Locally-adaptive loosely-coupled level sets for retinal layer and fluid segmentation in subjects with central serous retinopathy
| Autor: | Jelena Novosel, Ziyuan Wang, Lucas J. van Vliet, Henk de Jong, Koenraad A. Vermeer, Mirjam E J van Velthoven |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Pixel
medicine.diagnostic_test Computer science business.industry Interface (computing) Central serous retinopathy Retinal medicine.disease 030218 nuclear medicine & medical imaging 03 medical and health sciences chemistry.chemical_compound 0302 clinical medicine chemistry Optical coherence tomography Attenuation coefficient 030221 ophthalmology & optometry medicine Segmentation Computer vision Artificial intelligence business |
| Zdroj: | ISBI |
| DOI: | 10.1109/isbi.2016.7493363 |
| Popis: | We present a locally-adaptive approach to segment the fluid and the interfaces between retinal layers in eyes affected by central serous retinopathy based on loosely-coupled level sets. The approach exploits the local attenuation coefficient differences of layers around an interface and introduces auxiliary interfaces to delineate the fluid. Thus, it can handle abrupt attenuation coefficient variations and topology-disrupting anomalies. The method was applied to in-vivo images of retinas acquired by optical coherence tomography. A quantitative comparison with manual annotations shows the method's high accuracy: we obtained a mean absolute deviation for the interfaces of 3.7–8.9 sm (1–2 pixels) and a Dice coefficient for the fluid segmentation of 0.96. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|