2723 http://annalsofrscb.ro
A Review on Recent Development for Diagnosis of Glaucoma
M.Ponni Bala1, P.Rajalakshmi2,A.Maria Sindhuja3,S.Naganandhini4
1
Associate Professor,Department of Electronics and Instrumentation Engineering, Kongu Engineering College. Perundurai, [email protected]
2
PG student, Department of Electronics and Instrumentation Engineering, Kongu Engineering College. Perundurai, [email protected]
3
Department of Electrical and Electronics Engineering, M.Kumarasamy College of Engineering, Karur. [email protected]
4
Department of Computer Applications, PSNA College of Engineering and Technology, Dindigul.
Abstract
Glaucoma is the prominent retinal diseases which amends the Optic Nerve Head in the retina of human eye. It cannot be completely treated, but earlier diagnosis prevents vision loss. In the medical domain, broad array of applications can be carried out using an image processing techniques. Diagnosis of retinal diseases is the major employment in image processing techniques. Recently the new non-invasive modality called Optical Coherence Tomography Angiography which could be applied for better analysis of eye diseases such as Age Related Macular Degeneration, Glaucoma and Diabetic Retinopathy. This paper deals with the exploit of Deep Learning techniques for Glaucoma diagnosis and its automated diagnosis system that helps the physicians to lighten their task crucially.
Key words-Glaucoma, Fundus Image, Retinal Nerve Fiber Layer (RNFL), Angio-OCT images, Vessel density,Deep Learning Techniques
1 Introduction
Glaucoma is one of leading retinal diseases results in visual impairments and its predicted to affect more than 118.2million people by the year 2040 [1]. Earlier diagnosis can prevent the vision loss. Thus, it is essential to do eye screening for detecting the glaucoma at earlier stage[2]. The major reason for Glaucoma is the frequent thinning of Retinal Nerve Fiber Layer(RNFL)[3]. Reducing the Intra Ocular pressure(IoP) is the promising treatment for better progression [4] . The typical treatment comprises of regular optometrist checkup, doubtful persons needs to perform a supplementary tests for final verification[5,6]. The entire study usually includes entire record of a patient and comprehensive eye examination [7]. However, these techniques has major drawbacks that it is a time consuming process and its available only in high cost[8].Currently, the fundus images, OCT modality and Angio-OCT images are commonly employed modality for examining the optic nerve.
The ratio of optic cup and optic diskis the main parameter to assess the Optic Nerve Head (ONH).
When the optic nerve fibers gradually disappears, it may leads to glaucomatous stage. Fundus images intended feature such as Cup to Disk Ratio for classifying severity level of Glaucoma[9-11]. OCTA modality intended features such as Capillary, parafoveal density, vessel density and RNFL thickness measurements. OCT measured thickness parameter for classifying normal and eyes with mild to severe Glaucoma[12,13].Parafoveal density shows good progression with excellent accuracy. Parafoveal superficial vessel density in healthy eyes is(48.10±2.82%) whereas in glaucomatous stage vessel density
2724 http://annalsofrscb.ro
may reduce[14-16].
The prime objective of the analysis is to examine the better modality for screening and detecting severity level of glaucoma. Section 2 describes the different Retinal Imaging Techniques. Section 3 describes about the types of Glaucoma. Section 4 describes the Glaucoma diagnosis method and treatment for glaucoma. Section 5 provides information about the Glaucoma databases. Section 6 describes about the deep learning techniques and section 7 describes about the conclusion.
2. Different Retinal Imaging Techniques
Bio-medical applications such as MRI, CT scan and X-rays were used as modalities to visualize interior anatomy of the organ. Various parameters are evaluated and the results are acceptable if the results are predicted same as that of clinical results recommended by an ophthalmologist. OCT , OCTA and fundus images are the imaging modalities used to diagnosis the Glaucoma[17].These tools are immense todiagnose and treat in advance to prevent the vision loss.
2.1 Optical Coherence Tomography
OCT imaging modality is a non intrusive technique based on the law of low coherence interferometry and allows ophthalmologist to map and measure the retinal thickness[18,19]. However, this helps in early detection many ophthalmic disorders such as, macular edema and Glaucoma [20]. Optic Cup is the white region and its is slightly brighter region in the center of disc [21]. Disk and Cup region depicts in Figure1.
Fig 1.Fundus(above) and OCT(below) images [22]
2.2 Fundus Imaging Technique
Fundus imaging modality are the frequent methodology to capture retinal images[23]. In this modality, the optic disk comprises of bright and center area i.e., Optic cup depicts in Figure 2.
2725 http://annalsofrscb.ro
Fig.2 a) Normal Fundus image and b) Glaucoma iamge[24].
2.3 Optical Coherence Tomography Angiography
Angio-OCT images produces angiography images in seconds[25]. Angio OCT images provides detail report about both the structural and functional information[26].This technique demonstrates the ability of visualize the blood flow in both choroidal and retinal levels with high resolution[27].In addition to this choroidal and parafoveal vessel density can be quantified[28]. OCTA techniques has the potential to diagnose the variety of diseases such as Myopia[29].
3 Types of Glaucoma
The vessel density changes will be helpful for diagnosis of glaucoma and various types of glaucoma stages[30]. Thus, paying more attention on the vessel density parameters for earlier diagnosis[31,32].Angio OCT modality helps to determine the vessel density effective for better diagnosis.[33,34].Glaucoma comprises of several types among which majority percentage of the affected community suffer from Angle Closure Glaucoma[35,36][72][73]. Some other types of glaucoma are congenital, pigmentary, steroid induced types of glaucoma [37].Table 1shows the summary of Progression, Causes and symptoms of various types of Glaucoma.
Table 1 Summary of Several types of Glaucoma Author &
(Year)
Types of Glaucoma
Evolution Causes Symptoms
Philip, S., et al.,
& (2019)[38]
Open-angle glaucoma
It is the common form and its pain free
It has no symptoms at earlier stage. So it‟s known as „Silent Thief of sight‟
Peripheral vision may slowly damage tends to vision loss
Rong., et al.&(2020) [39]
Angle- closure glaucoma
Angle closure glaucoma is more painful
compared to other types.
This form of glaucoma requires instantaneous treatment
vomiting, obscured or indistinct vision
2726 http://annalsofrscb.ro
Igarashi, N., et al.,&(2019) [40]
Low-tension glaucoma
This form of glaucoma has drawback that even eye pressure is normal but optic nerves may get damaged.
This occurs mainly due to lack of blood flow
More vulnerable in damaging theoptic nerves. It is difficult to classify Low tension glaucoma
Nakano, H., et al.,& (2020) [41]
Exfoliative glaucoma
Mainly occurs due toexfoliation disorder.
Laser treatment prevents vision loss
Excessive whitish fluidon the lens and retina blocks the eye drainage canal results in increased intra- ocular pressure Simcoe, M.J., et
al.,
&
(2020) [42]
Pigmentary glaucoma
This type of glaucoma mainly affects the young and near-sighted
Iris get broken upand pigments leaked in the drainage system
slight agonyand hazy vision are the common symptoms for this type of glaucoma
Mursch- Edlmayr, A., et al., & (2020)[43]
Neovascular glaucoma
The drainagesystem may gets affect by diabetes that causes theintra-ocular pressure to increase
The fluid‟s drainage structure getsblocked
-
Badawi, A.H., et al.,&(2019) [44]
Congenital glaucoma
Occurs in eye frombirth. This type of glaucoma can be analyzed in child age.
It occurs mostly for child especially boys.
Zhang, S., et al.,
& (2019) [45]
Secondary glaucoma
This type of glaucoma occurs when the pressure is increased.
Irritation in the eye and may cause damage
This type of glaucoma occurs frequently during a surgical time.
Goldberg, I.et al.,&
(2020) [46]
Chronic glaucoma
Vision loss occurs suddenly
For preventing vision loss, early diagnosis is necessary
It cannot be cured.
Križaj, & (2019) [47]
Acute glaucoma
Liquidin the eye may totally obstructed.
This type of glaucoma does not cause any sudden pain
The symptoms for this type are red eyes and vomiting.
4. Clinical Diagnosis for Glaucoma
Guidelines for diagnosis, organization and anticipation were given by the Australian National Health and Medical Research Council in the year 2010[48]. For earlier diagnosis, a blend of various tests may become valuable[49]. To analyse the severity of glaucoma at frequent levels, Optic nerve evaluation (ONE) and visual field testing (VFT) are proficient. It is essential to analyse the efficiency of the treatment to determine whether treatment is necessary or not [50]. The main objective of the inspection is to estimate the level of severity period increased within a certain period of time[51][70][71]. Figure 3
2727 http://annalsofrscb.ro
depictsthe different tests employed in Glaucoma diagnosis.
Fig 3.Various test used in Glaucoma diagnosis[37]
4.1Treatment for Glaucoma
The treatment involves trabeculectomy, laser surgery and implantation of drainage canal. Figure 4 shows the various types of treatments.
Fig 4 Treatments for Glaucoma [52]
5. Database
Some of the freely accessible datasets available for diagnosis of glaucoma are discussed in Table.2 Table 2 Publicly available datasets for glaucoma diagnosis
Datasets Total No. of images Origin
DRIVE 40 Diabetic retinopathy research program,
Netherlands
MESSIDOR 1200 French Ministers of research and defence
ORIGA 650 Singapore Eye Research Institute
REFUGE 1200 Zhongshan Ophthalmic Center, Sun Yat-
sen University, China Combination of
tests for early diagnosis
Evaluate Optic Nerve (opthalmoscopy)
Inspect drainage angle of eye (Gonioscopy)
Short wavelength
automated periometry
Test the visual field of each eye (perimetry)
Standard automated
perimetry
Measure eye pressure(Tonometry)
Confocal Scanning LaserOpthalmos
copy
Scanning Laser Polarimetry
Frequency Doubling Technology
Perimetry
Glaucoma treatments
Drainage implants Laser surgery Eye drops
2728 http://annalsofrscb.ro
DRISHTI-GS 101 Arvind Eye hospital, Mumbai
6. Deep Learning models for Diagnosis of Glaucoma
Several enhancement methodologies are employed for the accurate diagnosis[53][69]. Various types of databases have been gathered comprises by numerous amount of data. Therefore while applying several classifiers; the accuracy of the modalities can be determined. Figure 5 shows various classifiers employed in diagnosis.
Fig 5 Classifiers used in glaucoma diagnosis Classifiers
Used
Decision Tree classifier Generalized
additive model
Trained Neural Networks
Machine learning Classifier Linear
Discriminative Analysis
Machine Learning Classifier Artificial
Neural Network
Naïve Bayesian Classifier Recrusive
partioning
&Recrusion
Support Vector Machine
Automated
Classifier Random
Forest Classifier
2729 http://annalsofrscb.ro
The literature analysis on several segmentation and classification techniques over retinal imaging techniques and some of the performance are discussed in the Table 3. The performance metrics such as Accuracy, Sensitivity and Specificity are summarized for different methodologies. It is evident that each methodology has both merits and demerits. The clustering based approach works well in eliminating the noise. The Level based technique is generally employed for sharp corners and it acquires better efficiency.
Even though it is efficient, it consumes much time and sometimes may consequences below or above- segmentation level. The threshold-based methodology is quick process. But threshold-based methodology cannot provide better results for wider level of pixels.
From the above analysis, clustering-based technique provides better results. The K-Nearest Neighbour algorithm is very efficient for training large datasets, but its calculation time is very high.
Support Vector Machine (SVM) has high searching capability when compared to other classifiers, although it is not efficient for binary classification. Therefore the SVM provides better progression while examining all other classifiers. Though, every technique has its merits and demerits, but enhanced methodology need to be anticipated for the Glaucoma diagnosis.
Table 3Summary of Various methodologies for Glaucoma Diagnosis Refer
ence
Databas e
Imagin g modalit
y
Technique s
Performance Metrics Remarks Accu
racy
Speci ficity
Sensi tivity [54] Rim-One
Dhristi- GS
Fundus images
Fuzzy C- Means methodolog y
93.47 91.56 - LARKIFCM methodology consumes less time and provides better progression [55] Messidor Fundus
images
Clustering- based approach
90.00 - - Residual noise appears even after
segmentation process [56] DRIVE Fundus
images
Local Binary Pattern
96 96 96 Needs to
extract more features to improve the classification [57] SCES Fundus
images
Disc-aware ensemble network
84.29 84.78 83.29 Earlier diagnosis of glaucoma by collecting contextual information of the Optic Disk
2730 http://annalsofrscb.ro
[58] ORIGA dataset
Fundus images
Deep object detection network
- - - Combination of
localization and
segmentation are done in a particular method [59] DRIVE Fundus
images
Adaptive thresholdin g and SVM classifier
93.36 85.56 - This technique provides better progression in vessel
extraction [60] Mendele
y
OCT images
Structure tensors to extract candidate layer pixels, Convolutio n Neural Network Graph Set Theory.
94.6, 94.07 94.68 Need to extend the
segmentation of retinal layers to higher dimensional level.
[61] DIARET DB1
OCT images
clustering kernel density estimation and Support vector classifier
97.25 - - SVM
dependent intelligence grounded on quadratic normalization
[62] Local Dataset
OCT images
Local binary pattern and Support vector machine.
99.30 96.64 98.83 Performance based on all RGB channels.
[63] Electroni c
research
&
medical records, Duke Universit y Vision
OCT images
Segmentati on-free Deep Learning technique
81 95 65.71 Better progression than usual RNFL thickness parameters even diagnosis at earlier stage.
2731 http://annalsofrscb.ro
[64] Mendele y data
OCT images
&
Fundus images
Automated Segmentati on
algorithm
- - - This study
reveals that for each OCT modality there is a equivalent fundus modality with marginal note for
understanding purposes [65] Zenodo OCT
images
Extra tree Classifier, Feature agnostic approach
95 - = Extra tree
classifier is used due to the high amount of datas.
[66] Dryad (Private dataset) .
OCT images
Multiple classifiers such as Random Forest and SVM classifier
98 98.3 97.1 Developed an synthesized model from original features and yields an higher accuracy.
[67] Local hospital
OCTA images
k-Means Segmentati on,SVM classifier
90 94.44 96.67 Features such as capillary loss shows better progression compared to RNFL thickness [68] All types
of dataset from Angio octa modality
OCTA images
Split Spectrum Amplitude Decorrelati on
Angiograph y algorithm
96 - - Vessel Density
is more changeable feature and possibly reflects when Intra Occular Pressure changes
7.Conclusion
2732 http://annalsofrscb.ro
This paper embraces various retinal imaging modalities, segmentation and classification techniques employed for the glaucoma diagnosis. Here we epitomized the disputations that came over while segmentation and classifications. Researchers examined numerous features for classification purposes but still more texture based features are required to increase the performance and diagnosis. From the analysis, for classification purposes deep learning techniques acquires better progression when compared to image processing methodologies. Finally thissurvey concludes that it is essential to incorporate hybrid techniques for segmentation and classification of Glaucoma images to attain better progression.
REFERENCES
1. Al-Bander, B., Williams, B. M., Al-Nuaimy, W., Al-Taee, M. A., Pratt, H., & Zheng, Y. (2018). Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis.
Symmetry, 10(4), 87.
2. Abbas, Q. (2017). Glaucoma-deep: detection of glaucoma eye disease on retinal fundus images using deep learning. Int J Adv Comput Sci Appl, 8(6), 41-45.
3. Kim, Y. K., Jeoung, J. W., & Park, K. H. (2017). Inferior macular damage in glaucoma: its relationship to retinal nerve fiber layer defect in macular vulnerability zone. Journal of glaucoma, 26(2), 126-132.
4. An, G., Omodaka, K., Hashimoto, K., Tsuda, S., Shiga, Y., Takada, N., et al. (2019). Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images. Journal of healthcare engineering, 2019.
5. Gómez-Valverde, J. J., Antón, A., Fatti, G., Liefers, B., Herranz, A., Santos, A., et al. (2019). Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomedical optics express, 10(2), 892-913.
6. Ponnibala, M., Priyanka, E. B., & Thangavel, S. (2021). Proliferative Diabetic Retinopathy Diagnostic Investigation Using Retinal Blood Vessels Mining Technique. Sensing and Imaging, 22(1), 10, doi:10.1007/s11220-021-00331-9.
7. Kansal, V., Armstrong, J. J., Pintwala, R., & Hutnik, C. (2018). Optical coherence tomography for glaucoma diagnosis: an evidence based meta-analysis. PloS one, 13(1), e0190621.
8. Liao, W., Zou, B., Zhao, R., Chen, Y., He, Z., & Zhou, M. (2019). Clinical Interpretable Deep Learning Model for Glaucoma Diagnosis. IEEE journal of biomedical and health informatics, 24(5), 1405-1412.
9. Soltani, A., Battikh, T., Jabri, I., & Lakhoua, N. (2018). A new expert system based on fuzzy logic and image processing algorithms for early glaucoma diagnosis. Biomedical Signal Processing and Control, 40, 366-377.
10. Khan, M. W., Sharif, M., Yasmin, M., & Fernandes, S. L. (2016). A new approach of cup to disk ratio based glaucoma detection using fundus images. Journal of Integrated Design and Process Science, 20(1), 77-94.
11. Keerthanashree, T., & Bala, M. P. (2016). Extraction of Retinal Features in Fundus Images for Glaucoma Diagnosis. Current Trends in Information Technology, 6(1), 21-28.
12. Bowd, C., Belghith, A., Proudfoot, J. A., Zangwill, L. M., Christopher, M., Goldbaum, M. H., et al.
(2020). Gradient Bosting Classifiers Combining Vessel Density and Tissue Thickness Measurements for Classifying Early to Moderate Glaucoma. American Journal of Ophthalmology.
13. Moghimi, S., Bowd, C., Zangwill, L. M., Penteado, R. C., Hasenstab, K., Hou, H., et al. (2019).
Measurement floors and dynamic ranges of OCT and OCT angiography in glaucoma. Ophthalmology, 126(7), 980-988.
14. Moghimi, S., Zangwill, L. M., Penteado, R. C., Hasenstab, K., Ghahari, E., Hou, H., et al. (2018).
2733 http://annalsofrscb.ro
Macular and optic nerve head vessel density and progressive retinal nerve fiber layer loss in glaucoma.
Ophthalmology, 125(11), 1720-1728.
15. Akagi, T., Iida, Y., Nakanishi, H., Terada, N., Morooka, S., Yamada, H., et al. (2016). Microvascular density in glaucomatous eyes with hemifield visual field defects: an optical coherence tomography angiography study. American Journal of Ophthalmology, 168, 237-249.
16. Suh, M. H., Zangwill, L. M., Manalastas, P. I. C., Belghith, A., Yarmohammadi, A., Medeiros, F. A., et al. (2016). Deep retinal layer microvasculature dropout detected by the optical coherence tomography angiography in glaucoma. Ophthalmology, 123(12), 2509-2518.
17. Singh, A., Mohammed, A. R., & Zelek, J. Interpretation of deep learning using attributions: application to ophthalmic diagnosis. In Applications of Machine Learning 2020, 2020 (Vol. 11511, pp. 115110A):
International Society for Optics and Photonics
18. Meeral, M. N., Nisha, S. S., & Sathik, M. M. (2019). A COMPREHENSIVE ANALYSIS OF EDGE DETECTORS IN SD-OCT IMAGES FOR GLAUCOMA DIAGNOSIS. International Research Journal of Engineering and Technology (IRJET) e-ISSN, 2395-0056.
19. Wang, C., Jin, Y., Chen, X., & Liu, Z. (2020). Automatic Classification of Volumetric Optical Coherence Tomography Images via Recurrent Neural Network. Sensing and Imaging, 21(1), 32, doi:10.1007/s11220-020-00299-y.
20. Raja, H., Akram, M. U., Shaukat, A., Khan, S. A., Alghamdi, N., Khawaja, S. G., et al. (2020).
Extraction of Retinal Layers Through Convolution Neural Network (CNN) in an OCT Image for Glaucoma Diagnosis. Journal of Digital Imaging, 1-15.
21. Nithya, R., & Venkateswaran, N. (2015). Analysis of segmentation algorithms in colour fundus and OCT images for glaucoma detection. Indian Journal of Science and Technology, 8(24), 1.
22. Naveed, M., Ramzan, A., & Akram, M. U. Clinical and technical perspective of glaucoma detection using OCT and fundus images: a review. In 2017 1st International Conference on Next Generation Computing Applications (NextComp), 2017 (pp. 157-162): IEEE
23. Elangovan, P., & Nath, M. K. (2020). Glaucoma assessment from color fundus images using convolutional neural network. International Journal of Imaging Systems and Technology.
24. Diaz-Pinto, A., Morales, S., Naranjo, V., Köhler, T., Mossi, J. M., & Navea, A. (2019). CNNs for automatic glaucoma assessment using fundus images: an extensive validation. Biomedical engineering online, 18(1), 29.
25. Bojikian, K. D., Chen, P. P., & Wen, J. C. (2019). Optical coherence tomography angiography in glaucoma. Current opinion in ophthalmology, 30(2), 110-116.
26. Bekkers, A., Borren, N., Ederveen, V., Fokkinga, E., Andrade De Jesus, D., Sánchez Brea, L., et al.
(2020). Microvascular damage assessed by optical coherence tomography angiography for glaucoma diagnosis: a systematic review of the most discriminative regions. Acta ophthalmologica, 98(6), 537-558.
27. Spaide, R. F., Fujimoto, J. G., Waheed, N. K., Sadda, S. R., & Staurenghi, G. (2018). Optical coherence tomography angiography. Progress in retinal and eye research, 64, 1-55.
28. Garcia-Arumi Fuste, C., Peralta Iturburu, F., & Garcia-Arumi, J. (2020). Is optical coherence tomography angiography helpful in the differential diagnosis of choroidal nevus versus melanoma?
European journal of ophthalmology, 30(4), 723-729.
29. Tsai, A. S., Gan, A. T., Ting, D. S., Wong, C. W., Teo, K. Y., Tan, A. C., et al. (2020). Diabetic macular ischemia: correlation of retinal vasculature changes by optical coherence tomography angiography and functional deficit. Retina, 40(11), 2184-2190.
30. Mammo, Z., Heisler, M., Balaratnasingam, C., Lee, S., Yu, D.-Y., Mackenzie, P., et al. (2016).
Quantitative optical coherence tomography angiography of radial peripapillary capillaries in glaucoma, glaucoma suspect, and normal eyes. American Journal of Ophthalmology, 170, 41-49.
31. Chung, J. K., Hwang, Y. H., Wi, J. M., Kim, M., & Jung, J. J. (2017). Glaucoma diagnostic ability of
2734 http://annalsofrscb.ro
the optical coherence tomography angiography vessel density parameters. Current eye research, 42(11), 1458-1467.
32. Akil, H., Huang, A. S., Francis, B. A., Sadda, S. R., & Chopra, V. (2017). Retinal vessel density from optical coherence tomography angiography to differentiate early glaucoma, pre-perimetric glaucoma and normal eyes. PloS one, 12(2), e0170476.
33. Lommatzsch, C., Rothaus, K., Koch, J., Heinz, C., & Grisanti, S. (2018). OCTA vessel density changes in the macular zone in glaucomatous eyes. Graefe's Archive for Clinical and Experimental Ophthalmology, 256(8), 1499-1508.
34. Yip, V. C., Wong, H. T., Yong, V. K., Lim, B. A., Hee, O. K., Cheng, J., et al. (2019). Optical coherence tomography angiography of optic disc and macula vessel density in glaucoma and healthy eyes.
Journal of glaucoma, 28(1), 80-87.
35. Sengupta, S., Singh, A., Leopold, H. A., Gulati, T., & Lakshminarayanan, V. (2020). Ophthalmic diagnosis using deep learning with fundus images–A critical review. Artificial Intelligence in Medicine, 102, 101758.
36. Zhu, X., Zeng, W., Wu, S., Chen, X., Zheng, T., & Ke, M. (2019). Measurement of retinal changes in primary acute angle closure Glaucoma under different durations of symptoms. Journal of Ophthalmology, 2019.
37. Saba, T., Bokhari, S. T. F., Sharif, M., Yasmin, M., & Raza, M. (2018). Fundus image classification methods for the detection of glaucoma: A review. Microscopy research and technique, 81(10), 1105-1121.
38. Philip, S., Najafi, A., Tantraworasin, A., Chui, T. Y., Rosen, R. B., & Ritch, R. (2019). Macula vessel density and foveal avascular zone parameters in exfoliation glaucoma compared to primary open-angle glaucoma. Investigative ophthalmology & visual science, 60(4), 1244-1253.
39. Rong, X., Cai, Y., Li, M., Chen, X., Kang, L., & Yang, L. (2020). Relationship between nailfold capillary morphology and retinal thickness and retinal vessel density in primary open‐ angle and angle‐ closure glaucoma. Acta Ophthalmologica.
40. Igarashi, N., Honjo, M., Asano, S., Takagi, K., & Aihara, M. (2019). Optic disc cupping characteristics of normal pressure hydrocephalus patients with normal-tension glaucoma. Scientific reports, 9(1), 1-9.
41. Nakano, H., Togano, T., Sakaue, Y., Suetaka, A., Iikawa, R., Nakano, R., et al. (2020). Clinical Features of Patients with Exfoliation Glaucoma Requiring Surgical Intervention. Journal of Ophthalmology, 2020.
42. Simcoe, M. J., Weisschuh, N., Wissinger, B., Hysi, P. G., & Hammond, C. J. (2020). Genetic Heritability of Pigmentary Glaucoma and Associations With Other Eye Phenotypes. JAMA ophthalmology, 138(3), 294-299.
43. Mursch-Edlmayr, A., Pickl, L., Calzetti, G., Waser, K., Wendelstein, J., Beka, S., et al. (2020).
Comparison of neurovascular coupling between normal tension glaucoma patients and healthy individuals with Laser Speckle Flowgraphy. Current eye research, 1-5.
44. Badawi, A. H., Al-Muhaylib, A. A., Al Owaifeer, A. M., Al-Essa, R. S., & Al-Shahwan, S. A. (2019).
Primary congenital glaucoma: An updated review. Saudi Journal of Ophthalmology, 33(4), 382-388.
45. Zhang, S., Wang, J., Li, Y., Liu, Y., He, L., & Xia, X. (2019). The role of primary intraocular lens implantation in the risk of secondary glaucoma following congenital cataract surgery: A systematic review and meta-analysis. PloS one, 14(4), e0214684.
46. Goldberg, I., Ritch, R., & Goldmann, N. (2020). Facilitating Patient-Ophthalmologist Dialog: A Call for a Patient-focused Classification of Glaucoma Diagnosis. Journal of glaucoma, 29(5), 329-330.
47. Križaj, D. (2019). What is glaucoma? In Webvision: The Organization of the Retina and Visual System [Internet]: University of Utah Health Sciences Center.
48. Jamous, K. F., Kalloniatis, M., Hayen, A., Mitchell, P., Stapleton, F. J., & Zangerl, B. (2014).
Application of clinical techniques relevant for glaucoma assessment by optometrists: concordance with
2735 http://annalsofrscb.ro
guidelines. Ophthalmic and Physiological Optics, 34(5), 580-591.
49. Li, L., Xu, M., Wang, X., Jiang, L., & Liu, H. Attention based glaucoma detection: A large-scale database and CNN Model. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019 (pp. 10571-10580)
50. Maetschke, S., Antony, B., Ishikawa, H., Wollstein, G., Schuman, J., & Garnavi, R. (2019). Inference of visual field test performance from OCT volumes using deep learning. arXiv preprint arXiv:1908.01428.
51. Kyei, S., Aberor, J., Assiamah, F., & Kwarteng, M. A. (2020). Optical coherence tomography indices in the diagnosis and discrimination of stages of primary open-angle glaucoma in an African population.
International ophthalmology, 1-10.
52. Yadav, K. S., Rajpurohit, R., & Sharma, S. (2019). Glaucoma: current treatment and impact of advanced drug delivery systems. Life sciences, 221, 362-376.
53. Vijayalakshmi, D., Nath, M. K., & Acharya, O. P. (2020). A Comprehensive Survey on Image Contrast Enhancement Techniques in Spatial Domain. Sensing and Imaging, 21(1), 40, doi:10.1007/s11220-020- 00305-3.
54. Thakur, N., & Juneja, M. (2019). Optic disc and optic cup segmentation from retinal images using hybrid approach. Expert Systems with Applications, 127, 308-322.
55. Cheng, J., Liu, J., Xu, Y., Yin, F., Wong, D. W. K., Tan, N.-M., et al. (2013). Superpixel classification based optic disc and optic cup segmentation for glaucoma screening. IEEE transactions on medical imaging, 32(6), 1019-1032.
56. Khunger, M., Choudhury, T., Satapathy, S. C., & Ting, K.-C. (2019). Automated detection of glaucoma using image processing techniques. Emerging Technologies in Data Mining and Information Security, 323-335.
57. Fu, H., Cheng, J., Xu, Y., Zhang, C., Wong, D. W. K., Liu, J., et al. (2018). Disc-aware ensemble network for glaucoma screening from fundus image. IEEE transactions on medical imaging, 37(11), 2493- 2501.
58. Sun, X., Xu, Y., Tan, M., Fu, H., Zhao, W., You, T., et al. (2018). Localizing optic disc and cup for glaucoma screening via deep object detection networks. In Computational pathology and ophthalmic medical image analysis (pp. 236-244): Springer.
59. Xu, L., & Luo, S. (2010). A novel method for blood vessel detection from retinal images. Biomedical engineering online, 9(1), 1-10.
60. Raja, H., Akram, M. U., Shaukat, A., Khan, S. A., Alghamdi, N., Khawaja, S. G., et al. (2020).
Extraction of retinal layers through convolution neural network (CNN) in an OCT image for glaucoma diagnosis. Journal of Digital Imaging, 33(6), 1428-1442.
61. Kumar, P. J., Li, X., Binford, T., Yuan, Y., Hu, W., Yung, Y., et al. (2019). Intelligent detection of glaucoma using ballistic optical imaging. Advanced Engineering Informatics, 40, 107-129.
62. Raimundo, M., Mateus, C., Faria, P., Oliveiros, B., Cardoso, J., Silva, J. F., et al. (2018).
SENSITIVITY OF PSYCHOPHYSICAL, ELECTROPHYSIOLOGICAL AND STRUCTURAL TESTS FOR DETECTION AND PROGRESSION MONITORING IN OCULAR HYPERTENSION AND GLAUCOMA. Revista Sociedade Portuguesa de Oftalmologia, 42(1).
63. Thompson, A. C., Jammal, A. A., Berchuck, S. I., Mariottoni, E. B., & Medeiros, F. A. (2020).
Assessment of a segmentation-free deep learning algorithm for diagnosing glaucoma from optical coherence tomography scans. JAMA ophthalmology, 138(4), 333-339.
64. Raja, H., Akram, M. U., Khawaja, S. G., Arslan, M., Ramzan, A., & Nazir, N. (2020). Data on OCT and fundus images for the detection of glaucoma. Data in brief, 29, 105342.
65. Maetschke, S., Antony, B., Ishikawa, H., Wollstein, G., Schuman, J., & Garnavi, R. (2019). A feature agnostic approach for glaucoma detection in OCT volumes. PloS one, 14(7), e0219126.
66. Kim, S. J., Cho, K. J., & Oh, S. (2017). Development of machine learning models for diagnosis of
2736 http://annalsofrscb.ro
glaucoma. PloS one, 12(5), e0177726.
67. Gopinath, K., Sivaswamy, J., & Mansoori, T. Automatic glaucoma assessment from angio-OCT images. In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), 2016 (pp. 193-196):
IEEE
68. Werner, A. C., & Shen, L. Q. A review of OCT angiography in glaucoma. In Seminars in ophthalmology, 2019 (Vol. 34, pp. 279-286, Vol. 4): Taylor & Francis
69.K.Venkatachalam, A.Devipriya, J.Maniraj, M.Sivaram, A.Ambikapathy, Iraj S Amiri, “A Novel Method of motor imagery classification using eeg signal”, Journal Artificial Intelligence in Medicine Elsevier, Volume 103, March 2020, 101787
70.Yasoda, K., Ponmagal, R.S., Bhuvaneshwari, K.S. K Venkatachalam, “ Automatic detection and classification of EEG artifacts using fuzzy kernel SVM and wavelet ICA (WICA)” Soft Computing Journal (2020).
71.P. Prabu, Ahmed Najat Ahmed, K. Venkatachalam, S. Nalini, R. Manikandan,Energy efficient data collection in sparse sensor networks using multiple Mobile Data Patrons, Computers & Electrical Engineering,Volume 87,2020.
72,V.R. Balaji, Maheswaran S, M. Rajesh Babu, M. Kowsigan, Prabhu E., Venkatachalam K,Combining statistical models using modified spectral subtraction method for embedded system,Microprocessors and Microsystems, Volume 73,2020.
73) Malar, A.C.J., Kowsigan, M., Krishnamoorthy, N. S. Karthick, E. Prabhu & K. Venkatachalam (2020).
Multi constraints applied energy efficient routing technique based on ant colony optimization used for disaster resilient location detection in mobile ad-hoc network. Journal of Ambient Intelligence and Humanized Computing, 01767-9.