A Bilayer Segmentation-Recombination Network for Accurate Segmentation of Overlapping C. elegans

TL;DR

This paper introduces BR-Net, a novel deep learning model designed to improve the segmentation accuracy of overlapping C. elegans in microscopy images by addressing boundary ambiguity and occlusion issues.

Contribution

The paper proposes a Bilayer Segmentation-Recombination Network with specialized modules for coarse segmentation, overlap handling, and semantic consistency, advancing the state-of-the-art in nematode image segmentation.

Findings

BR-Net outperforms existing methods on C. elegans datasets.

The model effectively handles overlapping and translucent boundary challenges.

Experimental results demonstrate improved segmentation accuracy.

Abstract

Caenorhabditis elegans (C. elegans) is an excellent model organism because of its short lifespan and high degree of homology with human genes, and it has been widely used in a variety of human health and disease models. However, the segmentation of C. elegans remains challenging due to the following reasons: 1) the activity trajectory of C. elegans is uncontrollable, and multiple nematodes often overlap, resulting in blurred boundaries of C. elegans. This makes it impossible to clearly study the life trajectory of a certain nematode; and 2) in the microscope images of overlapping C. elegans, the translucent tissues at the edges obscure each other, leading to inaccurate boundary segmentation. To solve these problems, a Bilayer Segmentation-Recombination Network (BR-Net) for the segmentation of C. elegans instances is proposed. The network consists of three parts: A Coarse Mask Segmentation Module (CMSM), a Bilayer Segmentation Module (BSM), and a Semantic Consistency Recombination Module (SCRM). The CMSM is used to extract the coarse mask, and we introduce a Unified Attention Module (UAM) in CMSM to make CMSM better aware of nematode instances. The Bilayer Segmentation Module (BSM) segments the aggregated C. elegans into overlapping and non-overlapping regions. This is followed by integration by the SCRM, where semantic consistency regularization is introduced to segment nematode instances more accurately. Finally, the effectiveness of the method is verified on the C. elegans dataset. The experimental results show that BR-Net exhibits good competitiveness and outperforms other recently proposed instance segmentation methods in processing C. elegans occlusion images.