Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation

TL;DR

This paper introduces a new dataset of volumetric vasculature microscopy images and demonstrates a hybrid 2D-3D deep learning approach for segmenting vasculature in these images, aiming to advance medical image analysis.

Contribution

The paper provides a publicly available dataset and applies a novel hybrid 2D-3D convolutional neural network architecture for vasculature segmentation in volumetric microscopy images.

Findings

Hybrid 2D-3D ConvNet achieved promising segmentation results.

Sharing datasets aims to foster further research and improvements.

Adaptation of architectures from electron microscopy segmentation.

Abstract

Recently there has been an increasing trend to use deep learning frameworks for both 2D consumer images and for 3D medical images. However, there has been little effort to use deep frameworks for volumetric vascular segmentation. We wanted to address this by providing a freely available dataset of 12 annotated two-photon vasculature microscopy stacks. We demonstrated the use of deep learning framework consisting both 2D and 3D convolutional filters (ConvNet). Our hybrid 2D-3D architecture produced promising segmentation result. We derived the architectures from Lee et al. who used the ZNN framework initially designed for electron microscope image segmentation. We hope that by sharing our volumetric vasculature datasets, we will inspire other researchers to experiment with vasculature dataset and improve the used network architectures.