Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection
arXiv:1703.08493
Abstract
In the field of connectomics, neuroscientists seek to identify cortical connectivity comprehensively. Neuronal boundary detection from the Electron Microscopy (EM) images is often done to assist the automatic reconstruction of neuronal circuit. But the segmentation of EM images is a challenging problem, as it requires the detector to be able to detect both filament-like thin and blob-like thick membrane, while suppressing the ambiguous intracellular structure. In this paper, we propose multi-stage multi-recursive-input fully convolutional networks to address this problem. The multiple recursive inputs for one stage, i.e., the multiple side outputs with different receptive field sizes learned from the lower stage, provide multi-scale contextual boundary information for the consecutive learning. This design is biologically-plausible, as it likes a human visual system to compare different possible segmentation solutions to address the ambiguous boundary issue. Our multi-stage networks are trained end-to-end. It achieves promising results on two public available EM segmentation datasets, the mouse piriform cortex dataset and the ISBI 2012 EM dataset.
arXiv commentAccepted by ICCV2017
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Holistically-Nested Edge Detection
- FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
- Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
- Machine learning of hierarchical clustering to segment 2D and 3D images
- Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph
- Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation