Deep Learning Based Quality Prediction of Retinal Fundus Images
The accuracy of diagnosing and monitoring eye diseases using fundus imaging is strongly dependent on the quality of the images. Poor image quality can result in delays or inaccuracies in diagnosis, thus risking patient health. Image quality assessment (IQA) is crucial for regulating retinal imaging...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2023-09-01
|
Series: | Current Directions in Biomedical Engineering |
Subjects: | |
Online Access: | https://doi.org/10.1515/cdbme-2023-1177 |
_version_ | 1797646296017797120 |
---|---|
author | Bolla Mounika Biswas Sria Palanisamy Rohini |
author_facet | Bolla Mounika Biswas Sria Palanisamy Rohini |
author_sort | Bolla Mounika |
collection | DOAJ |
description | The accuracy of diagnosing and monitoring eye diseases using fundus imaging is strongly dependent on the quality of the images. Poor image quality can result in delays or inaccuracies in diagnosis, thus risking patient health. Image quality assessment (IQA) is crucial for regulating retinal imaging quality and assisting in successful diagnoses. In this paper, a learning-based model for evaluating the quality of fundus images is proposed. The EyeQ dataset is selected due to its ease of availability and large collection of images. The images in the dataset are classified into three labels based on their perceptual quality. Label 0 denotes good, 1 denotes fair and 2 denotes poor quality. The ResNet50 deep learning model is fine-tuned with different hyperparameters to develop two models, which are labelled as network-1 and network-2. Network-1 uses the Stochastic Gradient Descent (SGD) optimizer and network-2 utilizes the Adam optimizer. Both networks utilise the Categorical Cross Entropy (CCE) loss function, are trained for 40 epochs and has a learning rate of 1e-3. The performance of the trained models is compared using the accuracy validation curve and the loss validation curve. Network-1 demonstrates an accuracy value of 85.8% with a loss of 0.37 and network-2 achieves an accuracy of 86.2% with a loss of 0.34. The results indicate that network-2 slightly outperforms the performance of the other in terms of accuracy, and should be preferred. Moreover, it is evident that the ResNet50 model is highly adept in appropriate feature extraction and quality evaluation of retinal fundus imaging. |
first_indexed | 2024-03-11T15:00:35Z |
format | Article |
id | doaj.art-35d7745d6b794697ade9017a041a732a |
institution | Directory Open Access Journal |
issn | 2364-5504 |
language | English |
last_indexed | 2024-03-11T15:00:35Z |
publishDate | 2023-09-01 |
publisher | De Gruyter |
record_format | Article |
series | Current Directions in Biomedical Engineering |
spelling | doaj.art-35d7745d6b794697ade9017a041a732a2023-10-30T07:58:13ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042023-09-019170670910.1515/cdbme-2023-1177Deep Learning Based Quality Prediction of Retinal Fundus ImagesBolla Mounika0Biswas Sria1Palanisamy Rohini2IIITDM Kancheepuram, Chennai, Tamil Nadu, IndiaIIITDM Kancheepuram, Chennai, Tamil Nadu, IndiaIIITDM Kancheepuram, Chennai, Tamil Nadu, IndiaThe accuracy of diagnosing and monitoring eye diseases using fundus imaging is strongly dependent on the quality of the images. Poor image quality can result in delays or inaccuracies in diagnosis, thus risking patient health. Image quality assessment (IQA) is crucial for regulating retinal imaging quality and assisting in successful diagnoses. In this paper, a learning-based model for evaluating the quality of fundus images is proposed. The EyeQ dataset is selected due to its ease of availability and large collection of images. The images in the dataset are classified into three labels based on their perceptual quality. Label 0 denotes good, 1 denotes fair and 2 denotes poor quality. The ResNet50 deep learning model is fine-tuned with different hyperparameters to develop two models, which are labelled as network-1 and network-2. Network-1 uses the Stochastic Gradient Descent (SGD) optimizer and network-2 utilizes the Adam optimizer. Both networks utilise the Categorical Cross Entropy (CCE) loss function, are trained for 40 epochs and has a learning rate of 1e-3. The performance of the trained models is compared using the accuracy validation curve and the loss validation curve. Network-1 demonstrates an accuracy value of 85.8% with a loss of 0.37 and network-2 achieves an accuracy of 86.2% with a loss of 0.34. The results indicate that network-2 slightly outperforms the performance of the other in terms of accuracy, and should be preferred. Moreover, it is evident that the ResNet50 model is highly adept in appropriate feature extraction and quality evaluation of retinal fundus imaging.https://doi.org/10.1515/cdbme-2023-1177image quality assessmentresnet50adamaccuracystochastic gradient descentfundus imaging |
spellingShingle | Bolla Mounika Biswas Sria Palanisamy Rohini Deep Learning Based Quality Prediction of Retinal Fundus Images Current Directions in Biomedical Engineering image quality assessment resnet50 adam accuracy stochastic gradient descent fundus imaging |
title | Deep Learning Based Quality Prediction of Retinal Fundus Images |
title_full | Deep Learning Based Quality Prediction of Retinal Fundus Images |
title_fullStr | Deep Learning Based Quality Prediction of Retinal Fundus Images |
title_full_unstemmed | Deep Learning Based Quality Prediction of Retinal Fundus Images |
title_short | Deep Learning Based Quality Prediction of Retinal Fundus Images |
title_sort | deep learning based quality prediction of retinal fundus images |
topic | image quality assessment resnet50 adam accuracy stochastic gradient descent fundus imaging |
url | https://doi.org/10.1515/cdbme-2023-1177 |
work_keys_str_mv | AT bollamounika deeplearningbasedqualitypredictionofretinalfundusimages AT biswassria deeplearningbasedqualitypredictionofretinalfundusimages AT palanisamyrohini deeplearningbasedqualitypredictionofretinalfundusimages |