Fundus image analysis for the detection of diabetic retinopathy disease
Due to the rapid development in computing technology and computer industry fields, medical diagnostic decision-support systems have been gaining importance in the modern society. Retina has received attention by specialists for early diagnosis and prevention of several diseases, such as diabetic ret...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2015
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my-mmu-ep.6313 |
|---|---|
| record_format |
uketd_dc |
| spelling |
my-mmu-ep.63132016-02-03T06:18:02Z Fundus image analysis for the detection of diabetic retinopathy disease 2015-05 Saleh, Marwan D. RC71-78.7 Examination. Diagnosis Due to the rapid development in computing technology and computer industry fields, medical diagnostic decision-support systems have been gaining importance in the modern society. Retina has received attention by specialists for early diagnosis and prevention of several diseases, such as diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma (GC). DR is one of the well-known and most common eye diseases, affecting patients with diabetes mellitus. DR is potentially considered as the major reason behind blindness in adults of age between 20 - 60 years, where it causes 45% of the legal blindness in patients with Diabetes Mellitus. Moreover, DR has become a serious threat in our society, where the number of patients with DR is considerably increasing as a result of the increasing number of people affected by diabetes mellitus. For this reason, early detection as well as periodic screening of DR potentially helps in reducing the progression of this disease and in preventing the subsequent loss of visual capability. The screening includes obtaining and analyzing a sequence of fundus images and observing the early changes in blood vessel patterns and also the presence of the spot lesions, such as exudates (EX), microaneurysms (MA), and haemorrhages (HA). In this work, the identification of the spot lesions is performed based on a set of features, such as size, shape, roughness, edge sharpness, type, color, and depth. The focus of this research is to develop algorithms for the detection of the retinal features, such as blood vessels and optic disc as well as the detection of the possible presence of some spot lesions, such as EX, MA, and HA. Based on the detected features, a rule-based diagnosis has been carried out to detect the presence/absence of DR. In case DR is detected, the disease is further classified into 3 scales, namely mild, moderate or severe. Furthermore, a user friendly interface has been developed to enable the user to interact with the developed grading system. 2015-05 Thesis http://shdl.mmu.edu.my/6313/ http://library.mmu.edu.my/diglib/onlinedb/dig_lib.php phd doctoral Multimedia University Faculty of Computing and Informatics |
| institution |
Multimedia University |
| collection |
MMU Institutional Repository |
| topic |
RC71-78.7 Examination Diagnosis |
| spellingShingle |
RC71-78.7 Examination Diagnosis Saleh, Marwan D. Fundus image analysis for the detection of diabetic retinopathy disease |
| description |
Due to the rapid development in computing technology and computer industry fields, medical diagnostic decision-support systems have been gaining importance in the modern society. Retina has received attention by specialists for early diagnosis and prevention of several diseases, such as diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma (GC). DR is one of the well-known and most common eye diseases, affecting patients with diabetes mellitus. DR is potentially considered as the major reason behind blindness in adults of age between 20 - 60 years, where it causes 45% of the legal blindness in patients with Diabetes Mellitus. Moreover, DR has become a serious threat in our society, where the number of patients with DR is considerably increasing as a result of the increasing number of people affected by diabetes mellitus. For this reason, early detection as well as periodic screening of DR potentially helps in reducing the progression of this disease and in preventing the subsequent loss of visual capability. The screening includes obtaining and analyzing a sequence of fundus images and observing the early changes in blood vessel patterns and also the presence of the spot lesions, such as exudates (EX), microaneurysms (MA), and haemorrhages (HA). In this work, the identification of the spot lesions is performed based on a set of features, such as size, shape, roughness, edge sharpness, type, color, and depth. The focus of this research is to develop algorithms for the detection of the retinal features, such as blood vessels and optic disc as well as the detection of the possible presence of some spot lesions, such as EX, MA, and HA. Based on the detected features, a rule-based diagnosis has been carried out to detect the presence/absence of DR. In case DR is detected, the disease is further classified into 3 scales, namely mild, moderate or severe. Furthermore, a user friendly interface has been developed to enable the user to interact with the developed grading system. |
| format |
Thesis |
| qualification_name |
Doctor of Philosophy (PhD.) |
| qualification_level |
Doctorate |
| author |
Saleh, Marwan D. |
| author_facet |
Saleh, Marwan D. |
| author_sort |
Saleh, Marwan D. |
| title |
Fundus image analysis for the detection of diabetic retinopathy disease |
| title_short |
Fundus image analysis for the detection of diabetic retinopathy disease |
| title_full |
Fundus image analysis for the detection of diabetic retinopathy disease |
| title_fullStr |
Fundus image analysis for the detection of diabetic retinopathy disease |
| title_full_unstemmed |
Fundus image analysis for the detection of diabetic retinopathy disease |
| title_sort |
fundus image analysis for the detection of diabetic retinopathy disease |
| granting_institution |
Multimedia University |
| granting_department |
Faculty of Computing and Informatics |
| publishDate |
2015 |
| _version_ |
1747829628007874560 |