Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network
Diabetic retinopathy is one of the leading diseases affecting eyes. Lack of early detection and treatment can lead to total blindness of the diseased eyes. Recently, numerous researchers have attempted producing automatic diabetic retinopathy detection techniques to supplement diagnosis and early tr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2021/6618666 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832565904042360832 |
|---|---|
| author | Abubakar M. Ashir Salisu Ibrahim Mohammed Abdulghani Abdullahi Abdu Ibrahim Mohammed S. Anwar |
| author_facet | Abubakar M. Ashir Salisu Ibrahim Mohammed Abdulghani Abdullahi Abdu Ibrahim Mohammed S. Anwar |
| author_sort | Abubakar M. Ashir |
| collection | DOAJ |
| description | Diabetic retinopathy is one of the leading diseases affecting eyes. Lack of early detection and treatment can lead to total blindness of the diseased eyes. Recently, numerous researchers have attempted producing automatic diabetic retinopathy detection techniques to supplement diagnosis and early treatment of diabetic retinopathy symptoms. In this manuscript, a new approach has been proposed. The proposed approach utilizes the feature extracted from the fundus image using a local extrema information with quantized Haralick features. The quantized features encode not only the textural Haralick features but also exploit the multiresolution information of numerous symptoms in diabetic retinopathy. Long Short-Term Memory network together with local extrema pattern provides a probabilistic approach to analyze each segment of the image with higher precision which helps to suppress false positive occurrences. The proposed approach analyzes the retina vasculature and hard-exudate symptoms of diabetic retinopathy on two different public datasets. The experimental results evaluated using performance matrices such as specificity, accuracy, and sensitivity reveal promising indices. Similarly, comparison with the related state-of-the-art researches highlights the validity of the proposed method. The proposed approach performs better than most of the researches used for comparison. |
| format | Article |
| id | doaj-art-0e77f8f22bb342b7bf1fa457b2f6ca4f |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-0e77f8f22bb342b7bf1fa457b2f6ca4f2025-02-03T01:05:33ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962021-01-01202110.1155/2021/66186666618666Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory NetworkAbubakar M. Ashir0Salisu Ibrahim1Mohammed Abdulghani2Abdullahi Abdu Ibrahim3Mohammed S. Anwar4Department of Computer Engineering, Tishk International University, Erbil, KRD, IraqDepartment of Mathematic Education, Tishk International University, Erbil, KRD, IraqDepartment of Computer Engineering, Tishk International University, Erbil, KRD, IraqDepartment of Computer Engineering, Altinbas University, Istanbul, TurkeyDepartment of Computer Engineering, Tishk International University, Erbil, KRD, IraqDiabetic retinopathy is one of the leading diseases affecting eyes. Lack of early detection and treatment can lead to total blindness of the diseased eyes. Recently, numerous researchers have attempted producing automatic diabetic retinopathy detection techniques to supplement diagnosis and early treatment of diabetic retinopathy symptoms. In this manuscript, a new approach has been proposed. The proposed approach utilizes the feature extracted from the fundus image using a local extrema information with quantized Haralick features. The quantized features encode not only the textural Haralick features but also exploit the multiresolution information of numerous symptoms in diabetic retinopathy. Long Short-Term Memory network together with local extrema pattern provides a probabilistic approach to analyze each segment of the image with higher precision which helps to suppress false positive occurrences. The proposed approach analyzes the retina vasculature and hard-exudate symptoms of diabetic retinopathy on two different public datasets. The experimental results evaluated using performance matrices such as specificity, accuracy, and sensitivity reveal promising indices. Similarly, comparison with the related state-of-the-art researches highlights the validity of the proposed method. The proposed approach performs better than most of the researches used for comparison.http://dx.doi.org/10.1155/2021/6618666 |
| spellingShingle | Abubakar M. Ashir Salisu Ibrahim Mohammed Abdulghani Abdullahi Abdu Ibrahim Mohammed S. Anwar Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network International Journal of Biomedical Imaging |
| title | Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network |
| title_full | Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network |
| title_fullStr | Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network |
| title_full_unstemmed | Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network |
| title_short | Diabetic Retinopathy Detection Using Local Extrema Quantized Haralick Features with Long Short-Term Memory Network |
| title_sort | diabetic retinopathy detection using local extrema quantized haralick features with long short term memory network |
| url | http://dx.doi.org/10.1155/2021/6618666 |
| work_keys_str_mv | AT abubakarmashir diabeticretinopathydetectionusinglocalextremaquantizedharalickfeatureswithlongshorttermmemorynetwork AT salisuibrahim diabeticretinopathydetectionusinglocalextremaquantizedharalickfeatureswithlongshorttermmemorynetwork AT mohammedabdulghani diabeticretinopathydetectionusinglocalextremaquantizedharalickfeatureswithlongshorttermmemorynetwork AT abdullahiabduibrahim diabeticretinopathydetectionusinglocalextremaquantizedharalickfeatureswithlongshorttermmemorynetwork AT mohammedsanwar diabeticretinopathydetectionusinglocalextremaquantizedharalickfeatureswithlongshorttermmemorynetwork |