Joint Segmentation of Retinal Layers and Focal Lesions in 3-D OCT Data of Topologically Disrupted Retinas
| Autor: | Lucas J. van Vliet, Jelena Novosel, Ziyuan Wang, Jan H. de Jong, Koenraad A. Vermeer |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Drusen
01 natural sciences Retina 030218 nuclear medicine & medical imaging 010309 optics 03 medical and health sciences chemistry.chemical_compound Macular Degeneration 0302 clinical medicine Sørensen–Dice coefficient Optical coherence tomography Retinal Diseases 0103 physical sciences Medicine Humans Segmentation Computer vision Electrical and Electronic Engineering Radiological and Ultrasound Technology medicine.diagnostic_test business.industry Retinal Image segmentation Macular degeneration medicine.disease Computer Science Applications medicine.anatomical_structure chemistry Artificial intelligence business Software Algorithms Tomography Optical Coherence |
| Zdroj: | IEEE transactions on medical imaging. 36(6) |
| ISSN: | 1558-254X |
| Popis: | Accurate quantification of retinal structures in 3-D optical coherence tomography data of eyes with pathologies provides clinically relevant information. We present an approach to jointly segment retinal layers and lesions in eyes with topology-disrupting retinal diseases by a loosely coupled level set framework. In the new approach, lesions are modeled as an additional space-variant layer delineated by auxiliary interfaces. Furthermore, the segmentation of interfaces is steered by local differences in the signal between adjacent retinal layers, thereby allowing the approach to handle local intensity variations. The accuracy of the proposed method of both layer and lesion segmentation has been evaluated on eyes affected by central serous retinopathy and age-related macular degeneration. In addition, layer segmentation of the proposed approach was evaluated on eyes without topology-disrupting retinal diseases. Good agreement between the segmentation performed manually by a medical doctor and results obtained from the automatic segmentation was found for all data types. The mean unsigned error for all interfaces varied between 2.3 and 11.9 $\mu \text{m}$ (0.6–3.1 pixels). Furthermore, lesion segmentation showed a Dice coefficient of 0.68 for drusen and 0.89 for fluid pockets. Overall, the method provides a flexible and accurate solution to jointly segment lesions and retinal layers. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|