Advanced search
1 file | 523.54 KB
Author
Organization
Abstract
Glaucoma is a major eye disease, leading to vision loss without proper medical treatment. Current diagnosis of glaucoma is performed by ophthalmologists who are typically analyzing different types of medical images generated by different types of medical equipment. However, capturing and analyzing these medical images is labor intensive and expensive. In this paper, we present a novel computational approach towards glaucoma diagnosis and localization, only making use of eye fundus images that are analyzed by state-of-the-art deep learning techniques. Specifically, our approach leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) for glaucoma diagnosis and localization, respectively. Quantitative and qualitative results, as obtained for a small-sized dataset with no segmentation ground truth, demonstrate that the proposed approach is promising, for instance achieving an accuracy of 0.91 and an ROC-AUC score of 0.92 for the diagnosis task.
Keywords
AUTOMATED DIAGNOSIS, computer-aided diagnosis, deep learning, fundus, glaucoma, localization, medical image analysis

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 523.54 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Kim, Mi Jung, Ho-min Park, Jasper Zuallaert, Olivier Janssens, Sofie Van Hoecke, and Wesley De Neve. 2018. “Computer-aided Diagnosis and Localization of Glaucoma Using Deep Learning.” In PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2357–2362. IEEE.
APA
Kim, M. J., Park, H., Zuallaert, J., Janssens, O., Van Hoecke, S., & De Neve, W. (2018). Computer-aided diagnosis and localization of glaucoma using deep learning. PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) (pp. 2357–2362). Presented at the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE.
Vancouver
1.
Kim MJ, Park H, Zuallaert J, Janssens O, Van Hoecke S, De Neve W. Computer-aided diagnosis and localization of glaucoma using deep learning. PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM). IEEE; 2018. p. 2357–62.
MLA
Kim, Mi Jung et al. “Computer-aided Diagnosis and Localization of Glaucoma Using Deep Learning.” PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM). IEEE, 2018. 2357–2362. Print.
@inproceedings{8606441,
  abstract     = {Glaucoma is a major eye disease, leading to vision loss without proper medical treatment. Current diagnosis of glaucoma is performed by ophthalmologists who are typically analyzing different types of medical images generated by different types of medical equipment. However, capturing and analyzing these medical images is labor intensive and expensive. In this paper, we present a novel computational approach towards glaucoma diagnosis and localization, only making use of eye fundus images that are analyzed by state-of-the-art deep learning techniques. Specifically, our approach leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM) for glaucoma diagnosis and localization, respectively. Quantitative and qualitative results, as obtained for a small-sized dataset with no segmentation ground truth, demonstrate that the proposed approach is promising, for instance achieving an accuracy of 0.91 and an ROC-AUC score of 0.92 for the diagnosis task.},
  author       = {Kim, Mi Jung and Park, Ho-min and Zuallaert, Jasper and Janssens, Olivier and Van Hoecke, Sofie and De Neve, Wesley},
  booktitle    = {PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)},
  isbn         = {9781538654880},
  issn         = {2156-1125},
  language     = {eng},
  location     = {Madrid, SPAIN},
  pages        = {2357--2362},
  publisher    = {IEEE},
  title        = {Computer-aided diagnosis and localization of glaucoma using deep learning},
  year         = {2018},
}

Web of Science
Times cited: