Search

Neuron segmentation is an important task for automatic analyses of brain images that are of huge volume. Previous methods for neuron segmentation rely on handcrafted image features, and have difficulty in coping with high-resolution, low signal-to-noise-ratio brain images. Convolutional neural network (CNN) has achieved remarkable success in natural image segmentation, but CNN requires accurately labeled data for training that are difficult to achieve on brain images of huge volume. In this paper, we present a weakly supervised learning strategy to deal with the inaccurate training data problem, and thus adopt 3D CNN to perform automatic soma segmentation from brain images. We test our method on our own collected mouse brain images that are of single-neuron resolution, and results show that 3D CNN-based method outperforms the traditional methods by a significant margin.

This paper presents a novel tone mapping method for the display of high dynamic range (HDR) 3D brain images at single-neuron resolution, where the fluorescent labeled neurons exhibit extremely high local contrast. Existing tone mapping methods fit for natural images cannot well preserve the details of neurons in the 3D brain image, and require huge memory when the image resolution is ultra high. Therefore, we propose a block-wise, progressive tone mapping strategy for efficient and high quality display of such image, which further offers two different modes for optimum global or local visual experience. Experimental results demonstrate that the proposed approach significantly improves the visualization quality of high contrast neurons in HDR brain images compared with existing methods.