BreakNet: Discontinuity-Resilient Multi-Scale Transformer Segmentation of Retinal Layers

TL;DR

BreakNet is a multi-scale Transformer-based model that effectively segments retinal layers in vis-OCT images, overcoming shadow artifacts and boundary discontinuities for improved retinal analysis.

Contribution

The paper introduces BreakNet, a novel Transformer-based segmentation model that handles boundary discontinuities caused by shadow artifacts in retinal imaging.

Findings

BreakNet outperforms state-of-the-art models like U-Net and TCCT-BP.

It maintains high segmentation accuracy even with limited ground truth data.

The model effectively captures multi-scale features for precise retinal layer segmentation.

Abstract

Visible light optical coherence tomography (vis-OCT) is gaining traction for retinal imaging due to its high resolution and functional capabilities. However, the significant absorption of hemoglobin in the visible light range leads to pronounced shadow artifacts from retinal blood vessels, posing challenges for accurate layer segmentation. In this study, we present BreakNet, a multi-scale Transformer-based segmentation model designed to address boundary discontinuities caused by these shadow artifacts. BreakNet utilizes hierarchical Transformer and convolutional blocks to extract multi-scale global and local feature maps, capturing essential contextual, textural, and edge characteristics. The model incorporates decoder blocks that expand pathwaproys to enhance the extraction of fine details and semantic information, ensuring precise segmentation. Evaluated on rodent retinal images acquired with prototype vis-OCT, BreakNet demonstrated superior performance over state-of-the-art segmentation models, such as TCCT-BP and U-Net, even when faced with limited-quality ground truth data. Our findings indicate that BreakNet has the potential to significantly improve retinal quantification and analysis.