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 μm (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.

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 βm (1-2 pixels) and a Dice coefficient for the fluid segmentation of 0.96.