboard Cite

Glaucoma as a neurodegeneration of the optic nerve is one of the most common causes of blindness. Because revitalization of the degenerated nerve fibers of the optic nerve is impossible early detection of the disease is essential. This can be supported by a robust and automated mass-screening. We propose a novel automated glaucoma detection system that operates on inexpensive to acquire and widely used digital color fundus images. After a glaucoma specific preprocessing, different generic feature types are compressed by an appearance-based dimension reduction technique. Subsequently, a probabilistic two-stage classification scheme combines these features types to extract the novel Glaucoma Risk Index (GRI) that shows a reasonable glaucoma detection performance. On a sample set of 575 fundus images a classification accuracy of 80 % has been achieved in a 5-fold cross validation setup. The GRI gains a competitive area under ROC (AUC) of 88 % compared to the established topography-based Glaucoma Probability Score of scanning laser tomography with AUC of 87 %. The proposed color fundus image-based GRI achieves a competitive and reliable detection performance on a low-priced modality by the statistical analysis of entire images of the optic nerve head.

show abstract

Section: Illumination Correctionmentioning

confidence: 99%

Section: Optic Nerve Head Normalizationmentioning

confidence: 99%

Glaucoma risk index:Automated glaucoma detection from color fundus images

Bock

Meier

Nyúl

et al. 2010

Medical Image Analysis

Self Cite

312

170

View full text Add to dashboard Cite

show abstract

“…It shows the highest contrast between the blood vessels and the background and also for the studies of the optic nerve head. This approach is also used by other research groups [4,9,10]. We implemented a correction method similar to the one proposed in [9].…”

Section: Correction Of Illumination and Intensity Inhomogeneitymentioning

confidence: 99%

“…We used a slightly modified version of the ONH localization method of [4]. It uses a mean filtering with a large kernel and threshold probing for rough localization, and then a circular Hough transform on the edge map to find the border of the neuroretinal rim.…”

Section: Normalization Of the Onh Region Of Interestmentioning

confidence: 99%

“…The acquisition is suitable for screening applications because fundus photos can be taken very fast and without any inconvenience for patients. Existing computer aided analysis of retina images are based on segmentation which is mostly done manually or by semi-automated methods [4]. Different research groups investigate in the field of getting and selecting segmentation measurements from HRT images [5,6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effects of Preprocessing Eye Fundus Images on Appearance Based Glaucoma Classification

Meier

Bock

Michelson

et al.

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Early detection of glaucoma is essential for preventing one of the most common causes of blindness. Our research is focused on a novel automated classification system based on image features from fundus photographs which does not depend on structure segmentation or prior expert knowledge. Our new data driven approach that needs no manual assistance achieves an accuracy of detecting glaucomatous retina fundus images compareable to human experts. In this paper, we study image preprocessing methods to provide better input for more reliable automated glaucoma detection. We reduce disease independent variations without removing information that discriminates between images of healthy and glaucomatous eyes. In particular, nonuniform illumination is corrected, blood vessels are inpainted and the region of interest is normalized before feature extraction and subsequent classification. The effect of these steps was evaluated using principal component analysis for dimension reduction and support vector machine as classifier.

show abstract

Morphometric Measurements of The Retinal Vasculature in Fundus Images with Vampire

Trucco

Giachetti

Ballerini

et al. 2015

Biomedical Image Understanding

View full text Add to dashboard Cite

Much research is being directed toward investigating links between quantitative characteristics of the retinal vasculature and a variety of outcomes to identify biomarkers. The interest for retinal biomarkers lies in the fact that the retina is easily observed via fundus photography. Outcomes considered for research of biomarkers in the literature include conditions such as diabetes and lacunar stroke, and also cognitive performance and genetic expression [1][2][3][4][5]. The need for measuring large volumes of images, needed to power biomarker discovery studies, makes semiautomatic software systems desirable. This chapter reports recent algorithms developed by the VAMPIRE group for vasculature detection and quantification, including recent developments on landmark detection. We focus on accuracy and validation issues, and, importantly, the conditions for comparing meaningful results from different algorithms. This work is a part of VAMPIRE (Vasculature Assessment and Measurement Platform for Images of the REtina), which is an international collaboration growing a software suite for automatic morphometric measurements of the retinal vasculature.

show abstract

Automated Segmentation of the Optic Nerve Head for Glaucoma Diagnosis

Cited by 42 publications

References 1 publication

Glaucoma risk index:Automated glaucoma detection from color fundus images

Glaucoma risk index:Automated glaucoma detection from color fundus images

Effects of Preprocessing Eye Fundus Images on Appearance Based Glaucoma Classification

Morphometric Measurements of The Retinal Vasculature in Fundus Images with Vampire

Contact Info

Product

Resources

About