Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction
Diabetic Retinopathy (DR) is one of the major causes of visual impairment and blindness across the world. It is usually found in patients who suffer from diabetes for a long period. The major focus of this work is to derive optimal representation of retinal images that further helps to improve the p...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/6/914 |
| _version_ | 1797566622711414784 |
|---|---|
| author | Jyostna Devi Bodapati Veeranjaneyulu Naralasetti Shaik Nagur Shareef Saqib Hakak Muhammad Bilal Praveen Kumar Reddy Maddikunta Ohyun Jo |
| author_facet | Jyostna Devi Bodapati Veeranjaneyulu Naralasetti Shaik Nagur Shareef Saqib Hakak Muhammad Bilal Praveen Kumar Reddy Maddikunta Ohyun Jo |
| author_sort | Jyostna Devi Bodapati |
| collection | DOAJ |
| description | Diabetic Retinopathy (DR) is one of the major causes of visual impairment and blindness across the world. It is usually found in patients who suffer from diabetes for a long period. The major focus of this work is to derive optimal representation of retinal images that further helps to improve the performance of DR recognition models. To extract optimal representation, features extracted from multiple pre-trained ConvNet models are blended using proposed multi-modal fusion module. These final representations are used to train a Deep Neural Network (DNN) used for DR identification and severity level prediction. As each ConvNet extracts different features, fusing them using 1D pooling and cross pooling leads to better representation than using features extracted from a single ConvNet. Experimental studies on benchmark Kaggle APTOS 2019 contest dataset reveals that the model trained on proposed blended feature representations is superior to the existing methods. In addition, we notice that cross average pooling based fusion of features from Xception and VGG16 is the most appropriate for DR recognition. With the proposed model, we achieve an accuracy of 97.41%, and a kappa statistic of 94.82 for DR identification and an accuracy of 81.7% and a kappa statistic of 71.1% for severity level prediction. Another interesting observation is that DNN with dropout at input layer converges more quickly when trained using blended features, compared to the same model trained using uni-modal deep features. |
| first_indexed | 2024-03-10T19:30:00Z |
| format | Article |
| id | doaj.art-cb1747bd8aea404f95a3e1adfc70d968 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T19:30:00Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-cb1747bd8aea404f95a3e1adfc70d9682023-11-20T02:15:27ZengMDPI AGElectronics2079-92922020-05-019691410.3390/electronics9060914Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity PredictionJyostna Devi Bodapati0Veeranjaneyulu Naralasetti1Shaik Nagur Shareef2Saqib Hakak3Muhammad Bilal4Praveen Kumar Reddy Maddikunta5Ohyun Jo6Department of CSE, Vignan’s Foundation for Science Technology and Research, Guntur 522213, IndiaDepartment of IT, Vignan’s Foundation for Science Technology and Research, Guntur 522213, IndiaDepartment of CSE, Vignan’s Foundation for Science Technology and Research, Guntur 522213, IndiaFaculty of Computer Science, University of Northern British Columbia, Prince George, BC V2N 4Z9, CanadaDepartment of Computer and Electronics Systems Engineering, Hankuk University of Foreign Studies, Yongin-si 17035, KoreaSchool of Information Technology and Engineering, The Vellore Institute of Technology (VIT), Vellore 632014, IndiaDepartment of Computer Science, College of Electrical and Computer Engineering, Chungbuk National University, Cheongju 28644, KoreaDiabetic Retinopathy (DR) is one of the major causes of visual impairment and blindness across the world. It is usually found in patients who suffer from diabetes for a long period. The major focus of this work is to derive optimal representation of retinal images that further helps to improve the performance of DR recognition models. To extract optimal representation, features extracted from multiple pre-trained ConvNet models are blended using proposed multi-modal fusion module. These final representations are used to train a Deep Neural Network (DNN) used for DR identification and severity level prediction. As each ConvNet extracts different features, fusing them using 1D pooling and cross pooling leads to better representation than using features extracted from a single ConvNet. Experimental studies on benchmark Kaggle APTOS 2019 contest dataset reveals that the model trained on proposed blended feature representations is superior to the existing methods. In addition, we notice that cross average pooling based fusion of features from Xception and VGG16 is the most appropriate for DR recognition. With the proposed model, we achieve an accuracy of 97.41%, and a kappa statistic of 94.82 for DR identification and an accuracy of 81.7% and a kappa statistic of 71.1% for severity level prediction. Another interesting observation is that DNN with dropout at input layer converges more quickly when trained using blended features, compared to the same model trained using uni-modal deep features.https://www.mdpi.com/2079-9292/9/6/914diabetic retinopathy (DR)pre-trained deep ConvNetuni-modal deep featuresmulti-modal deep featurestransfer learning1D pooling |
| spellingShingle | Jyostna Devi Bodapati Veeranjaneyulu Naralasetti Shaik Nagur Shareef Saqib Hakak Muhammad Bilal Praveen Kumar Reddy Maddikunta Ohyun Jo Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction Electronics diabetic retinopathy (DR) pre-trained deep ConvNet uni-modal deep features multi-modal deep features transfer learning 1D pooling |
| title | Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction |
| title_full | Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction |
| title_fullStr | Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction |
| title_full_unstemmed | Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction |
| title_short | Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction |
| title_sort | blended multi modal deep convnet features for diabetic retinopathy severity prediction |
| topic | diabetic retinopathy (DR) pre-trained deep ConvNet uni-modal deep features multi-modal deep features transfer learning 1D pooling |
| url | https://www.mdpi.com/2079-9292/9/6/914 |
| work_keys_str_mv | AT jyostnadevibodapati blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT veeranjaneyulunaralasetti blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT shaiknagurshareef blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT saqibhakak blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT muhammadbilal blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT praveenkumarreddymaddikunta blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction AT ohyunjo blendedmultimodaldeepconvnetfeaturesfordiabeticretinopathyseverityprediction |