Automated detection of glaucoma using structural and non structural features

Salam, Anum Abdul; Khalil, Tehmina; Akram, M. Usman; Jameel, Amina; Basit, Imran

doi:10.1186/s40064-016-3175-4

Cited by 100 publications

(50 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os trabalhos de Archarya et al [4], Simonthomas et al [5], Salam et al [6] e Srinivasan et al [7] apresentaram soluções para a mesma problemática. A Acurácia obtida nos quatro trabalhos foi superior a 91% com a utilização de descritores de textura.…”

Section: Trabalhos Relacionadosunclassified

“…Sendo a Gray Level Co-occurrence Matrix (GLCM), um ponto em comum em todos os trabalhos. No trabalho de Salam et al [6], os autores incluíram os descritores Color Moments e Autocorrelogram na etapa de extração de características, o que proporcionou 100% de sensibilidade do método proposto. Entretanto, a utilização de bases de dados privadas dificulta a recriação de experimentos e consequentemente possíveis comparações.…”

Section: Trabalhos Relacionadosunclassified

“…Segundo Salam et al [6] a identificação de imagens glaucomatosas pode ser eficientemente realizada utilizando os descritores de textura e forma. Neste estudo forma avaliados os descritores de textura Local Binary Pattern (LBP) [14]; Gray Level Co-occurrence Matrix (GLCM) [15]; Histogram of Oriented Gradients (HOG) [16]; Tamura [17]; Gray Level Run Length Matrix (GLRLM) [18], [19], [20] e descritores de forma.…”

Section: Extração De Característicasunclassified

See 2 more Smart Citations

Diagnóstico de Glaucoma Utilizando Atributos de Textura e CNN’s Pré-treinadas

Claro

Veras

Santana

et al. 2018

RITA

View full text Add to dashboard Cite

Resumo: Glaucoma is a disease that damages the optic nerve. It is considered the second leading cause of blindness in the world. Several automatic diagnostic systems have been proposed. However, such systems have not been shown to be able to handle a great diversity of images. Thus, this work proposes a method of detecting glaucoma, through the use of texture descriptors and Convolutional Neural Networks (CNNs). Tests were conducted in four public databases, making a total of 873 images. The results showed that the junction of GLCM and pre-trained CNN descriptors and the use of the Random Forest classifier are promising in the detection of this pathology, obtaining an accuracy of 91.06%. Keywords: medical images -glaucoma diagnosis -texture features -transfer learning Resumo: Glaucomaé uma doença que danifica o nervoóptico. Elaé considerada a segunda principal causa de cegueira no mundo. Vários sistemas de diagnóstico automático têm sido propostos, contudo, tais sistemas não demonstraram ser capazes de lidar com uma grande diversidade de imagens. Dessa forma, este trabalho propõe um método de detecção do glaucoma, através do uso de descritores de textura e Redes Neurais Convolucionais (CNNs). Testes foram conduzidos em quatro bases públicas, o que constitui um total de 873 imagens. Os resultados mostraram que a junção dos descritores GLCM e CNNs pré-treinadas e a utilização do classificador Random Forest são promissores na detecção dessa patologia, obtendo uma acurácia de 91,06%.. Palavras-Chave: imagens médicas -diagnóstico de glaucoma -atributos de textura -transferência de aprendizagem

show abstract

Section: Trabalhos Relacionadosunclassified

Section: Extração De Característicasunclassified

See 1 more Smart Citation

Diagnóstico de Glaucoma Utilizando Atributos de Textura e CNN’s Pré-treinadas

Claro

Veras

Santana

et al. 2018

RITA

View full text Add to dashboard Cite

show abstract

“…The methodology incorporated Conversion to various color spaces, channel extraction, statistical, histogram, GLCM based feature extraction and classification through Grafted C4.5 yielding an accuracy of 86.67% on HRF images with cross valiation of 3 folds. Again in 2014, Vijapur [9] proposed a data driven workflow for detection of Glaucoma through extraction of energy features from detailed co-efficient images obtained through application of daubechies, symlets and bioorthogonal wavelet filters and computation of cup to disc ratio feature through optic disc attained through disc prediction and cup In 2016, Salem et al [10] attempted to detect Glaucoma through Cup to disc ratio, texture and intensity based features. The predictions from cup to disc ratio and combination of texture and intensity features are correlated to categorize the image as Glaucoma, suspect or non-Glaucoma.…”

Section: Literature Surveymentioning

confidence: 99%

Automatic Detection of Glaucoma in Retinal Fundus Images through Image Processing and Data Mining Techniques

Ramani¹,

Sugirtharani²,

Lakshmi³

2017

IJCA

View full text Add to dashboard Cite

Computational techniques are highly used in medical image analysis to aid the medical professionals. Glaucoma is a sight threatening retinal disease that needs attention at its early stages, though it does not reveal any symptoms. Glaucoma is identified usually through cup to disc ratio and ISNT rule. This work involves segmentation of blood vessels, segmentation of optic disc through proposed maximum voting of three segmentation algorithms (K-Means, Wavelet and Histogram based), segmentation of optic cup through intensity thresholding, feature extraction from these segmented structures, feature selection to identify siginificant features, hybrid model involving Naive Bayes to remove noise in data followed by ensemble classification of Reduced Error Pruning Tree. Optic disc segmentation methodology attains an average accuracy of 99.33%. Glaucoma detection accuracy reaches a maximum of 96.42%.

show abstract

“…The reason for using segmentation method proposed in [10] is because it is quite robust to noise and it can even detect small vascular patterns with an average accuracy of 94.85% [10].The images are then cropped such that the resulting image has optic disc and a small region surrounding the optic disc (2-disc diameter). Apart from this, we have also extracted the optic disc boundary by removing blood vessels around the optic disc region using the method which we proposed in [11] and the boundary of OD is smoothened using ellipse fitting. The extracted disc boundary plays a vital role in extracting color features as described in section 2.2.1 below.…”

Section: Preprocessingmentioning

confidence: 99%

Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs

Fatima¹,

Hassan²,

Akram³

et al. 2017

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

Rapid development in the field of ophthalmology has increased the demand of computer aided diagnosis of various eye diseases. Papilledema is an eye disease in which the optic disc of the eye is swelled due to an increase in intracranial pressure. This increased pressure can cause severe encephalic complications like abscess, tumors, meningitis or encephalitis, which may lead to a patient's death. Although there have been several papilledema case studies reported from a medical point of view, only a few researchers have presented automated algorithms for this problem. This paper presents a novel computer aided system which aims to automatically detect papilledema from fundus images. Firstly, the fundus images are preprocessed by going through optic disc detection and vessel segmentation. After preprocessing, a total of 26 different features are extracted to capture possible changes in the optic disc due to papilledema. These features are further divided into four categories based upon their color, textural, vascular and disc margin obscuration properties. The best features are then selected and combined to form a feature matrix that is used to distinguish between normal images and images with papilledema using the supervised support vector machine (SVM) classifier. The proposed method is tested on 160 fundus images obtained from two different data sets i.e. structured analysis of retina (STARE), which is a publicly available data set, and our local data set that has been acquired from the Armed Forces Institute of Ophthalmology (AFIO). The STARE data set contained 90 and our local data set contained 70 fundus images respectively. These annotations have been performed with the help of two ophthalmologists. We report detection accuracies of 95.6% for STARE, 87.4% for the local data set, and 85.9% for the combined STARE and local data sets. The proposed system is fast and robust in detecting papilledema from fundus images with promising results. This will aid physicians in clinical assessment of fundus images. It will not take away the role of physicians, but will rather help them in the time consuming process of screening fundus images.

show abstract

Automated detection of glaucoma using structural and non structural features

Cited by 100 publications

References 27 publications

Diagnóstico de Glaucoma Utilizando Atributos de Textura e CNN’s Pré-treinadas

Diagnóstico de Glaucoma Utilizando Atributos de Textura e CNN’s Pré-treinadas

Automatic Detection of Glaucoma in Retinal Fundus Images through Image Processing and Data Mining Techniques

Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs

Contact Info

Product

Resources

About