Supervised learning and dimension reduction techniques for quantification of retinal fluid in optical coherence tomography images

Purpose The purpose of the present study is to develop fast automated quantification of retinal fluid in optical coherence tomography (OCT) image sets. Methods We developed an image analysis pipeline tailored towards OCT images that consists of five steps for binary retinal fluid segmentation. The method is based on feature extraction, pre-segmention, dimension reduction procedures, and supervised learning tools. Results Fluid identification using our pipeline was tested on two separate patient groups: one associated to neovascular agerelated macular degeneration, the other showing diabetic macular edema. For training and evaluation purposes, retinal fluid was annotated manually in each cross-section by human expert graders of the Vienna Reading Center. Compared with the manual annotations, our pipeline yields good quantification, visually and in numbers. Conclusions By demonstrating good automated retinal fluid quantification, our pipeline appears useful to expert graders within their current grading processes. Owing to dimension reduction, the actual learning part is fast and requires only few training samples. Hence, it is well-suited for integration into actual manufacturer's devices, further improving segmentation by its use in daily clinical life.