Flood-Filling Networks

Abstract

State-of-the-art image segmentation algorithms generally consist of at least two successive and distinct computations: a boundary detection process that uses local image information to classify image locations as boundaries between objects, followed by a pixel grouping step such as watershed or connected components that clusters pixels into segments. Prior work has varied the complexity and approach employed in these two steps, including the incorporation of multi-layer neural networks to perform boundary prediction, and the use of global optimizations during pixel clustering. We propose a unified and end-to-end trainable machine learning approach, flood-filling networks, in which a recurrent 3d convolutional network directly produces individual segments from a raw image. The proposed approach robustly segments images with an unknown and variable number of objects as well as highly variable object sizes. We demonstrate the approach on a challenging 3d image segmentation task, connectomic reconstruction from volume electron microscopy data, on which flood-filling neural networks substantially improve accuracy over other state-of-the-art methods. The proposed approach can replace complex multi-step segmentation pipelines with a single neural network that is learned end-to-end.

11 pages, 4 figures

References in corpus (6)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Identity Mappings in Deep Residual Networks
• Pixel-wise Deep Learning for Contour Detection
• Learning to Refine Object Segments
• Pushing the Boundaries of Boundary Detection using Deep Learning
• Image Segmentation by Size-Dependent Single Linkage Clustering of a Watershed Basin Graph

Cited by in corpus (7)

• Large Scale Image Segmentation with Structured Loss based Deep Learning for Connectome Reconstruction
• A Multi-Pass Approach to Large-Scale Connectomics
• Morphological Error Detection in 3D Segmentations
• Beyond the Pixel-Wise Loss for Topology-Aware Delineation
• Learning and Segmenting Dense Voxel Embeddings for 3D Neuron Reconstruction
• Detecting Synapse Location and Connectivity by Signed Proximity Estimation and Pruning with Deep Nets
• Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping