FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images
The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. T...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9611261/ |
| _version_ | 1818388541095280640 |
|---|---|
| author | Bhargav J. Bhatkalkar S. Vighnesh Nayak Sathvik V. Shenoy R. Vijaya Arjunan |
| author_facet | Bhargav J. Bhatkalkar S. Vighnesh Nayak Sathvik V. Shenoy R. Vijaya Arjunan |
| author_sort | Bhargav J. Bhatkalkar |
| collection | DOAJ |
| description | The localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. To train the regression model, we transform the ground-truth center coordinates of optic disc and fovea of the IDRiD dataset to heatmaps using a 2D-Gaussian equation. The model is capable of pinpointing any single pixel in a vast 2D image space. The model is tested on IDRiD test dataset, Messidor, and G1020 datasets. The model outperforms the state-of-the-art methods on these datasets. The model is very robust and generic, which can be trained and used for the simultaneous localization of multiple landmarks in different medical image datasets. The full implementation code and the trained model with weights (based on Keras) are available for reuse at <bold><uri>https://github.com/bhargav-jb/FundusPosNet</uri></bold>. |
| first_indexed | 2024-12-14T04:27:28Z |
| format | Article |
| id | doaj.art-09972580cfe24667a73893ae0ca67f34 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T04:27:28Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-09972580cfe24667a73893ae0ca67f342022-12-21T23:17:10ZengIEEEIEEE Access2169-35362021-01-01915907115908010.1109/ACCESS.2021.31272809611261FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus ImagesBhargav J. Bhatkalkar0https://orcid.org/0000-0002-3282-4341S. Vighnesh Nayak1https://orcid.org/0000-0002-8660-618XSathvik V. Shenoy2https://orcid.org/0000-0002-3293-5690R. Vijaya Arjunan3https://orcid.org/0000-0002-1402-6573Department of Computer Science and Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, Karnataka, IndiaDepartment of Computer and Communication Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, IndiaDepartment of Electronics and Communication Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, IndiaDepartment of Computer Science and Engineering, Manipal Academy of Higher Education (MAHE), Manipal Institute of Technology, Manipal, Karnataka, IndiaThe localization of the optic disc and fovea is crucial in the automated diagnosis of various retinal diseases. We propose a novel deep learning driven heatmap regression model based on the encoder-decoder architecture for the joint detection of optic disc and fovea centers in color fundus images. To train the regression model, we transform the ground-truth center coordinates of optic disc and fovea of the IDRiD dataset to heatmaps using a 2D-Gaussian equation. The model is capable of pinpointing any single pixel in a vast 2D image space. The model is tested on IDRiD test dataset, Messidor, and G1020 datasets. The model outperforms the state-of-the-art methods on these datasets. The model is very robust and generic, which can be trained and used for the simultaneous localization of multiple landmarks in different medical image datasets. The full implementation code and the trained model with weights (based on Keras) are available for reuse at <bold><uri>https://github.com/bhargav-jb/FundusPosNet</uri></bold>.https://ieeexplore.ieee.org/document/9611261/Fundus imageoptic discfoveadeep learningheatmapregression neural network |
| spellingShingle | Bhargav J. Bhatkalkar S. Vighnesh Nayak Sathvik V. Shenoy R. Vijaya Arjunan FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images IEEE Access Fundus image optic disc fovea deep learning heatmap regression neural network |
| title | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
| title_full | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
| title_fullStr | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
| title_full_unstemmed | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
| title_short | FundusPosNet: A Deep Learning Driven Heatmap Regression Model for the Joint Localization of Optic Disc and Fovea Centers in Color Fundus Images |
| title_sort | fundusposnet a deep learning driven heatmap regression model for the joint localization of optic disc and fovea centers in color fundus images |
| topic | Fundus image optic disc fovea deep learning heatmap regression neural network |
| url | https://ieeexplore.ieee.org/document/9611261/ |
| work_keys_str_mv | AT bhargavjbhatkalkar fundusposnetadeeplearningdrivenheatmapregressionmodelforthejointlocalizationofopticdiscandfoveacentersincolorfundusimages AT svighneshnayak fundusposnetadeeplearningdrivenheatmapregressionmodelforthejointlocalizationofopticdiscandfoveacentersincolorfundusimages AT sathvikvshenoy fundusposnetadeeplearningdrivenheatmapregressionmodelforthejointlocalizationofopticdiscandfoveacentersincolorfundusimages AT rvijayaarjunan fundusposnetadeeplearningdrivenheatmapregressionmodelforthejointlocalizationofopticdiscandfoveacentersincolorfundusimages |