Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection

Citations Over TimeTop 10% of 2017 papers

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-recursiveinput 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.

Related Papers

• → Overview of deep learning in medical imaging(2017)1,052 cited
• → Deep learning ensemble 2D CNN approach towards the detection of lung cancer(2023)173 cited
• → Research and Application of Ancient Chinese Pattern Restoration Based on Deep Convolutional Neural Network(2021)4 cited
• → Leaf Features Extraction for Plant Classification using CNN(2021)7 cited
• → Deep Convolution Neural Network for RBC Images(2022)2 cited