Exploiting ensemble learning for automatic cataract detection and grading

Yang, Ji-Jiang; Li, Jianqiang; Shen, Ruifang; Zeng, Yang; Jian, He; Bi, Jing; Li, Yong; Zhang, Qinyan; Peng, Lihui; Wang, Qing

doi:10.1016/j.cmpb.2015.10.007

Cited by 144 publications

(64 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Automatic cataract detection using fundus images has also attracted significant attention, and was discussed in [40][41][42]. Prior to presenting the proposed method, the validation of retinal images in cataract screening is discussed and the features are introduced [43][44][45][46][47][48][49].…”

Section: Related Workmentioning

confidence: 99%

“…It can be observed that our method exhibits higher accuracy in both the two-class and four-class classification tasks. Compared to the features of Fourier transform [43], DCT of sketch lines [44][45], luminance and correlation [46], and local standard deviation [48], the detail component of the Haar wavelet indicates the blurriness more directly [47]. Blurring of digital retinal images occurs because no significant gray variation exists between the retinal structures and background [66].…”

Section: Performance Under Noise Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical method for cataract grading based on retinal images using improved Haar wavelet

Cao

Zhang

et al. 2020

Information Fusion

View full text Add to dashboard Cite

Cataracts, which are lenticular opacities that may occur at different lens locations, are the leading cause of visual impairment worldwide. Accurate and timely diagnosis can improve the quality of life of cataract patients. In this paper, a feature extraction-based method for grading cataract severity using retinal images is proposed. To obtain more appropriate features for the automatic grading, the Haar wavelet is improved according to the characteristics of retinal images. Retinal images of non-cataract, as well as mild, moderate, and severe cataracts, are automatically recognized using the improved Haar wavelet. A hierarchical strategy is used to transform the four-class classification problem into three adjacent two-class classification problems. Three sets of two-class classifiers based on a neural network are trained individually and integrated together to establish a complete classification system. The accuracies of the two-class classification (cataract and non-cataract) and four-class classification are 94.83% and 85.98%, respectively.The performance analysis demonstrates that the improved Haar wavelet feature achieves higher accuracy than the original Haar wavelet feature, and the fusion of three sets of two-class classifiers is superior to a simple four-class classifier. The discussion indicates that the retinal image-based method offers significant potential for cataract detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Performance Under Noise Conditionsmentioning

confidence: 99%

Hierarchical method for cataract grading based on retinal images using improved Haar wavelet

Cao

Zhang

et al. 2020

Information Fusion

View full text Add to dashboard Cite

show abstract

“…One issue is that existing methods cannot handle the retinal images with vitreous opacity well. All available methods of screening cataract using retinal images are only based on the features of contrast between retinal structures and background [13, 35–37] without considering the influence of vitreous opacity. In these methods, vitreous opacities with strong contrast will be detected as retinal structures, which will lead to incorrect grading.…”

Section: Introductionmentioning

confidence: 99%

An Approach to Evaluate Blurriness in Retinal Images with Vitreous Opacity for Cataract Diagnosis

2017

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Cataract is one of the leading causes of blindness in the world's population. A method to evaluate blurriness for cataract diagnosis in retinal images with vitreous opacity is proposed in this paper. Three types of features are extracted, which include pixel number of visible structures, mean contrast between vessels and background, and local standard deviation. To avoid the wrong detection of vitreous opacity as retinal structures, a morphological method is proposed to detect and remove such lesions from retinal visible structure segmentation. Based on the extracted features, a decision tree is trained to classify retinal images into five grades of blurriness. The proposed approach was tested using 1355 clinical retinal images, and the accuracies of two-class classification and five-grade grading compared with that of manual grading are 92.8% and 81.1%, respectively. The kappa value between automatic grading and manual grading is 0.74 in five-grade grading, in which both variance and P value are less than 0.001. Experimental results show that the grading difference between automatic grading and manual grading is all within 1 grade, which is much improvement compared with that of other available methods. The proposed grading method provides a universal measure of cataract severity and can facilitate the decision of cataract surgery.

show abstract

“…Total number of images used in this research work is 261. J.J. Yang et al [16] presented ensemble learning [17] based model for grading and automatic cataract detection. In preprocessing stage all the images are resized and are converted to green channel.…”

Section: Related Workmentioning

confidence: 99%

Automatic Cataract Classification on Retinal Image using Support Vector Machine

Kumari¹,

Jagadev²

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-Eye is a delicate organ of the body which provides organisms a vision. Eye is made up of sensory component such as lens, pupil, retina etc. One of the diseases which affect the human eye is cataract. Cataract occurs due to clouding of lens in the eye. Cataract is an eye disease which is responsible for vision loss and blindness. But earlier cataract detection system can provide a patient to know their condition timely and they can get the treatment accordingly. Using various image processing and classification technique one can detect and classify images. This paper points out different algorithm for detecting cataract in fundus images. This paper mainly involves mainly three steps specially preprocessing of the image, extraction of feature of preprocessed image and the last one is classification of image. In the very first step, image processing technique is applied for processing the image. We have used brightness preserving dynamic fuzzy histogram equalization method for contrast enhancement of image. In second step various feature of optical eye is extracted and the same feature are then used in classifier. For feature extraction statistical texture features such as mean, variance, energy, entropy and kurtosis of the eye is found. Support Vector Machine (SVM). SVM classification accuracy is 89%.

show abstract

Exploiting ensemble learning for automatic cataract detection and grading

Cited by 144 publications

References 30 publications

Hierarchical method for cataract grading based on retinal images using improved Haar wavelet

Hierarchical method for cataract grading based on retinal images using improved Haar wavelet

An Approach to Evaluate Blurriness in Retinal Images with Vitreous Opacity for Cataract Diagnosis

Automatic Cataract Classification on Retinal Image using Support Vector Machine

Contact Info

Product

Resources

About