Figure 7 - uploaded by Agus Harjoko
Content may be subject to copyright.
Notching Nerve fiber layer hemorrhage appears as a red line that is parallel or close to the surface area dics. Hemorrhage is possible contained in the neuroretinal rim area or PPA. The example of hemorrhage is shown in Figure 8.
Source publication
Glaucoma is an eye disease that is the second most common cause of blindness in worldwide. The characteristic of glaucoma are high eye pressure, loss of vision gradually which can cause blindness and damage to the structure of retina. The damages which may occur for example are structural form changes of the Optic Nerve Head (ONH) and Retinal Nerve...
Context in source publication
Context 1
... eyes and glaucoma can be distinguished based on the changes in the ONH and RNFL. Enlargement of cup size can lead to changes the value of CDR and neuroretinal rim area becomes smaller. Area neuroretinal rim thinning (notching) make void the ISNT rule. The changes in the initial stages of neuroretinal rim are located on the inferior and superior rim. Figure 7 shows the thinning of neuroretinal rim in the inferior part. Patients which is has asymmetry disc conditions between the two eyes can be a sign of the possibility that the patient suffering from glaucoma. In general, the normal eye has a different value of CDR between right and left eyes, it value is not more than 0.2. When research on glaucoma utilize computer-based image analysis can be seen that 30% of patients with glaucoma have a cup size of areas in which asymmetry [7]. The next feature is the emergence of beta-zone PPA is also one of the characteristics of the disease ...
Similar publications
Gray crescent (GC) was first described by Shields¹ as increased pigmentation in the substance of the optic nerve head. In contrast to peripapillary atrophy, which is noted along and external to the clinical disc margin, angiographic findings indicate that GC represents a pigmented portion of the neuroretinal rim.¹ The main clinical importance of GC...
Citations
... Clinical manifestations of glaucoma include visible anatomical changes that appear within the head of optic nerve (ONH) such as lamina cribrosa sheet thinning along with posterior bowing in its head -these characteristics should help doctors make educated clinical judgments of this neuropathy condition. To make informed clinical judgements regarding glaucomatous optic neuropathies it's essential that an in-depth investigation of symptoms will take place before making clinical judgements about any specific cases glaucomatous optic neuropathies is conducted [1,2]. ...
Glaucoma, an eye condition marked by elevated eye pressure, is one of the leading causes of complete blindness for those affected. Early intervention through treatment and screening programs for glaucoma may reduce its detrimental consequences and help keep people seeing clearly. Glaucoma testing can be complex, and finding qualified healthcare providers to conduct assessments may prove challenging. Delays in diagnosis and treatment lead to an increasing global population suffering blindness or vision impairment. An automated screening system must be created quickly to address the limitations of existing manual screening methods, enabling early detection and treatment of abnormalities within either the Optic Cup (OC), Optic Disc or both eye regions. Accurate classification has become even more challenging as abnormalities overlap visually with the natural colour of eye tissue. This research paper introduces an automated framework designed to detect glaucoma. Our approach involves two stages-segmentation and classification-both crucial for an accurate diagnosis. At UNet++ we have developed a novel initial segmentation architecture combining the Grey Wolf optimization algorithm and UNet++ architecture specifically tailored for extracting optic disk from retinal fundus images. This approach uses an automatic evolutionary model which intelligently determines optimal and precise network configuration parameters through the Grey Wolf Optimization Algorithm (GWOA). Once the segmentation is complete, for the accurate classification of glaucoma, we utilize CapsNet (an advanced deep learning architecture known for its effectiveness in image recognition tasks) for this task. Our proposed method achieves an outstanding accuracy rate of 98.23%-surpassing other approaches and highlighting its power to enhance the accuracy and efficiency in diagnosing glaucoma. This remarkable feat highlights our automated system's potential to improve accuracy and efficiency when diagnosing this condition.
... Glaucoma detection or classification is greatly influenced by the feature extraction method, feature selection, and what features are used. In general, there are two groups of features used for glaucoma detection, namely morphological features and non-morphological features (image-based features) [25]. ...
Glaucoma is an eye disease that is the second leading cause of blindness.Examination of glaucoma by an ophthalmologist is usually done by observingthe retinal image directly. Observations from one doctor to another may differ,depending on their educational background, experience, and psychologicalcondition. Therefore, a glaucoma detection system based on digital imageprocessing is needed. The detection or classification of glaucoma with digitalimage processing is strongly influenced by the feature extraction method,feature selection, and the type of features used. Many researchers have carriedout various kinds of feature extraction for glaucoma detection systems whoseaccuracy needs to be improved. In general, there are two groups of features,namely morphological features and non-morphological features (image-basedfeatures). In this study, it is proposed to detect glaucoma using texture features,namely the GLCM feature extraction method, histograms, and the combinedGLCM-histogram extraction method. The GLCM method uses 5 features andthe Histogram uses 6 features. To distinguish between glaucoma and non-glaucoma eyes, the multi-layer perceptron (MLP) artificial neural networkmodel serves as a classifier. The data used in this study consisted of 136 fundusimages (66 normal images and 70 images affected by glaucoma). Theperformance obtained with this approach is an accuracy of 93.4%, a sensitivityof 86.6%, and a specificity of 100%
(PDF) Mix histogram and gray level co-occurrence matrix to improve glaucoma prediction machine learning. Available from: https://www.researchgate.net/publication/367190952_Mix_histogram_and_gray_level_co-occurrence_matrix_to_improve_glaucoma_prediction_machine_learning [accessed Feb 25 2023].
... According to the World Health Organization (WHO), more than 76 million people suffered from glaucoma in 2020, which is expected to increase to 111.8 million by 2040 [1]. Because glaucoma has no noticeable symptoms in the early stage, it is nicknamed the silent thief of sight [2], and 90% of glaucoma is not detected early. If glaucoma patients are not diagnosed and treated in time, they may be permanently blind as the optic nerve is damaged. ...
Among various eye diseases, glaucoma is one of the leading causes of blindness. Glaucoma is also one of the most common eye diseases in Taiwan. Glaucoma screenings can use optical coherence tomography (OCT) to locate areas in which the retinal nerve fiber layer is thinning. However, because OCT equipment is costly, only large hospitals with well-equipped facilities will have OCT, and regular eye clinics cannot afford such expensive equipment. This has caused many glaucoma patients to worsen because they cannot get an early diagnosis in regular eye clinics in time. This paper proposes a method of using a generative adversarial network (GAN) to generate corresponding OCT images from fundus images to assist family doctors in judging whether further examination is needed based on the generated OCT images to achieve early detection and treatment of glaucoma. In addition, in order to improve the classification accuracy of the system deployed in different hospitals or clinics, this paper also proposes to use the incremental training method to fine-tune the model. The model can be quickly applied by adding a small number of images from a specific clinic or hospital. Experimental results show that the cosine similarity between the generated OCT image and the real OCT image is 97.8%. Combined with the proposed transfer learning method, the classification accuracy of the classification model reaches 83.17%. As well as the use of the incremental method, the accuracy of identifying glaucoma is approximately 78.94%, which is 8.77% higher than the 70.17% accuracy of the initial model. Experimental results show the effectiveness and feasibility of our proposed method.
... Glaucoma has no symptoms at the beginning stage and slowly progresses over many years. Therefore, glaucoma is not recognized by many people until the damage is already severe in the ONH [18]. Some people are diagnosed with glaucoma during a routine eye test. ...
Glaucoma is a common eye disease that damages an optic nerve due to abnormally high pressure inside the eye. Glaucoma can cause visual impairments and eventually lead to blindness. There is no appropriate treatment to prevent blindness when the optic nerve is damaged. Therefore, an early diagnosis is important to prevent vision loss from glaucoma. An automated framework for glaucoma screening from fundus images is advantageous. It can facilitate the ophthalmologist in the diagnosis and prevent blindness. Many glaucoma screening algorithms have been developed based on a clinical indicator, the cup-to-disc ratio (CDR). However, these algorithms have some limitations for myopia and genetically large optic cup eyes. Therefore, this paper proposes a framework for glaucoma screening that can be applied even in myopia. The 2 clinical indicators, cup-to-disc ratio (CDR) and neuroretinal rim area rule (inferior > superior > nasal > temporal (ISNT)), are applied in the proposed screening algorithm for accurate glaucoma assessment. Moreover, the automatic classification of glaucoma or non-glaucoma from fundus images is performed by a support vector machine (SVM). Therefore, the experimental results show that the proposed screening algorithm can accurately classify glaucoma to normal eyes or myopic eyes. HIGHLIGHTS A framework for glaucoma screening is proposed to classify myopia and genetically large optic cup eyes Two clinical indicators, cup-to-disc ratio (CDR) and neuroretinal rim area rule (inferior > superior > nasal > temporal (ISNT)), are applied in the proposed screening algorithm for accurate glaucoma assessment Automatic classification of glaucoma or non-glaucoma from fundus images is performed by a support vector machine (SVM) The proposed framework can provide less time consuming, cost-effective and physician independent system for glaucoma screening GRAPHICAL ABSTRACT
... It can lead to total damage to the optic nerves and cause vision loss, if glaucoma is left untreated. is gradual and complete damage to the optic nerves is often followed by only mild or no symptoms, so it is known as the "sneak thief of sight" [2]. ...
... e changes can be used as a parameter for the early indicator of glaucoma. e ONH transmits visual information from retina to the brain [2]. Figure 1 shows the retinal fundus images. ...
... Retinal fundus images: (a) healthy eye, (b) early glaucoma, (c) moderate glaucoma, and (d) deep glaucoma[2]. Structure of optic nerve head: (a) normal and (b) glaucoma[3]. ...
Glaucoma is the second most common cause for blindness around the world and the third most common in Europe and the USA. Around 78 million people are presently living with glaucoma (2020). It is expected that 111.8 million people will have glaucoma by the year 2040. 90% of glaucoma is undetected in developing nations. It is essential to develop a glaucoma detection system for early diagnosis. In this research, early prediction of glaucoma using deep learning technique is proposed. In this proposed deep learning model, the ORIGA dataset is used for the evaluation of glaucoma images. The U-Net architecture based on deep learning algorithm is implemented for optic cup segmentation and a pretrained transfer learning model; DenseNet-201 is used for feature extraction along with deep convolution neural network (DCNN). The DCNN approach is used for the classification, where the final results will be representing whether the glaucoma infected or not. The primary objective of this research is to detect the glaucoma using the retinal fundus images, which can be useful to determine if the patient was affected by glaucoma or not. The result of this model can be positive or negative based on the outcome detected as infected by glaucoma or not. The model is evaluated using parameters such as accuracy, precision, recall, specificity, and F-measure. Also, a comparative analysis is conducted for the validation of the model proposed. The output is compared to other current deep learning models used for CNN classification, such as VGG-19, Inception ResNet, ResNet 152v2, and DenseNet-169. The proposed model achieved 98.82% accuracy in training and 96.90% in testing. Overall, the performance of the proposed model is better in all the analysis.
... ) Illustrates the important anatomical structures present in the retinal image[19][20].Figure 2b) Illustrates the healthy fundus image (blood vessels are clear).Figure 2c) illustrates the neovascular image (blood vessels are damaged due to diabetes).Figure 2d) shows the Histogram of healthy retina. It is not uniform due to randomly distributed pixels. ...
... Another alternative that can be used to detect types of facial skin diseases is to use digital images [3], [4]. The use of digital images in the object classification process has been implemented in various medical and non-medical fields [5]- [7]. A digital image of the problem skin is extracted to obtain its characteristics. ...
... The current software algorithms for CDR detection use various features including color (color cup), blood vessel anatomy (contour cup), best fit shapes (arbitrary cup), edge detection, or manual marking for identification. [25][26][27][28] A few software have gone a step further to try and detect the minimum rim width of the neuroretinal rim (NRR). [8,20,26] This gives a distinct advantage over the CDR alone as it may be used to derive the disc damage likelihood scale (DDLS). ...
Purpose:
To clinically validate a new automated glaucoma diagnosis software RIA-G.
Methods:
A double-blinded study was conducted where 229 valid random fundus images were evaluated independently by RIA-G and three expert ophthalmologists. Optic nerve head parameters [vertical and horizontal cup-disc ratio (CDR) and neuroretinal rim (NRR) changes] were quantified. Disc damage likelihood scale (DDLS) staging and presence of glaucoma were noted. The software output was compared with consensus values of ophthalmologists.
Results:
Mean difference between the vertical CDR output by RIA-G and the ophthalmologists was - 0.004 ± 0.1. Good agreement and strong correlation existed between the two [interclass correlation coefficient (ICC) 0.79; r = 0.77, P < 0.005]. Mean difference for horizontal CDR was - 0.07 ± 0.13 with a moderate to strong agreement and correlation (ICC 0.48; r = 0.61, P < 0.05). Experts and RIA-G found a violation of the inferior-superior NRR in 47 and 54 images, respectively (Cohen's kappa = 0.56 ± 0.07). RIA-G accurately detected DDLS in 66.2% cases, while in 93.8% cases, output was within ± 1 stage (ICC 0.51). Sensitivity and specificity of RIA-G to diagnose glaucomatous neuropathy were 82.3% and 91.8%, respectively. Overall agreement between RIA-G and experts for glaucoma diagnosis was good (Cohen's kappa = 0.62 ± 0.07). Overall accuracy of RIA-G to detect glaucomatous neuropathy was 90.3%. A detection error rate of 5% was noted.
Conclusion:
RIA-G showed good agreement with the experts and proved to be a reliable software for detecting glaucomatous optic neuropathy. The ability to quantify optic nerve head parameters from simple fundus photographs will prove particularly useful in glaucoma screening, where no direct patient-doctor contact is established.
... M. [22] . Anindita et al. proposed a review paper which consisted of all possible features that can be extracted from the retinal image and can be used as a parameter to detect glaucoma disease [23]. ...
... Anindita Septiarini et al. [22] 2015, had proposed that Glaucoma was an eye infection that is the second most regular reason for visual impairment. The automatic feature extraction method in retinal fundus images which can be applied for detection or classification of glaucoma. ...
Glaucoma is commonly a genuine visual disorder and it causes permanent blindness if it couldn't be identified and treated at the early stage. The main intention of this paper is to classify the retinal fundus image as glaucoma or normal image using artificial intelligence technique. At first, from the RGB input retinal fundus image, the green channel is chosen for preprocessing. In the preprocessing assignment Anti forensic contrast augmentation technique is applied to the green band image for proper color enhancement. After preprocessing the fundus image, Fuzzy C-Means centroid optimization technique is utilized as a part to segment the section of optic disc. In the next step, the significant features are extracted using two-feature extraction techniques such as Cup to Disc Ratio (CDR) and Neuroretinal Rim Ratio (NRR) in inferior, superior, nasal and temporal (ISNT) quadrant that is to state ISNT parameter regions. Based on the above two features, feed forward back-propagation neural network (FFBN) is applied to categorize the input image as glaucoma or normal image. Additionally various optimization techniques such as Artificial Fish Swarm Optimization (AFSO), Firefly Optimization (FFO) and Particle Swarm Optimization (PSO) are applied separately for optimizing the hidden layer and neuron of FFBN Classification. In the outcome the AFSO technique evaluation metric has given better result comparatively as Accuracy 84%, Sensitivity 84%, and Specificity 84%. Keywords-Glaucoma, Anti forensic contrast enhancement, Fuzzy C-Means clustering, Cup to Disc Ratio (CDR), Neuroretinal Rim (NRR), feed forward back propagation neural network (FFBN) and Artificial Fish Swarm Optimization (AFSO).
