{"title":"基于深度学习的糖尿病视网膜病变图像二值分类迁移学习方法。","authors":"Dimple Saproo, Aparna N Mahajan, Seema Narwal","doi":"10.1007/s40200-024-01497-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images.</p><p><strong>Method: </strong>This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight.</p><p><strong>Results: </strong>This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network.</p><p><strong>Conclusion: </strong>Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.</p>","PeriodicalId":15635,"journal":{"name":"Journal of Diabetes and Metabolic Disorders","volume":"23 2","pages":"2289-2314"},"PeriodicalIF":1.8000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11599653/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning based binary classification of diabetic retinopathy images using transfer learning approach.\",\"authors\":\"Dimple Saproo, Aparna N Mahajan, Seema Narwal\",\"doi\":\"10.1007/s40200-024-01497-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images.</p><p><strong>Method: </strong>This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight.</p><p><strong>Results: </strong>This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network.</p><p><strong>Conclusion: </strong>Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.</p>\",\"PeriodicalId\":15635,\"journal\":{\"name\":\"Journal of Diabetes and Metabolic Disorders\",\"volume\":\"23 2\",\"pages\":\"2289-2314\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-09-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11599653/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Diabetes and Metabolic Disorders\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s40200-024-01497-1\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/12/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q4\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Diabetes and Metabolic Disorders","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s40200-024-01497-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/12/1 0:00:00","PubModel":"eCollection","JCR":"Q4","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
Deep learning based binary classification of diabetic retinopathy images using transfer learning approach.
Objective: Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images.
Method: This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight.
Results: This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network.
Conclusion: Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.
期刊介绍:
Journal of Diabetes & Metabolic Disorders is a peer reviewed journal which publishes original clinical and translational articles and reviews in the field of endocrinology and provides a forum of debate of the highest quality on these issues. Topics of interest include, but are not limited to, diabetes, lipid disorders, metabolic disorders, osteoporosis, interdisciplinary practices in endocrinology, cardiovascular and metabolic risk, aging research, obesity, traditional medicine, pychosomatic research, behavioral medicine, ethics and evidence-based practices.As of Jan 2018 the journal is published by Springer as a hybrid journal with no article processing charges. All articles published before 2018 are available free of charge on springerlink.Unofficial 2017 2-year Impact Factor: 1.816.