Exudates as Landmarks Identified through FCM Clustering in Retinal Images
The aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient’s status through a noninvasive a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/1/142 |
| _version_ | 1827699285236383744 |
|---|---|
| author | Hadi Hamad Tahreer Dwickat Domenico Tegolo Cesare Valenti |
| author_facet | Hadi Hamad Tahreer Dwickat Domenico Tegolo Cesare Valenti |
| author_sort | Hadi Hamad |
| collection | DOAJ |
| description | The aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient’s status through a noninvasive approach. In the field of diabetic retinopathy detection, we considered four public domain datasets (DIARETDB0/1, IDRID, and e-optha) as benchmarks. In order to refine the final results, a specialist ophthalmologist manually segmented a random selection of DIARETDB0/1 fundus images that presented exudates. An innovative pipeline of morphological procedures and fuzzy C-means clustering was integrated in order to extract exudates with a pixel-wise approach. Our methodology was optimized, and verified and the parameters were fine-tuned in order to define both suitable values and to produce a more accurate segmentation. The method was used on 100 tested images, resulting in averages of sensitivity, specificity, and accuracy equal to 83.3%, 99.2%, and 99.1%, respectively. |
| first_indexed | 2024-03-10T13:46:44Z |
| format | Article |
| id | doaj.art-b1826ebafcb045e8b852ad4dca7bc9ae |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T13:46:44Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-b1826ebafcb045e8b852ad4dca7bc9ae2023-11-21T02:34:46ZengMDPI AGApplied Sciences2076-34172020-12-0111114210.3390/app11010142Exudates as Landmarks Identified through FCM Clustering in Retinal ImagesHadi Hamad0Tahreer Dwickat1Domenico Tegolo2Cesare Valenti3Department of Mathematics, Faculty of Science, An-Najah National University, Nablus P.O. Box 7, PalestineDepartment of Mathematics, Faculty of Science, An-Najah National University, Nablus P.O. Box 7, PalestineDepartment of Mathematics and Informatics, University of Palermo, 90123 Palermo, ItalyDepartment of Mathematics and Informatics, University of Palermo, 90123 Palermo, ItalyThe aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient’s status through a noninvasive approach. In the field of diabetic retinopathy detection, we considered four public domain datasets (DIARETDB0/1, IDRID, and e-optha) as benchmarks. In order to refine the final results, a specialist ophthalmologist manually segmented a random selection of DIARETDB0/1 fundus images that presented exudates. An innovative pipeline of morphological procedures and fuzzy C-means clustering was integrated in order to extract exudates with a pixel-wise approach. Our methodology was optimized, and verified and the parameters were fine-tuned in order to define both suitable values and to produce a more accurate segmentation. The method was used on 100 tested images, resulting in averages of sensitivity, specificity, and accuracy equal to 83.3%, 99.2%, and 99.1%, respectively.https://www.mdpi.com/2076-3417/11/1/142exudatesdiabetic retinopathysegmentationmorphological processingfuzzy C-means clusteringretinal landmarks |
| spellingShingle | Hadi Hamad Tahreer Dwickat Domenico Tegolo Cesare Valenti Exudates as Landmarks Identified through FCM Clustering in Retinal Images Applied Sciences exudates diabetic retinopathy segmentation morphological processing fuzzy C-means clustering retinal landmarks |
| title | Exudates as Landmarks Identified through FCM Clustering in Retinal Images |
| title_full | Exudates as Landmarks Identified through FCM Clustering in Retinal Images |
| title_fullStr | Exudates as Landmarks Identified through FCM Clustering in Retinal Images |
| title_full_unstemmed | Exudates as Landmarks Identified through FCM Clustering in Retinal Images |
| title_short | Exudates as Landmarks Identified through FCM Clustering in Retinal Images |
| title_sort | exudates as landmarks identified through fcm clustering in retinal images |
| topic | exudates diabetic retinopathy segmentation morphological processing fuzzy C-means clustering retinal landmarks |
| url | https://www.mdpi.com/2076-3417/11/1/142 |
| work_keys_str_mv | AT hadihamad exudatesaslandmarksidentifiedthroughfcmclusteringinretinalimages AT tahreerdwickat exudatesaslandmarksidentifiedthroughfcmclusteringinretinalimages AT domenicotegolo exudatesaslandmarksidentifiedthroughfcmclusteringinretinalimages AT cesarevalenti exudatesaslandmarksidentifiedthroughfcmclusteringinretinalimages |