Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier
Diabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the diseas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-05-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-456.pdf |
| _version_ | 1818961482183868416 |
|---|---|
| author | Lakshmana Kumar Ramasamy Shynu Gopalan Padinjappurathu Seifedine Kadry Robertas Damaševičius |
| author_facet | Lakshmana Kumar Ramasamy Shynu Gopalan Padinjappurathu Seifedine Kadry Robertas Damaševičius |
| author_sort | Lakshmana Kumar Ramasamy |
| collection | DOAJ |
| description | Diabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the disease can lead to blindness. DR diagnosis is an exceedingly difficult task because of changes in the retina during the disease stages. An automatic DR early detection method can save a patient's vision and can also support the ophthalmologists in DR screening. This paper develops a model for the diagnostics of DR. Initially, we extract and fuse the ophthalmoscopic features from the retina images based on textural gray-level features like co-occurrence, run-length matrix, as well as the coefficients of the Ridgelet Transform. Based on the retina features, the Sequential Minimal Optimization (SMO) classification is used to classify diabetic retinopathy. For performance analysis, the openly accessible retinal image datasets are used, and the findings of the experiments demonstrate the quality and efficacy of the proposed method (we achieved 98.87% sensitivity, 95.24% specificity, 97.05% accuracy on DIARETDB1 dataset, and 90.9% sensitivity, 91.0% specificity, 91.0% accuracy on KAGGLE dataset). |
| first_indexed | 2024-12-20T12:14:08Z |
| format | Article |
| id | doaj.art-88ac32af7ee54d30875667beb32a958c |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-20T12:14:08Z |
| publishDate | 2021-05-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-88ac32af7ee54d30875667beb32a958c2022-12-21T19:41:12ZengPeerJ Inc.PeerJ Computer Science2376-59922021-05-017e45610.7717/peerj-cs.456Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifierLakshmana Kumar Ramasamy0Shynu Gopalan Padinjappurathu1Seifedine Kadry2Robertas Damaševičius3Hindusthan College of Engineering and Technology, Coimbatore, IndiaVellore Institute of Technology University, Vellore, IndiaNoroff University College, Kristiansand, NorwayDepartment of Applied Informatics, Vytautas Magnus University, Kaunas, LithuaniaDiabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the disease can lead to blindness. DR diagnosis is an exceedingly difficult task because of changes in the retina during the disease stages. An automatic DR early detection method can save a patient's vision and can also support the ophthalmologists in DR screening. This paper develops a model for the diagnostics of DR. Initially, we extract and fuse the ophthalmoscopic features from the retina images based on textural gray-level features like co-occurrence, run-length matrix, as well as the coefficients of the Ridgelet Transform. Based on the retina features, the Sequential Minimal Optimization (SMO) classification is used to classify diabetic retinopathy. For performance analysis, the openly accessible retinal image datasets are used, and the findings of the experiments demonstrate the quality and efficacy of the proposed method (we achieved 98.87% sensitivity, 95.24% specificity, 97.05% accuracy on DIARETDB1 dataset, and 90.9% sensitivity, 91.0% specificity, 91.0% accuracy on KAGGLE dataset).https://peerj.com/articles/cs-456.pdfDiabetic RetinopathyFundus imageTextural featuresImage processingContinous Ridgelet transform |
| spellingShingle | Lakshmana Kumar Ramasamy Shynu Gopalan Padinjappurathu Seifedine Kadry Robertas Damaševičius Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier PeerJ Computer Science Diabetic Retinopathy Fundus image Textural features Image processing Continous Ridgelet transform |
| title | Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| title_full | Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| title_fullStr | Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| title_full_unstemmed | Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| title_short | Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| title_sort | detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier |
| topic | Diabetic Retinopathy Fundus image Textural features Image processing Continous Ridgelet transform |
| url | https://peerj.com/articles/cs-456.pdf |
| work_keys_str_mv | AT lakshmanakumarramasamy detectionofdiabeticretinopathyusingafusionoftexturalandridgeletfeaturesofretinalimagesandsequentialminimaloptimizationclassifier AT shynugopalanpadinjappurathu detectionofdiabeticretinopathyusingafusionoftexturalandridgeletfeaturesofretinalimagesandsequentialminimaloptimizationclassifier AT seifedinekadry detectionofdiabeticretinopathyusingafusionoftexturalandridgeletfeaturesofretinalimagesandsequentialminimaloptimizationclassifier AT robertasdamasevicius detectionofdiabeticretinopathyusingafusionoftexturalandridgeletfeaturesofretinalimagesandsequentialminimaloptimizationclassifier |