Fully Convolutional Network-Based Eyeball Segmentation from Sparse Annotation for Eye Surgery Simulation Model

This paper presents a fully convolutional network-based segmentation method to create an eyeball model data for patient-specific ophthalmologic surgery simulation. In order to create an elaborate eyeball model for each patient, we need to accurately segment eye structures with different sizes and complex shapes from high-resolution images. Therefore, we aim to construct a fully convolutional network to enable accurate segmentation of anatomical structures in an eyeball from training on sparsely-annotated images, which can provide a user with all annotated slices if he or she annotates a few slices in each image volume data. In this study, we utilize a fully convolutional network with full-resolution residual units that effectively learns multi-scale image features for segmentation of eye macro- and microstructures by acting as a bridge between the two processing streams (residual and pooling streams). In addition, a weighted loss function and data augmentation are utilized for network training to accurately perform the semantic segmentation from only sparsely-annotated axial images. From the results of segmentation experiments using micro-CT images of pig eyeballs, we found that the proposed network provided better segmentation performance than conventional networks and achieved mean Dice similarity coefficient scores of 91.5% for segmentation of eye structures even from a small amount of training data.