Generative Adversarial Networks in Retinal Image Classification
The recent introduction of generative adversarial networks has demonstrated remarkable capabilities in generating images that are nearly indistinguishable from real ones. Consequently, both the academic and industrial communities have raised concerns about the challenge of differentiating between fa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/18/10433 |
| _version_ | 1827727293183688704 |
|---|---|
| author | Francesco Mercaldo Luca Brunese Fabio Martinelli Antonella Santone Mario Cesarelli |
| author_facet | Francesco Mercaldo Luca Brunese Fabio Martinelli Antonella Santone Mario Cesarelli |
| author_sort | Francesco Mercaldo |
| collection | DOAJ |
| description | The recent introduction of generative adversarial networks has demonstrated remarkable capabilities in generating images that are nearly indistinguishable from real ones. Consequently, both the academic and industrial communities have raised concerns about the challenge of differentiating between fake and real images. This issue holds significant importance, as images play a vital role in various domains, including image recognition and bioimaging classification in the biomedical field. In this paper, we present a method to assess the distinguishability of bioimages generated by a generative adversarial network, specifically using a dataset of retina images. Once the images are generated, we train several supervised machine learning models to determine whether these classifiers can effectively discriminate between real and fake retina images. Our experiments utilize a deep convolutional generative adversarial network, a type of generative adversarial network, and demonstrate that the generated images, although visually imperceptible as fakes, are correctly identified by a classifier with an F-Measure greater than 0.95. While the majority of the generated images are accurately recognized as fake, a few of them are not classified as such and are consequently considered real retina images. |
| first_indexed | 2024-03-10T23:04:21Z |
| format | Article |
| id | doaj.art-57b43c65b7db42cc84ae9b7c47bff72e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T23:04:21Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-57b43c65b7db42cc84ae9b7c47bff72e2023-11-19T09:27:39ZengMDPI AGApplied Sciences2076-34172023-09-0113181043310.3390/app131810433Generative Adversarial Networks in Retinal Image ClassificationFrancesco Mercaldo0Luca Brunese1Fabio Martinelli2Antonella Santone3Mario Cesarelli4Department of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyDepartment of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyInstitute for Informatics and Telematics, National Research Council of Italy, 56124 Pisa, ItalyDepartment of Medicine and Health Sciences “Vincenzo Tiberio”, University of Molise, 86100 Campobasso, ItalyDepartment of Engineering, University of Sannio, 82100 Benevento, ItalyThe recent introduction of generative adversarial networks has demonstrated remarkable capabilities in generating images that are nearly indistinguishable from real ones. Consequently, both the academic and industrial communities have raised concerns about the challenge of differentiating between fake and real images. This issue holds significant importance, as images play a vital role in various domains, including image recognition and bioimaging classification in the biomedical field. In this paper, we present a method to assess the distinguishability of bioimages generated by a generative adversarial network, specifically using a dataset of retina images. Once the images are generated, we train several supervised machine learning models to determine whether these classifiers can effectively discriminate between real and fake retina images. Our experiments utilize a deep convolutional generative adversarial network, a type of generative adversarial network, and demonstrate that the generated images, although visually imperceptible as fakes, are correctly identified by a classifier with an F-Measure greater than 0.95. While the majority of the generated images are accurately recognized as fake, a few of them are not classified as such and are consequently considered real retina images.https://www.mdpi.com/2076-3417/13/18/10433generative adversarial networkdeep convolutional generative adversarial networkbiomedicalretinamachine learningdeep learning |
| spellingShingle | Francesco Mercaldo Luca Brunese Fabio Martinelli Antonella Santone Mario Cesarelli Generative Adversarial Networks in Retinal Image Classification Applied Sciences generative adversarial network deep convolutional generative adversarial network biomedical retina machine learning deep learning |
| title | Generative Adversarial Networks in Retinal Image Classification |
| title_full | Generative Adversarial Networks in Retinal Image Classification |
| title_fullStr | Generative Adversarial Networks in Retinal Image Classification |
| title_full_unstemmed | Generative Adversarial Networks in Retinal Image Classification |
| title_short | Generative Adversarial Networks in Retinal Image Classification |
| title_sort | generative adversarial networks in retinal image classification |
| topic | generative adversarial network deep convolutional generative adversarial network biomedical retina machine learning deep learning |
| url | https://www.mdpi.com/2076-3417/13/18/10433 |
| work_keys_str_mv | AT francescomercaldo generativeadversarialnetworksinretinalimageclassification AT lucabrunese generativeadversarialnetworksinretinalimageclassification AT fabiomartinelli generativeadversarialnetworksinretinalimageclassification AT antonellasantone generativeadversarialnetworksinretinalimageclassification AT mariocesarelli generativeadversarialnetworksinretinalimageclassification |