DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer
Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Compact Convolutional Transformer (DRCCT) model, which combines convolutional and transformer techniques to enhance the classifi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/9/1/9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589141541388288 |
|---|---|
| author | Mohamed Touati Rabeb Touati Laurent Nana Faouzi Benzarti Sadok Ben Yahia |
| author_facet | Mohamed Touati Rabeb Touati Laurent Nana Faouzi Benzarti Sadok Ben Yahia |
| author_sort | Mohamed Touati |
| collection | DOAJ |
| description | Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Compact Convolutional Transformer (DRCCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCCT model achieved an impressive average F1-score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Over 100 training epochs, the model demonstrated outstanding generalization capabilities, achieving a remarkable training accuracy of 99% and a validation accuracy of 95%. This consistent improvement underscores the model’s robust learning process and its effectiveness in avoiding overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model’s ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making. |
| format | Article |
| id | doaj-art-b806ffc63921493fb8e7d3e6e82e8077 |
| institution | Kabale University |
| issn | 2504-2289 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj-art-b806ffc63921493fb8e7d3e6e82e80772025-01-24T13:22:32ZengMDPI AGBig Data and Cognitive Computing2504-22892025-01-0191910.3390/bdcc9010009DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional TransformerMohamed Touati0Rabeb Touati1Laurent Nana2Faouzi Benzarti3Sadok Ben Yahia4Lab-STICC/UMR CNRS 6285, University of Brest, F-29238 Brest, FranceLaboratory of Human Genetics, Faculty of Medicine of Tunis, University of Tunis El Manar, Tunis 1007, TunisiaLab-STICC/UMR CNRS 6285, University of Brest, F-29238 Brest, FranceThe National Higher Engineering School of Tunis, University of Tunis, Tunis 1008, TunisiaThe Maersk Mc-Kinney Moller Institute, University of Southern Denmark, 6400 Sonderborg, DenmarkDiabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Compact Convolutional Transformer (DRCCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCCT model achieved an impressive average F1-score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Over 100 training epochs, the model demonstrated outstanding generalization capabilities, achieving a remarkable training accuracy of 99% and a validation accuracy of 95%. This consistent improvement underscores the model’s robust learning process and its effectiveness in avoiding overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model’s ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making.https://www.mdpi.com/2504-2289/9/1/9AIdiabetic retinopathydeep learningDRCCTclassificationtransformer |
| spellingShingle | Mohamed Touati Rabeb Touati Laurent Nana Faouzi Benzarti Sadok Ben Yahia DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer Big Data and Cognitive Computing AI diabetic retinopathy deep learning DRCCT classification transformer |
| title | DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer |
| title_full | DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer |
| title_fullStr | DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer |
| title_full_unstemmed | DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer |
| title_short | DRCCT: Enhancing Diabetic Retinopathy Classification with a Compact Convolutional Transformer |
| title_sort | drcct enhancing diabetic retinopathy classification with a compact convolutional transformer |
| topic | AI diabetic retinopathy deep learning DRCCT classification transformer |
| url | https://www.mdpi.com/2504-2289/9/1/9 |
| work_keys_str_mv | AT mohamedtouati drcctenhancingdiabeticretinopathyclassificationwithacompactconvolutionaltransformer AT rabebtouati drcctenhancingdiabeticretinopathyclassificationwithacompactconvolutionaltransformer AT laurentnana drcctenhancingdiabeticretinopathyclassificationwithacompactconvolutionaltransformer AT faouzibenzarti drcctenhancingdiabeticretinopathyclassificationwithacompactconvolutionaltransformer AT sadokbenyahia drcctenhancingdiabeticretinopathyclassificationwithacompactconvolutionaltransformer |