Application of different imaging modalities for diagnosis of Diabetic Macular Edema: A review

Mookiah MR 1 , Acharya UR 2 , Fujita H 3 , Tan JH 4 , Chua CK 4 , Bhandary SV 5 Show all authors , Laude A 6 , Tong L 7

Affiliations 

  • 1 Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, 599489, Singapore. Electronic address: mkm2@np.edu.sg
  • 2 Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, 599489, Singapore; Department of Biomedical Engineering, School of Science and Technology, SIM University, 599491, Singapore; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia
  • 3 Faculty of Software and Information Science, Iwate Prefectural University (IPU), Iwate 020-0693, Japan
  • 4 Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, 599489, Singapore
  • 5 Department of Ophthalmology, Kasturba Medical College, Manipal 576104, India
  • 6 National Healthcare Group Eye Institute, Tan Tock Seng Hospital, 308433, Singapore
  • 7 Singapore National Eye Center, 168751, Singapore; Ocular Surface Research Group, Singapore Eye Research Institute, 168751, Singapore; Duke-NUS Graduate Medical School, 169857, Singapore; Yong Loo Lin School of Medicine, National University of Singapore, 117597, Singapore
Comput Biol Med, 2015 Nov 1;66:295-315.
PMID: 26453760 DOI: 10.1016/j.compbiomed.2015.09.012

Abstract

Diabetic Macular Edema (DME) is caused by accumulation of extracellular fluid from hyperpermeable capillaries within the macula. DME is one of the leading causes of blindness among Diabetes Mellitus (DM) patients. Early detection followed by laser photocoagulation can save the visual loss. This review discusses various imaging modalities viz. biomicroscopy, Fluorescein Angiography (FA), Optical Coherence Tomography (OCT) and colour fundus photographs used for diagnosis of DME. Various automated DME grading systems using retinal fundus images, associated retinal image processing techniques for fovea, exudate detection and segmentation are presented. We have also compared various imaging modalities and automated screening methods used for DME grading. The reviewed literature indicates that FA and OCT identify DME related changes accurately. FA is an invasive method, which uses fluorescein dye, and OCT is an expensive imaging method compared to fundus photographs. Moreover, using fundus images DME can be identified and automated. DME grading algorithms can be implemented for telescreening. Hence, fundus imaging based DME grading is more suitable and affordable method compared to biomicroscopy, FA, and OCT modalities.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

MeSH terms
Similar publications