LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
This addresses the lack of manually annotated training data for ophthalmology imaging, though it is incremental as it builds on existing unsupervised algorithms.
The paper tackles the problem of 3D retinal vessel segmentation in OCT-A images by proposing a learning-based method supervised by a self-synthesized modality, achieving a Dice score of 0.7736 on human data and 0.8594 +/- 0.0275 on zebrafish data.
Optical coherence tomography (OCT) is a non-invasive imaging technique widely used for ophthalmology. It can be extended to OCT angiography (OCT-A), which reveals the retinal vasculature with improved contrast. Recent deep learning algorithms produced promising vascular segmentation results; however, 3D retinal vessel segmentation remains difficult due to the lack of manually annotated training data. We propose a learning-based method that is only supervised by a self-synthesized modality named local intensity fusion (LIF). LIF is a capillary-enhanced volume computed directly from the input OCT-A. We then construct the local intensity fusion encoder (LIFE) to map a given OCT-A volume and its LIF counterpart to a shared latent space. The latent space of LIFE has the same dimensions as the input data and it contains features common to both modalities. By binarizing this latent space, we obtain a volumetric vessel segmentation. Our method is evaluated in a human fovea OCT-A and three zebrafish OCT-A volumes with manual labels. It yields a Dice score of 0.7736 on human data and 0.8594 +/- 0.0275 on zebrafish data, a dramatic improvement over existing unsupervised algorithms.