Energetic Glaucoma Segmentation and Classification Strategies using Depth Optimized Machine Learning Strategies

TLDR: A new methodology is introduced to identify the Glaucoma on earlier stages called Depth Optimized Machine Learning Strategy (DOMLS), in which it adapts the new optimization logic called Modified K-Means Optimization Logic (MkMOL) to provide best accuracy in results and the proposed approach assures the accuracy level of more than 96.2%.

Abstract: \n Glaucoma is a major threatening cause, in which it affects the optical nerve to lead a permanent blindness to individuals. The major causes of Glaucoma are high pressure to eyes, family history, irregular sleeping habits and so on. These kinds of causes leads to Glaucoma easily as well as the affection to such disease leads a heavy damage to the internal optic nervous system and the affected person will get permanent blindness within few months. The eye fluid called aqueous humor is getting blocked inside due to Glaucoma, in normal cases sometimes the fluid comes out from the eye via mesh perspective channel, but this Glaucoma blocks that channel and causes the fluid to getting locked inside and provides the permanent blockage inside. So, that the eyes are getting severe affections such as infection, random blindness in initial stages and so on. The World Health Organization analyzes and reports nearly 80 million people around the globe are affected due to some form of Glaucoma. The major problem with this disease is it is incurable, however, the affection stages can be reduced and maintain the same level of affection as it is for the long period but it is possible only earlier stages of identification. This Glaucoma causes structural affection to the eye ball and it is complex to estimate the cause during regular diagnosis. In medical terms, the Cup to Disc Ratio (CDR) is minimized to the Glaucoma patients suddenly and leads a harmful damage to one's eye in severe manner. The general way to identify the Glaucoma is to take Optical Coherence Tomography (OCT) test, in which it captures the uncovered portion of eye ball (backside) and it is an efficient way to visualize diverse portions of eyes with optical nerve visibility is shown clearly. The OCT images are mainly used to identify the diseases like Glaucoma with proper and robust accuracy levels. In this paper, a new methodology is introduced to identify the Glaucoma on earlier stages called Depth Optimized Machine Learning Strategy (DOMLS), in which it adapts the new optimization logic called Modified K-Means Optimization Logic (MkMOL) to provide best accuracy in results and the proposed approach assures the accuracy level of more than 96.2% with least error rate of 0.002%. This paper focuses on the identification of early stage of Glaucoma and provides an efficient solution to people in case of affection by such disease using OCT images. The exact position point out is handled by using Region of Interest (ROI) based optical region selection, in which it is easy to point the Optical Cup (OC) and Optical Disc (OD). The proposed algorithm of DOMLS proves the accuracy levels in estimation of Glaucoma and shows the practical proofs on resulting section in clear manner.

Figures

Figure 1

Figure 12

Figure 13

Figure 6

Figure 8

Figure 9

Full text

Page 1/25
Energetic Glaucoma Segmentation and
Classication Strategies using Depth Optimized
Machine Learning Strategies
ELIZABETH JESI V
SRM Institute of Science and Technology
SHABNAM MOHAMED ASLAM
Majmaah University
RAMKUMAR G (  pgrvlsi@gmail.com )
Saveetha Institute of Medical and Technical Sciences: Saveetha University
SUJATHA M
Koneru Lakshmaiah Education Foundation
ANUSHYA A
St. Jerome's College
MARY SUBAJA CHRISTO
SRM Institute of Science and Technology
Research Article
Keywords: Glaucoma Detection, Depth Optimized Machine Learning Strategy, Modied K-Means
Optimization Logic, Optical Disc, Optical Cup, Optimization, Region of Interest
Posted Date: June 7th, 2021
DOI: https://doi.org/10.21203/rs.3.rs-559074/v1
License:   This work is licensed under a Creative Commons Attribution 4.0 International License. 
Read Full License

Page 2/25
Abstract
Glaucoma is a major threatening cause, in which it affects the optical nerve to lead a permanent
blindness to individuals. The major causes of Glaucoma are high pressure to eyes, family history,
irregular sleeping habits and so on. These kinds of causes leads to Glaucoma easily as well as the
affection to such disease leads a heavy damage to the internal optic nervous system and the affected
person will get permanent blindness within few months. The eye uid called aqueous humor is getting
blocked inside due to Glaucoma, in normal cases sometimes the uid comes out from the eye via mesh
perspective channel, but this Glaucoma blocks that channel and causes the uid to getting locked inside
and provides the permanent blockage inside. So, that the eyes are getting severe affections such as
infection, random blindness in initial stages and so on. The World Health Organization analyzes and
reports nearly 80 million people around the globe are affected due to some form of Glaucoma. The major
problem with this disease is it is incurable, however, the affection stages can be reduced and maintain the
same level of affection as it is for the long period but it is possible only earlier stages of identication.
This Glaucoma causes structural affection to the eye ball and it is complex to estimate the cause during
regular diagnosis. In medical terms, the Cup to Disc Ratio (CDR) is minimized to the Glaucoma patients
suddenly and leads a harmful damage to one's eye in severe manner. The general way to identify the
Glaucoma is to take Optical Coherence Tomography (OCT) test, in which it captures the uncovered
portion of eye ball (backside) and it is an ecient way to visualize diverse portions of eyes with optical
nerve visibility is shown clearly. The OCT images are mainly used to identify the diseases like Glaucoma
with proper and robust accuracy levels. In this paper, a new methodology is introduced to identify the
Glaucoma on earlier stages called Depth Optimized Machine Learning Strategy (DOMLS), in which it
adapts the new optimization logic called Modied K-Means Optimization Logic (MkMOL) to provide best
accuracy in results and the proposed approach assures the accuracy level of more than 96.2% with least
error rate of 0.002%. This paper focuses on the identication of early stage of Glaucoma and provides an
ecient solution to people in case of affection by such disease using OCT images. The exact position
point out is handled by using Region of Interest (ROI) based optical region selection, in which it is easy to
point the Optical Cup (OC) and Optical Disc (OD). The proposed algorithm of DOMLS proves the accuracy
levels in estimation of Glaucoma and shows the practical proofs on resulting section in clear manner.
1. Introduction
Glaucoma is the calm killer of vision, in which it is caused due to intra-ocular eye pressure. The general
causes of Glaucoma is reduced eye sight and slowly it leads to a permanent vision loss, in which it is
considered to be the world second place eye vision loss perspective and blindness (ManarAljazaeri'et al.,
2020). The analysis of World Health Organization reports nearly 80 millions of people suffered from such
disease over 2022. In general the optical nerves of eyes are sending the visualization signals to the brain
and internally it consists of millions of other nerve regions and this affection harm may prompt primary
disgurement of Optical Disc otherwise called Optical-Nervous-Head, in which at last it cause vision
misfortune. As Glaucoma has no side effects in starting period and vision misfortune cause by the

Page 3/25
sickness is irreversible thusly early identication followed by treatment to limit the indications is vital. In
order to notice the eye ball structure using OCT pictures are procured by means of various methods
counting, Ophthalmoscope is utilized for the immediate assessment of optical nerve system, backhanded
assessment is done by means of microscopy features (Ramkumar.G'et al., 2018). Glaucoma can be
identied based on various kinds of assessments specically morphologic as well as non morphologic
feature measurements. Measurement of Optical Disc, Optical Cup and neuro-retinal edge region by
means of Inferior-Superior-Nasal-temporal (ISNT) are determined through morphologic enabled
component extraction procedures. Retinal Nerve Fiber Layer (RNFL), PeriPapillary Atrophy (PPA), blood
vessels goes under non morphological feature estimations (ManarAljazaeri'et al. and ArkajaSaxena'et al.,
2020). Computerized shaded OCT images is an arising procedure in the discovery of glaucoma as it is
nancially savvy as contrast with other methods, that is, Optical intelligence and Heidelberg Retinal
Tomography (HRT), So in order to the proposed analysis, OCT images are utilized to identify the optical
discs and cups with respect to Glaucoma measurements. For the investigation of retinal pictures, optic
circle location is an emerging portion (Ramkumar.G et al., 2016, SaumyaBorwankar'et al., 2020 and
Shifani’et al., 2019).
A. Glaucoma Types and Specications
The Glaucoma can be classied into four different types such as: Open-Angle Glaucoma, Angle-Closure
Glaucoma, Secondary-Glaucoma and Childhood-Glaucoma. All these types are harmful and cause severe
damage into human eyes with respect to systematic causes and leads to permanent blind stages. The
following summary illustrates the visualization of all stages in detail with proper specications.
(i) Open-Angle Glaucoma:
A general form of eye disease type is Open-Angle Glaucoma, in which it is a
common type occurred over the cornea-region of the eye ball, in which the IRIS state stay open. This will
cause the severe pressure to internal eye and causes the eye-stress suddenly, in which it leads to Optical
Nerve Damage. These scenario leads an eye to non-visualize pattern in slow manner and it occurs so
gradually that one's may lose vision before even mindful of an issue. The following gure, Fig-1
illustrates the modular view of Open-Angle Glaucoma, in which the level of affection is increased slowly
and it causes the serious effects to the inner region without any harmful symptoms (AparnaKanakatte'et
al., 2020 and Amirthalakshmi.T.M.et al., 2016).
(ii) Angle-Closure Glaucoma:
The second form of Glaucoma is considered to be the angular form of
Glaucoma, in which it is also called as Closed Angle Glaucoma. In this stage happens when the iris swells
forward to limited or square the seepage point framed by the cornea as well as IRIS. The following gure,
Fig-2 illustrates the modular view of Closed-Angle Glaucoma, in which the level of uid in the inner region
of eye is locked and the affection is serious and harmful in later stages (Manuel'et al., 2020).
Based on the view of above gure, the visualization of closed-angle glaucoma is clearly seen and
therefore, eye uid cannot course through the eye and pressing factor increments. A few people have tight

Page 4/25
seepage points and put them at expanded danger of closed-angle glaucoma. Closed-Angle Glaucoma
may happen out of nowhere or steadily and acute closed-angle glaucoma is a health related crisis.
(iii) Secondary-Glaucoma:
In typical strain glaucoma, the optical-nerve becomes harmed despite the fact
that one's eye pressure is inside the ordinary reach and nobody knows the specic purpose behind this. It
may have a delicate optical-nerve or it may have less blood being provided to individual's optic nerve.
This restricted blood stream could be brought about by atherosclerosis: the development of fat-points in
the supply routes or different conditions that debilitate blood ow. This condition of Glaucoma is called
Secondary-Glaucoma stage. The following gure, Fig-3 illustrates the modular view of Secondary-
Glaucoma.
(iv) Childhood-Glaucoma:
It is feasible for babies and kids to have glaucoma on earlier stages and it very
well might be available from birth or create in the initial not many long periods of life. The optical-nervous
system harm might be brought about by waste blockages or a basic ailment on the eye region. The
following gure, Fig-4 illustrates the modular view of Childhood-Glaucoma.
B. Dataset Summary
This proposed approach adopts real-time modied Glaucoma disease dataset with the presence of
multiple OCT image patterns with the association of several classes and the respective labels bind to the
classes (GibranSatyaNugraha'et al. and Karkuzhali'et al., 2020). Every class labels indicates different
types of Glaucoma disease combination as well as that can easily be identifying the Glaucoma constrain
category with proper prediction principles. The following gure, Fig-5 illustrates the different views of OCT
Glaucoma disease images with proper label indications accumulated from "OCT-Glaucoma Disease
Dataset". In this dataset, all the Glaucoma disease images are properly segmented without dominating
background surroundings as well as the clarity of respective images are comparatively good with proper
proportions of 256x256 pixel ranges. The Glaucoma disease dataset segmentation process is systematic
in terms of scripting and it provides good enough nature on associated dataset as well as the proposed
approach associates a new optimization logic in the summary during feature extraction stage of
implementation for estimating the coloring range, brightness of the image and the saturation-key points
of the Glaucoma disease image. One of the means of that handling too permitted us to effortlessly x
color casting, which turned out to be very solid in a portion of the subsets of the dataset, accordingly
eliminating another possible pre-disposition (ThananSapthamrong'et al. and Gangadevi'et al., 2020). This
arrangement of tests was intended to comprehend if the machine learning procedures really learn the
idea of eye sicknesses or in the event that it is simply learning the intrinsic pre-dispositions in the dataset.
The following gure, Fig-5 shows the various renditions of a different Glaucoma disease dataset images
view for an arbitrarily chosen set of disease types.
The rest of this paper describe regarding Related Study over section 2, further section of Section 3
illustrates the proposed system methodologies in detail with proper algorithm ow and the Section 4
illustrates the Result and Discussion portion of the paper and the nal section, Section 5 illustrates the

Page 5/25
concept of Conclusion and Future Scope of the proposed paper. These all will be explained in detail over
the further section summaries.
2. Related Study
JieWang'et al., 2019, proposed a paper related to Glaucoma analysis based on joint retinal segmenting
and classifying procedures. In this paper (JieWang'et al., 2019), the authors illustrated such as the earlier
stage identication of Glaucoma provides a lot of benets and saves human vision in clear manner. This
system follows proposed ow with Optical-Coherence-Tomography (OCT) images, in which it is a well-
known digital image format for identifying retinal diseases. The major objective of this work (JieWang'et
al., 2019) is to analyze the ophthalmologists, in which it provides the best treatment for the Glaucoma
disease in an effective manner, but the logic of diagnosis is important for providing an effective
treatment accordingly. So, that a new model is proposed on this paper (JieWang'et al., 2019) called Bi-
Decision Strategy Logic, in which it is designed with respect to deep learning principles. In this paper the
screening process of images are done through the analysis of Cup to disc ratio and the resulting
determination provides a good accuracy ratio of identifying the disease in outcome. At last, the
classication principles take the retinal nerve ber layer thickness vector as information and yield the
likelihood of being glaucoma. In the classication procedure, a painstakingly planned module is
proposed to actualize the clinical procedure to analyze glaucoma. This strategy is approved both in a
gathered dataset ratio of 1004 OCT-B Scan analysis from 234 intense things and in a public dataset of
110 B Scans from 10 patients with diabetes-macular swelling. The major advantages identied from this
paper (JieWang'et al., 2019) are the appliance of Decision based new algorithm called Bi-Decision
Strategy Logic and accuracy level of Glaucoma disease prediction is high.
Fathima'et al., 2019, proposed a paper (Fathima'et al., 2019) related to Glaucoma identication with
respect to fundus and Optical-Coherence-Tomography images. In this paper (Fathima'et al., 2019), the
authors illustrated such as Glaucoma is the major cause and leads to destroy one's vision within a small
scale of time period as well as this kind of affection causes severe damages to the internal eye as well.
The Glaucoma effects permanent blind conditions to the people and most of the people around globe
suffered based on Intra-Ocular-Pressure (IOP) over an eye. This kind of IOP affections causes severe
destructions in the optical nervous system which is connected towards the brain. The major objective of
this work (Fathima'et al., 2019) is to design a new framework for recognizing and predicting the
Glaucoma diseases with respect to digital image processing scheme. The authors (Fathima'et al., 2019)
specify several methods are available in past to identify the Glaucoma disease, however, the major
problem identied with such implementations are time consuming and irregular interval iterations. To
avoid these issues a new strategy with powerful classication norms are introduced in this paper
(Fathima'et al., 2019) with respect to Support Vector Classier logic with multiple class specications.
This work is applied on a public dataset and respective dataset images gathered from eye clinic
containing Glaucoma, Non-glaucoma as well as suspect for glaucomatous. This proposed strategy
(Fathima'et al., 2019) gives precision of 90% for fundus pictures and 92% for OCT retinal images and the
recognizable proof of the glaucoma stage is accomplished by contrasting the aftereffects of both the