Neuron Segmentation Using Deep Complete Bipartite Networks

TL;DR

This paper introduces a novel deep learning model called CB-Net for neuron segmentation in microscopy images, effectively handling dense cell clusters and limited annotations, and demonstrating superior performance over existing models.

Contribution

The paper presents a new FCN-type deep learning architecture, CB-Net, and a training scheme that leverages approximate annotations, improving neuron segmentation accuracy in challenging microscopy images.

Findings

CB-Net outperforms existing FCN models on seven datasets.

The proposed method effectively handles dense neuronal clusters.

Limited approximate annotations can be successfully used for training.

Abstract

In this paper, we consider the problem of automatically segmenting neuronal cells in dual-color confocal microscopy images. This problem is a key task in various quantitative analysis applications in neuroscience, such as tracing cell genesis in Danio rerio (zebrafish) brains. Deep learning, especially using fully convolutional networks (FCN), has profoundly changed segmentation research in biomedical imaging. We face two major challenges in this problem. First, neuronal cells may form dense clusters, making it difficult to correctly identify all individual cells (even to human experts). Consequently, segmentation results of the known FCN-type models are not accurate enough. Second, pixel-wise ground truth is difficult to obtain. Only a limited amount of approximate instance-wise annotation can be collected, which makes the training of FCN models quite cumbersome. We propose a new FCN-type deep learning model, called deep complete bipartite networks (CB-Net), and a new scheme for leveraging approximate instance-wise annotation to train our pixel-wise prediction model. Evaluated using seven real datasets, our proposed new CB-Net model outperforms the state-of-the-art FCN models and produces neuron segmentation results of remarkable quality