Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma
Glaucoma is a heterogeneous group of diseases characterised by cupping of the optic nerve head and visual field damage, starting with a progressive loss of vision that leads to permanent blindness. When diagnosed in time, Glaucoma can be delayed by adequate treatment. More efficient processes for di...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9921304/ |
| _version_ | 1811329172046348288 |
|---|---|
| author | Ricardo Leonardo Joao Goncalves Andre Carreiro Beatriz Simoes Tiago Oliveira Filipe Soares |
| author_facet | Ricardo Leonardo Joao Goncalves Andre Carreiro Beatriz Simoes Tiago Oliveira Filipe Soares |
| author_sort | Ricardo Leonardo |
| collection | DOAJ |
| description | Glaucoma is a heterogeneous group of diseases characterised by cupping of the optic nerve head and visual field damage, starting with a progressive loss of vision that leads to permanent blindness. When diagnosed in time, Glaucoma can be delayed by adequate treatment. More efficient processes for diagnosis are being proposed, and the role of artificial intelligence in the field is growing. This work presents a pipeline to evaluate the impact of generative modelling in Computer-Aided Diagnosis (CADx) of Glaucoma based on Deep Learning, particularly focused on the optic disc region. The methodology relies on transforming retinal fundus images to improve and degrade their quality to augment the training data and assess the diagnostic performance. The objective evaluation of the proposed model based on Generative Adversarial Networks revealed quantitative and qualitative improvements in image quality. To support this, we propose a new model to evaluate the quality of fundus images, which can also be used within the pipeline to reject samples with lower image quality for diagnosis. Its performance surpassed related work, achieving a balanced accuracy of 0.929. Concerning Glaucoma CADx, the results obtained in public datasets point to a considerable gain in Sensitivity, Specificity, and Accuracy, achieving scores of 0.883 (+0.054), 0.957 (+0.019), and 0.931 (+0.031), respectively, after image data augmentation when compared with previous work targeted at offline inference in mobile devices. Considering the restriction of choosing simpler backbone networks that can run on edge devices, our findings support the importance of image quality diversity and realistic augmentation. |
| first_indexed | 2024-04-13T15:39:06Z |
| format | Article |
| id | doaj.art-a56017041c144dac80addd4d8037a9ba |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T15:39:06Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a56017041c144dac80addd4d8037a9ba2022-12-22T02:41:12ZengIEEEIEEE Access2169-35362022-01-011011163611164910.1109/ACCESS.2022.32151269921304Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of GlaucomaRicardo Leonardo0https://orcid.org/0000-0003-2695-4462Joao Goncalves1https://orcid.org/0000-0002-8341-8167Andre Carreiro2https://orcid.org/0000-0002-4234-5336Beatriz Simoes3Tiago Oliveira4Filipe Soares5https://orcid.org/0000-0002-2881-313XFraunhofer Portugal AICOS, Porto, PortugalFraunhofer Portugal AICOS, Porto, PortugalFraunhofer Portugal AICOS, Porto, PortugalFraunhofer Portugal AICOS, Porto, PortugalFirst Solutions—Sistemas de Informação, Matosinhos, PortugalFraunhofer Portugal AICOS, Porto, PortugalGlaucoma is a heterogeneous group of diseases characterised by cupping of the optic nerve head and visual field damage, starting with a progressive loss of vision that leads to permanent blindness. When diagnosed in time, Glaucoma can be delayed by adequate treatment. More efficient processes for diagnosis are being proposed, and the role of artificial intelligence in the field is growing. This work presents a pipeline to evaluate the impact of generative modelling in Computer-Aided Diagnosis (CADx) of Glaucoma based on Deep Learning, particularly focused on the optic disc region. The methodology relies on transforming retinal fundus images to improve and degrade their quality to augment the training data and assess the diagnostic performance. The objective evaluation of the proposed model based on Generative Adversarial Networks revealed quantitative and qualitative improvements in image quality. To support this, we propose a new model to evaluate the quality of fundus images, which can also be used within the pipeline to reject samples with lower image quality for diagnosis. Its performance surpassed related work, achieving a balanced accuracy of 0.929. Concerning Glaucoma CADx, the results obtained in public datasets point to a considerable gain in Sensitivity, Specificity, and Accuracy, achieving scores of 0.883 (+0.054), 0.957 (+0.019), and 0.931 (+0.031), respectively, after image data augmentation when compared with previous work targeted at offline inference in mobile devices. Considering the restriction of choosing simpler backbone networks that can run on edge devices, our findings support the importance of image quality diversity and realistic augmentation.https://ieeexplore.ieee.org/document/9921304/Computer-aided diagnosisconvolutional neural networksdeep learningfundus imagesgenerative adversarial networksglaucoma |
| spellingShingle | Ricardo Leonardo Joao Goncalves Andre Carreiro Beatriz Simoes Tiago Oliveira Filipe Soares Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma IEEE Access Computer-aided diagnosis convolutional neural networks deep learning fundus images generative adversarial networks glaucoma |
| title | Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma |
| title_full | Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma |
| title_fullStr | Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma |
| title_full_unstemmed | Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma |
| title_short | Impact of Generative Modeling for Fundus Image Augmentation With Improved and Degraded Quality in the Classification of Glaucoma |
| title_sort | impact of generative modeling for fundus image augmentation with improved and degraded quality in the classification of glaucoma |
| topic | Computer-aided diagnosis convolutional neural networks deep learning fundus images generative adversarial networks glaucoma |
| url | https://ieeexplore.ieee.org/document/9921304/ |
| work_keys_str_mv | AT ricardoleonardo impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma AT joaogoncalves impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma AT andrecarreiro impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma AT beatrizsimoes impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma AT tiagooliveira impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma AT filipesoares impactofgenerativemodelingforfundusimageaugmentationwithimprovedanddegradedqualityintheclassificationofglaucoma |