Detecting glaucomatous wedge shaped defects in polarimetric images
| Autor: | Koen A. Vermeer, Frans M. Vos, H. G. Lemij, Albert M. Vossepoel |
|---|---|
| Přispěvatelé: | Amsterdam Gastroenterology Endocrinology Metabolism, Amsterdam Neuroscience, Radiology and Nuclear Medicine |
| Rok vydání: | 2003 |
| Předmět: |
Materials science
Optic Disk Nerve fiber layer Polarimetry Glaucoma Scanning laser polarimetry Health Informatics Diagnostic Techniques Ophthalmological Sensitivity and Specificity Wedge (geometry) Retina law.invention Nerve Fibers Optics law medicine Humans Radiology Nuclear Medicine and imaging Computer vision Diagnosis Computer-Assisted Sensitivity (control systems) Radiological and Ultrasound Technology business.industry Lasers Laser medicine.disease Computer Graphics and Computer-Aided Design medicine.anatomical_structure Computer Vision and Pattern Recognition Artificial intelligence business |
| Zdroj: | Medical image analysis, 7(4), 503-511. Elsevier |
| ISSN: | 1361-8415 |
| DOI: | 10.1016/s1361-8415(03)00041-0 |
| Popis: | Wedge shaped defects of the retinal nerve fiber layer (RNFL) may occur in glaucoma. Currently, automatic detection of wedge shaped defects in Scanning Laser Polarimetry (SLP) images of the RNFL is not available. An automatic classification is currently based only on global parameters, thereby ignoring important local information. Our method works by a modified dynamic programming technique that searches for locally strong edges with a preference for straight edges. These edges are initially classified based on their strength and next combined into wedge shaped defects. Our method yields a sensitivity of 73% and a specificity of 90% on a limited set of 65 images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect