We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Local directional gradient pattern histogram and optimization based deep residual network for age related macular degeneration detection.
- Authors
Ashok, S.; Jaffino, G.; Prabin Jose, J.; Murthy, K. V. S. Ramachandra
- Abstract
The ocular condition known as age-related macular degeneration (AMD) affects the retina and impairs vision in the elderly. For both controlling and detecting retinal illnesses like AMD, optical coherence tomography (OCT) is an important investigative tool. The accurate segmentation of retinal layers is critical, as accurately segmenting the layers helps ophthalmologists for early diagnosis of AMD. An accurate and effective detection technique is created using the proposed Water Cycle Corona Virus Optimization-based Deep Residual Network (WCCVO-based DRN) to address these problems and identify AMD at the early stages. In the first step, the active contour model is used to segment the layers, and features such as reflectivity, thickness, curvature, statistical features, and the devised Local Directional Gradient Pattern Histogram (LDGPH) are retrieved. The LDGPH is designed based on the concept of Local Directional pattern (LDP) and Local Gradient pattern (LGP). At last, for the AMD detection DRN classifier is used, which is trained by the devised WCCVO. The accuracy, sensitivity, and specificity metrics for the WCCVO-based DRN achieved satisfactory performance with values of 0.916, 0.923, and 0.919.
- Subjects
MACULAR degeneration; OPTICAL coherence tomography; HYDROLOGIC cycle; CORONAVIRUSES; RETINA
- Publication
Multimedia Tools & Applications, 2024, Vol 83, Issue 32, p77303
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-024-18549-6