Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation

TL;DR

This paper introduces a novel deep learning framework combining fully convolutional and recurrent neural networks to effectively segment 3D biomedical images by explicitly addressing their anisotropic nature.

Contribution

It presents the first deep learning framework explicitly designed to leverage 3D image anisotropism for biomedical segmentation tasks.

Findings

Achieved promising segmentation results on ISBI neuronal data

Outperformed existing deep learning methods for 3D segmentation

Effectively exploited intra-slice and inter-slice contexts

Abstract

Segmentation of 3D images is a fundamental problem in biomedical image analysis. Deep learning (DL) approaches have achieved state-of-the-art segmentation perfor- mance. To exploit the 3D contexts using neural networks, known DL segmentation methods, including 3D convolution, 2D convolution on planes orthogonal to 2D image slices, and LSTM in multiple directions, all suffer incompatibility with the highly anisotropic dimensions in common 3D biomedical images. In this paper, we propose a new DL framework for 3D image segmentation, based on a com- bination of a fully convolutional network (FCN) and a recurrent neural network (RNN), which are responsible for exploiting the intra-slice and inter-slice contexts, respectively. To our best knowledge, this is the first DL framework for 3D image segmentation that explicitly leverages 3D image anisotropism. Evaluating using a dataset from the ISBI Neuronal Structure Segmentation Challenge and in-house image stacks for 3D fungus segmentation, our approach achieves promising results comparing to the known DL-based 3D segmentation approaches.