Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification
The emergence of deep learning has markedly enhanced the identification and diagnosis of ocular diseases, providing considerable benefits compared to conventional machine learning techniques. This research investigates the application of deep feature extraction for classifying eight different ocular...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Applied Computational Intelligence and Soft Computing |
| Online Access: | http://dx.doi.org/10.1155/acis/6653543 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849321499634171904 |
|---|---|
| author | Shreemat Kumar Dash Kante Satyanarayana Santi Kumari Behera Sudarson Jena Ashoka Kumar Ratha Prabira Kumar Sethy Aziz Nanthaamornphong |
| author_facet | Shreemat Kumar Dash Kante Satyanarayana Santi Kumari Behera Sudarson Jena Ashoka Kumar Ratha Prabira Kumar Sethy Aziz Nanthaamornphong |
| author_sort | Shreemat Kumar Dash |
| collection | DOAJ |
| description | The emergence of deep learning has markedly enhanced the identification and diagnosis of ocular diseases, providing considerable benefits compared to conventional machine learning techniques. This research investigates the application of deep feature extraction for classifying eight different ocular diseases. The VGG16, a pretrained convolutional neural network (CNN) model, was employed for feature extraction, while the fine k-nearest neighbor (KNN) classifier was utilized for classification. Experimental results showed an initial classification accuracy of 89.2% using features from Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps and 83.1% using Multiscale Retinex (MSR) enhanced images. However, combining both feature sets led to an improved classification accuracy of 96.5%. Despite these promising results, several challenges remain, including the need for models that generalize across diverse patient imaging and demographics modalities, the accessibility of extensive annotated datasets, and the interpretability of models. Ethical issues and legal frameworks are also crucial for the safe and fair implementation of AI in medical services. The study suggests that future efforts in deep learning for ophthalmology should focus on creating large-scale, annotated datasets to enhance the detection of ocular diseases. |
| format | Article |
| id | doaj-art-53be5a666efd42a78e0dc2e4b0f5575c |
| institution | Kabale University |
| issn | 1687-9732 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Computational Intelligence and Soft Computing |
| spelling | doaj-art-53be5a666efd42a78e0dc2e4b0f5575c2025-08-20T03:49:45ZengWileyApplied Computational Intelligence and Soft Computing1687-97322025-01-01202510.1155/acis/6653543Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN ClassificationShreemat Kumar Dash0Kante Satyanarayana1Santi Kumari Behera2Sudarson Jena3Ashoka Kumar Ratha4Prabira Kumar Sethy5Aziz Nanthaamornphong6Department of CSEDepartment of CSEDepartment of CSEDepartment of CSEDepartment of Electronics EngineeringDepartment of Electronics EngineeringCollege of ComputingThe emergence of deep learning has markedly enhanced the identification and diagnosis of ocular diseases, providing considerable benefits compared to conventional machine learning techniques. This research investigates the application of deep feature extraction for classifying eight different ocular diseases. The VGG16, a pretrained convolutional neural network (CNN) model, was employed for feature extraction, while the fine k-nearest neighbor (KNN) classifier was utilized for classification. Experimental results showed an initial classification accuracy of 89.2% using features from Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps and 83.1% using Multiscale Retinex (MSR) enhanced images. However, combining both feature sets led to an improved classification accuracy of 96.5%. Despite these promising results, several challenges remain, including the need for models that generalize across diverse patient imaging and demographics modalities, the accessibility of extensive annotated datasets, and the interpretability of models. Ethical issues and legal frameworks are also crucial for the safe and fair implementation of AI in medical services. The study suggests that future efforts in deep learning for ophthalmology should focus on creating large-scale, annotated datasets to enhance the detection of ocular diseases.http://dx.doi.org/10.1155/acis/6653543 |
| spellingShingle | Shreemat Kumar Dash Kante Satyanarayana Santi Kumari Behera Sudarson Jena Ashoka Kumar Ratha Prabira Kumar Sethy Aziz Nanthaamornphong Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification Applied Computational Intelligence and Soft Computing |
| title | Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification |
| title_full | Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification |
| title_fullStr | Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification |
| title_full_unstemmed | Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification |
| title_short | Ocular Disease Detection Using Fundus Images: A Hybrid Approach of Grad-CAM and Multiscale Retinex Preprocessing With VGG16 Deep Features and Fine KNN Classification |
| title_sort | ocular disease detection using fundus images a hybrid approach of grad cam and multiscale retinex preprocessing with vgg16 deep features and fine knn classification |
| url | http://dx.doi.org/10.1155/acis/6653543 |
| work_keys_str_mv | AT shreematkumardash oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT kantesatyanarayana oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT santikumaribehera oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT sudarsonjena oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT ashokakumarratha oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT prabirakumarsethy oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification AT aziznanthaamornphong oculardiseasedetectionusingfundusimagesahybridapproachofgradcamandmultiscaleretinexpreprocessingwithvgg16deepfeaturesandfineknnclassification |