BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images

TL;DR

This paper introduces BioNet, a novel biomarker-infused global-to-local network for more accurate and robust choroid segmentation in OCT images, leveraging biomarker features as regularizers.

Contribution

The paper proposes a new biomarker-infused segmentation framework that improves choroid segmentation accuracy by integrating biomarker features into a global-to-local network architecture.

Findings

Achieved 90.77% Dice-index on AROD dataset.

Reduced average surface detection error to 6.23 pixels.

Outperformed state-of-the-art methods in choroid segmentation.

Abstract

Choroid is the vascular layer of the eye, which is directly related to the incidence and severity of many ocular diseases. Optical Coherence Tomography (OCT) is capable of imaging both the cross-sectional view of retina and choroid, but the segmentation of the choroid region is challenging because of the fuzzy choroid-sclera interface (CSI). In this paper, we propose a biomarker infused global-to-local network (BioNet) for choroid segmentation, which segments the choroid with higher credibility and robustness. Firstly, our method trains a biomarker prediction network to learn the features of the biomarker. Then a global multi-layers segmentation module is applied to segment the OCT image into 12 layers. Finally, the global multi-layered result and the original OCT image are fed into a local choroid segmentation module to segment the choroid region with the biomarker infused as regularizer. We conducted comparison experiments with the state-of-the-art methods on a dataset (named AROD). The experimental results demonstrate the superiority of our method with $90.77\%$ Dice-index and 6.23 pixels Average-unsigned-surface-detection-error, etc.