Donghao Zhang

Rivulet: 3D Neuron Morphology Tracing with Iterative Back-Tracking

The digital reconstruction of single neurons from 3D confocal microscopic images is an important tool for understanding the neuron morphology and function. However the accurate automatic neuron reconstruction remains a challenging task due to the varying image quality and the complexity in the neuronal arborisation. Targeting the common challenges of neuron tracing, we propose a novel automatic 3D neuron reconstruction algorithm, named Rivulet, which is based on the multi-stencils fast-marching and iterative back-tracking. The proposed Rivulet algorithm is capable of tracing discontinuous areas without being interrupted by densely distributed noises. By evaluating the proposed pipeline with the data provided by the Diadem challenge and the recent BigNeuron project, Rivulet is shown to be robust to challenging microscopic imagestacks. We discussed the algorithm design in technical details regarding the relationships between the proposed algorithm and the other state-of-the-art neuron tracing algorithms.

Automated 3D Soma Segmentation with Morphological Surface Evolution for Neuron Reconstruction

The automatic neuron reconstruction is important since it accelerates the collection of 3D neuron models for the neuronal morphological studies. The majority of the previous neuron reconstruction methods only focused on tracing neuron fibres without considering the somatic surface. Thus, topological errors often present around the soma area in the results obtained by these tracing methods. Segmentation of the soma structures can be embedded in the existing neuron tracing methods to reduce such topological errors. In this paper, we present a novel method to segment the soma structures with complex geometry. It can be applied along with the existing methods in a fully automated pipeline. An approximate bounding block is firstly estimated based on a geodesic distance transform. Then the soma segmentation is obtained by evolving the surface with a set of morphological operators inside the initial bounding region. By evaluating the methods against the challenging images released by the BigNeuron project, we showed that the proposed method can outperform the existing soma segmentation methods regarding the accuracy. We also showed that the soma segmentation can be used for enhancing the results of existing neuron tracing methods.

Reconstruction of 3D neuron morphology using Rivulet back-tracking

The 3D reconstruction of neuronal morphology is a powerful technique for investigating nervous systems. Due to the noises in optical microscopic images, the automated reconstruction of neuronal morphology has been a challenging problem. We propose a novel automatic neuron reconstruction algorithm, Rivulet, to target the challenges raised by the poor quality of the optical microscopic images. After the neuron images being de-noised with an anisotropic filter, the Rivulet algorithm combines multi-stencils fast-marching and iterative back-tracking from the geodesic farthest point on the segmented foreground. The neuron segments are dumped or merged according to a set of criteria at the end of each iteration. The proposed Rivulet tracing algorithm is evaluated with data provided from the BigNeuron Project. The experimental results demonstrate that Rivulet outperforms the compared state-of-the-art tracing methods when the images are of poor quality.

Panoptic Segmentation with an End-to-End Cell R-CNN for Pathology Image Analysis

The morphological clues of various cancer cells are essential for pathologists to determine the stages of cancers. In order to obtain the quantitative morphological information, we present an end-to-end network for panoptic segmentation of pathology images. Recently, many methods have been proposed, focusing on the semantic-level or instance-level cell segmentation. Unlike existing cell segmentation methods, the proposed network unifies detecting, localizing objects and assigning pixel-level class information to regions with large overlaps such as the background. This unifier is obtained by optimizing the novel semantic loss, the bounding box loss of Region Proposal Network (RPN), the classifier loss of RPN, the background-foreground classifier loss of segmentation Head instead of class-specific loss, the bounding box loss of proposed cell object, and the mask loss of cell object. The results demonstrate that the proposed method not only outperforms state-of-the-art approaches to the 2017 MICCAI Digital Pathology Challenge dataset, but also proposes an effective and end-to-end solution for the panoptic segmentation challenge.

Triple-Crossing 2.5D Convolutional Neural Network for Detecting Neuronal Arbours in 3D Microscopic Images

The automatic analysis of the 3D optical microscopic images containing neuron cells remains one of the central challenges in the modern computational neuroscience. The varying image qualities make the accurate detection of the curvilinear neuronal arbours elusive. The high computational cost raised by large 3D image volumes also makes the conventional filter-bank learning methods impractical. We present a novel Triple-Crossing (TC) 2.5D convolutional neural network to detect the neuronal arbours in large 3D microscopic volumes with a reasonable computational cost. The network is trained to output a regression map that indicates the presence of the neuronal arbours. The proposed methods can be used as a pre-processing step in an automated neuronal circuit reconstruction pipeline, which enables the collection of large-scale neuron morphological datasets. In our experiments, we show that the proposed methods could effectively eliminate dense background noises and fix the gaps along neuronal arbours. The proposed methods could also outperform the original 2.5D neural network regarding the training efficiency as well as the generalisation performance.