Neuron Segmentation Using Deep Complete Bipartite Networks
This work addresses a key challenge in neuroscience for quantitative analysis, such as tracing cell genesis in zebrafish brains, but it is incremental as it builds on existing FCN-type models.
The paper tackles the problem of segmenting dense clusters of neuronal cells in microscopy images, where existing FCN models are inaccurate and pixel-wise ground truth is scarce, by proposing a new CB-Net model and training scheme that outperforms state-of-the-art FCN models on seven real datasets.
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