Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features

Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities linked to di...

Full description

Bibliographic Details
Main Authors: Tamoor Aziz, Ademola E. Ilesanmi, Chalie Charoenlarpnopparut
Format: Article
Language:English
Published: MDPI AG 2021-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/11/14/6391
id doaj-c2070ce2b9bf4e4a93ba395c53e81d56
record_format Article
spelling doaj-c2070ce2b9bf4e4a93ba395c53e81d562021-07-23T13:29:27ZengMDPI AGApplied Sciences2076-34172021-07-01116391639110.3390/app11146391Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window FeaturesTamoor Aziz0Ademola E. Ilesanmi1Chalie Charoenlarpnopparut2School of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum-Thani 12000, ThailandSchool of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum-Thani 12000, ThailandSchool of Information, Computer and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum-Thani 12000, ThailandDiabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in retinal fundus images. The proposed method first performs preprocessing on retinal fundus images. Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally, conventional and hand-crafted features are extracted from each candidate and classified by a support vector machine. Two datasets are used to evaluate the algorithms. Precision rate (<i>P</i>), recall rate (<i>R</i>), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error, peak signal to noise ratio, information entropy, and contrast are also used to evaluate preprocessing method. The proposed method achieves a high F1 score with 83.85% for the DIARETDB1 image dataset and 72.25% for the DIARETDB0 image dataset. The proposed algorithm adequately adapts when compared with conventional algorithms, hence will act as a tool for segmentation.https://www.mdpi.com/2076-3417/11/14/6391adaptive thresholdingclassification and feature extractionsmart window featureshemorrhage detection
collection DOAJ
language English
format Article
sources DOAJ
author Tamoor Aziz
Ademola E. Ilesanmi
Chalie Charoenlarpnopparut
spellingShingle Tamoor Aziz
Ademola E. Ilesanmi
Chalie Charoenlarpnopparut
Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
Applied Sciences
adaptive thresholding
classification and feature extraction
smart window features
hemorrhage detection
author_facet Tamoor Aziz
Ademola E. Ilesanmi
Chalie Charoenlarpnopparut
author_sort Tamoor Aziz
title Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
title_short Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
title_full Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
title_fullStr Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
title_full_unstemmed Efficient and Accurate Hemorrhages Detection in Retinal Fundus Images Using Smart Window Features
title_sort efficient and accurate hemorrhages detection in retinal fundus images using smart window features
publisher MDPI AG
series Applied Sciences
issn 2076-3417
publishDate 2021-07-01
description Diabetic retinopathy (DR) is one of the diseases that cause blindness globally. Untreated accumulation of fat and cholesterol may trigger atherosclerosis in the diabetic patient, which may obstruct blood vessels. Retinal fundus images are used as diagnostic tools to screen abnormalities linked to diseases that affect the eye. Blurriness and low contrast are major problems when segmenting retinal fundus images. This article proposes an algorithm to segment and detect hemorrhages in retinal fundus images. The proposed method first performs preprocessing on retinal fundus images. Then a novel smart windowing-based adaptive threshold is utilized to segment hemorrhages. Finally, conventional and hand-crafted features are extracted from each candidate and classified by a support vector machine. Two datasets are used to evaluate the algorithms. Precision rate (<i>P</i>), recall rate (<i>R</i>), and F1 score are used for quantitative evaluation of segmentation methods. Mean square error, peak signal to noise ratio, information entropy, and contrast are also used to evaluate preprocessing method. The proposed method achieves a high F1 score with 83.85% for the DIARETDB1 image dataset and 72.25% for the DIARETDB0 image dataset. The proposed algorithm adequately adapts when compared with conventional algorithms, hence will act as a tool for segmentation.
topic adaptive thresholding
classification and feature extraction
smart window features
hemorrhage detection
url https://www.mdpi.com/2076-3417/11/14/6391
work_keys_str_mv AT tamooraziz efficientandaccuratehemorrhagesdetectioninretinalfundusimagesusingsmartwindowfeatures
AT ademolaeilesanmi efficientandaccuratehemorrhagesdetectioninretinalfundusimagesusingsmartwindowfeatures
AT chaliecharoenlarpnopparut efficientandaccuratehemorrhagesdetectioninretinalfundusimagesusingsmartwindowfeatures
_version_ 1721289585702469632