A Bayesian framework for glaucoma progression detection using Heidelberg Retina Tomograph images

Glaucoma, the second leading cause of blindness in the United States, is an ocular disease characterized by structural changes of the optic nerve head (ONH) and changes in visual function. Therefore, early detection is of high importance to preserve remaining visual function. In this context, the Heidelberg Retina Tomograph (HRT), a confocal scanning laser tomograph, is widely used as a research tool as well as a clinical diagnostic tool for imaging the optic nerve head to detect glaucoma and monitor its progression. In this paper, a glaucoma progression detection technique is proposed using the HRT images. Contrary to the existing methods that do not integrate the spatial pixel dependency in the change detection map, we propose the use of the Markov Random Field (MRF) to handle a such dependency. In order to estimate the model parameters, a Monte Carlo Markov Chain procedure is used. We then compared the diagnostic performance of the proposed framework to existing methods of glaucoma progression detection.

@article{Belghith2013,
  title     = {A Bayesian framework for glaucoma progression detection using Heidelberg Retina Tomograph images},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {4},
  number    = {9},
  year      = {2013},
  publisher = {The Science and Information Organization},
  author    = {Akram Belghith and Christopher Bowd and Madhusudhanan Balasubramanian and Robert N. Weinreb and Linda M. Zangwill},
  doi       = {10.14569/IJACSA.2013.040934},
  url       = {https://doi.org/10.14569/IJACSA.2013.040934}
}