Automatic Detection of Microaneurysms for Diabetic Retinopathy Screening Using Fuzzy Image Processing

Rahim, Sarni Suhaila; Palade, Vasile; Shuttleworth, James; Jayne, Chrisina; Omar, Raja Norliza Raja

doi:10.1007/978-3-319-23983-5_7

Cited by 16 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We proposed the implementation of fuzzy filtering and fuzzy edge detection separately, in addition to the fuzzy histogram equalisation as mentioned before, for the automatic detection of microaneurysms [7]. The fuzzy techniques work better for fuzzy histogram equalisation and fuzzy edge detection.…”

Section: Previous Related Workmentioning

confidence: 99%

“…The fundus images were collected from the Eye Clinic, Department of Ophthalmology, Hospital Melaka, Malaysia. The details of the developed dataset are presented in [7], under Sect. 4—“Proposed System”.…”

Section: Experimental Datasetsmentioning

confidence: 99%

“…The proposed system builds on the systems proposed in [7] and [8]. The previous system in [7] implements the use of fuzzy techniques for the image processing stage, including the fuzzy histogram equalisation, fuzzy median filter and fuzzy edge detection, for the purpose of one of the important lesion detection in diabetic retinopathy screening—microaneurysms. However, the fuzzy techniques are implemented individually in different variants of the system.…”

Section: Proposed System: Detection Of Diabetic Retinopathy and Maculmentioning

confidence: 99%

“…Three features, which are the area of on pixels, the mean and the standard deviation of the white pixels area, are extracted from the output image for the classification stage, which classifies into two main categories with the aid of several machine learning classifiers. Due to the promising results of both systems reported in [7] and [8], especially on the fuzzy techniques ability, we continued our developments with the proposed system to investigate the capability of the combination of the fuzzy image processing techniques, together with retinal structures detection approach and by using more extracted features, in order to produce a more reliable system for the detection of diabetic maculopathy.…”

Section: Proposed System: Detection Of Diabetic Retinopathy and Maculmentioning

confidence: 99%

“…Fuzzy image processing has been reported to work well as fuzzy histogram equalisation method by Sheet et al [4], Garud et al [5] and Rahim et al [6–8]. Fuzzy filtering is another fuzzy image processing method, proposed by Patil and Chaudhari [9], Toh et al [10, 11], Kwan [12, 13] and also Rahim et al [7, 8]. In addition, fuzzy edge detection can be used as a preprocessing technique in order to enhance the image quality and is reported in [7, 8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing

et al. 2016

Self Cite

View full text Add to dashboard Cite

Digital retinal imaging is a challenging screening method for which effective, robust and cost-effective approaches are still to be developed. Regular screening for diabetic retinopathy and diabetic maculopathy diseases is necessary in order to identify the group at risk of visual impairment. This paper presents a novel automatic detection of diabetic retinopathy and maculopathy in eye fundus images by employing fuzzy image processing techniques. The paper first introduces the existing systems for diabetic retinopathy screening, with an emphasis on the maculopathy detection methods. The proposed medical decision support system consists of four parts, namely: image acquisition, image preprocessing including four retinal structures localisation, feature extraction and the classification of diabetic retinopathy and maculopathy. A combination of fuzzy image processing techniques, the Circular Hough Transform and several feature extraction methods are implemented in the proposed system. The paper also presents a novel technique for the macula region localisation in order to detect the maculopathy. In addition to the proposed detection system, the paper highlights a novel online dataset and it presents the dataset collection, the expert diagnosis process and the advantages of our online database compared to other public eye fundus image databases for diabetic retinopathy purposes.

show abstract

Section: Previous Related Workmentioning

confidence: 99%

Section: Experimental Datasetsmentioning

confidence: 99%

Section: Proposed System: Detection Of Diabetic Retinopathy and Maculmentioning

confidence: 99%

Section: Proposed System: Detection Of Diabetic Retinopathy and Maculmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

Diabetic retinopathy severity grading employing quadrant‐based Inception‐V3 convolution neural network architecture

Bhardwaj

Jain

Sood

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Diabetic retinopathy (DR) accounts in eye‐related disorders due to accumulated damage to small retinal blood vessels. Automated diagnostic systems are effective in early detection and diagnosis of severe eye complications by assisting the ophthalmologists. Deep learning‐based techniques have emerged as an advancement over conventional techniques based on hand‐crafted features. The authors have proposed a Quadrant‐based automated DR grading system in this work using Inception‐V3 deep neural network to extract small lesions present in retinal fundus images. The grading efficiency of the proposed architecture is improved utilizing image enhancement and optical disc removal pipeline along with data augmentation stage. The proposed system yields accuracy of 93.33% with minimized cross‐entropy loss of 0.291. Capability of proposed system is demonstrated experimentally to provide efficient DR diagnosis. The diagnosis ability of the proposed architecture is demonstrated by state‐of‐the‐art comparison with other mainstream convolution neural network models and a maximum improvement of 14.33% is observed.

show abstract

Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation

Rahim

Palade

Almakky

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Diabetic retinopathy is a significant complication of diabetes, produced by high blood sugar level, which causes damage to the retina. Effective diabetic retinopathy screening is required because diabetic retinopathy does not show any symptoms in the initial stages, and can cause blindness if it is not diagnosed and treated promptly. This paper presents a novel diabetic retinopathy automatic detection in retinal images by implementing efficient image processing and deep learning techniques. Besides diabetic retinopathy detection, the developed system integrates a novel detection of maculopathy into one detection system. Maculopathy is the damage to the macula, the eye part that is responsible for central vision. Therefore, the combined detection of diabetic retinopathy and maculopathy is essential for an effective screening of diabetic retinopathy. The paper investigates the capability of image pre-processing techniques based on data augmentation as well as deep learning for diabetic retinopathy and maculopathy detection. Computer-assisted clinical decision-making is inevitably transforming the diabetic retinopathy detection and management today, which is crucial for clinicians and patients alike. Therefore, a high degree of accuracy, with which computer algorithms can detect the diabetic retinopathy and maculopathy, is absolutely necessary.

show abstract

Automatic Detection of Microaneurysms for Diabetic Retinopathy Screening Using Fuzzy Image Processing

Cited by 16 publications

References 13 publications

Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing

Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing

Diabetic retinopathy severity grading employing quadrant‐based Inception‐V3 convolution neural network architecture

Detection of Diabetic Retinopathy and Maculopathy in Eye Fundus Images Using Deep Learning and Image Augmentation

Contact Info

Product

Resources

About