TY - JOUR
T1 - FundusPosNet
T2 - A deep learning driven heatmap regression model for the joint localization of optic disc and fovea centers in color fundus images
AU - Bhatkalkar, Bhargav J.
AU - Nayak, Vighnesh
AU - Shenoy, Sathvik
AU - Vijaya Arjunan, R.
N1 - Publisher Copyright:
Author
PY - 2021
Y1 - 2021
N2 - 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 https://github.com/bhargav-jb/FundusPosNet.
AB - 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 https://github.com/bhargav-jb/FundusPosNet.
UR - http://www.scopus.com/inward/record.url?scp=85119454188&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119454188&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2021.3127280
DO - 10.1109/ACCESS.2021.3127280
M3 - Article
AN - SCOPUS:85119454188
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
ER -