No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Medical decision support system to identify glaucoma using cup to disc ratio
Abstract
ARGALI is an Automatic cup-to-disc Ratio measurement system for Glaucoma AnaLysIs Using level-set image processing. The parameters such as rim volume, cup/disc area ratio, cup area and volume, disc area and volume have been estimated and considered for general classification of Glaucoma. The developed method aims to exploit the advantages of ARGALI and for automated glaucoma risk assessment. The developed approach achieves a better CDR (Cup-to-Disc Ratio) value using novel techniques discussed in this paper. The level of Glaucoma influence for the patients has been estimated from the CDR values and it has been observed that the glaucoma level is independent of the age and dependent on the physical dimension of the eyes. Finally, it has been observed that the estimated values are very close to the clinical values and the correctness of the estimation have been verified with a team of Doctors and has been appreciated by them about its clinical usefulness.
... In [20], the local binary pattern was used to obtain the representative texture features, which were classified using the k-NN algorithm. In addition to texture, shape features have been analyzed for glaucoma detection [21,22]. The implementation of shape feature analysis was proposed in [23] based on the cup and SVM contours. ...
Objectives
Glaucoma is an incurable eye disease and the second leading cause of blindness in the world. Until 2020, the number of patients of this disease is estimated to increase. This paper proposes a glaucoma detection method using statistical features and the k-nearest neighbor algorithm as the classifier.
Methods
We propose three statistical features, namely, the mean, smoothness and 3rd moment, which are extracted from images of the optic nerve head. These three features are obtained through feature extraction followed by feature selection using the correlation feature selection method. To classify those features, we apply the k-nearest neighbor algorithm as a classifier to perform glaucoma detection on fundus images.
Results
To evaluate the performance of the proposed method, 84 fundus images were used as experimental data consisting of 41 glaucoma image and 43 normal images. The performance of our proposed method was measured in terms of accuracy, and the overall result achieved in this work was 95.24%, respectively.
Conclusions
This research showed that the proposed method using three statistics features achieves good performance for glaucoma detection.
Glaucoma is the eye defect that has become the second leading cause of blindness worldwide and also stated as incurable, may cause complete vision loss. The earlier diagnosis of glaucoma in Human Eye is a great confrontation and very important in present scenario, for providing efficient and appropriate treatments to the persons. Though there is much advancement in Ocular Imaging that affords methods for earlier detection, the appropriate results can be obtained by integrating the data from structural and functional evaluations. With that note, this paper involves in developing automated technique for glaucomatous image classification and diagnosis (AT-GICD). The model considers both the textural and energy features for effectively diagnosing the defect. Image Segmentation is processed for obtaining the exact area of optic nerve head; histogram gradient based conversion is employed for enhancing the fundus image features. Further, Wavelet Energy features are extracted and applied to the artificial neural networks (ANN) for classifying the NORMAL and GLAUCOMA images. The Accuracy rate based comparison with other existing models is carried out for evidencing the effectiveness of the proposed model in glaucomatous image classification.
To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression.
Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard.
The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58).
The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.
A new approach to automatically extract the main features in color fundus images is proposed. The optic disk is localized by principal component analysis (PCA) and its shape is detected by a modified active shape model (ASM). Exudates are extracted by the combined region growing and edge detection. A fundus coordinate system is further set up based on fovea localization to provide a better description of the features in fundus images. The success rates achieved are 99%, 94%, and 100% for disk localization, disk boundary detection, and fovea localization respectively. The sensitivity and specificity for exudate detection are 100% and 71%. The success of the proposed algorithms can be attributed to utilization of the model-based methods.
Glaucoma is the second leading cause of blindness. Glaucoma can be diagnosed through measurement of neuro-retinal optic cup-to-disc ratio (CDR). Automatic calculation of optic cup boundary is challenging due to the interweavement of blood vessels with the surrounding tissues around the cup. A Convex Hull based Neuro-Retinal Optic Cup Ellipse Optimization algorithm improves the accuracy of the boundary estimation. The algorithm's effectiveness is demonstrated on 70 clinical patient's data set collected from Singapore Eye Research Institute. The root mean squared error of the new algorithm is 43% better than the ARGALI system which is the state-of-the-art. This further leads to a large clinical evaluation of the algorithm involving 15 thousand patients from Australia and Singapore.
Although glaucoma is a major global cause of blindness, the lack of a uniform definition of the disease in its different forms makes it difficult to assess its public health impact. By considering the common features of glaucoma, we have analysed available data on the three main forms of the disease: congenital/hereditary glaucoma, primary open-angle, and primary angle-closure glaucoma. A simple model was then developed to estimate the extent of glaucoma on a regional basis, taking into account demographic data, e.g., age distribution, gender and ethnic groups. Overall, the results demonstrate that glaucoma is responsible for approximately 5.2 million blind (15% of the total burden of world blindness).
Optic disc parameters are commonly used for the early detection of glaucomatous optic discs. We used receiver operating characteristics (ROC) curves to illustrate the separation characteristics of different disc parameters for this purpose.
We performed computer perimetry and computerized optic disc topometry on 93 eyes of 53 subjects with glaucoma and glaucoma-related diseases. The optic disc parameters were correlated with visual field indexes, and ROC curves for the detection of glaucomatous disc changes were calculated.
According to clinical experience, the vertical cup/disc ratio was able to identify the glaucomatous eyes the most easily, whereas the neuroretinal rim area was less helpful in this regard. In terms of the correlation of optic disc parameters with visual field indexes, the rim area was the more powerful of the two. The cup volume showed neither separation of glaucomatous from normal eyes nor correlation with visual field indexes.
The vertical cup-to-disc ratio is the most suitable for screening purposes, whereas the rim area is more valuable for follow-up evaluation.
There are approximately 2 million people who have glaucoma. And about 90% of glaucoma patients have chronic type disease, and most of them do not notice of their disease. Finally they will lost their eyesight by this disease. Therefore, it is necessary to develop the auto diagnostic method for glaucoma. Our objective of this study is the development of the auto diagnostic system for the glaucoma by using fundus photograph. In our system, digitized fundus photograph is tested in personal computer, and the ratio of the area of optic disk and the area of optic disk cup (named C/D ratio) is calculated and evaluated automatically. And then this system can checkup subject condition for glaucoma. In this paper, we will discuss our auto diagnostic system for the glaucoma.