Learning Metric Graphs for Neuron Segmentation In Electron Microscopy Images

01/31/2019
by   Kyle Luther, et al.
0

In the deep metric learning approach to image segmentation, a convolutional net densely generates feature vectors at the pixels of an image. Pairs of feature vectors are trained to be similar or different, depending on whether the corresponding pixels belong to same or different ground truth segments. To segment a new image, the feature vectors are computed and clustered. Both empirically and theoretically, it is unclear whether or when deep metric learning is superior to the more conventional approach of directly predicting an affinity graph with a convolutional net. We compare the two approaches using brain images from serial section electron microscopy images, which constitute an especially challenging example of instance segmentation. We first show that seed-based postprocessing of the feature vectors, as originally proposed, produces inferior accuracy because it is difficult for the convolutional net to predict feature vectors that remain uniform across large objects. Then we consider postprocessing by thresholding a nearest neighbor graph followed by connected components. In this case, segmentations from a "metric graph" turn out to be competitive or even superior to segmentations from a directly predicted affinity graph. To explain these findings theoretically, we invoke the property that the metric function satisfies the triangle inequality. Then we show with an example where this constraint suppresses noise, causing connected components to more robustly segment a metric graph than an unconstrained affinity graph.

READ FULL TEXT

page 1

page 3

page 4

research
03/30/2017

Semantic Instance Segmentation via Deep Metric Learning

We propose a new method for semantic instance segmentation, by first com...
research
11/28/2009

Maximin affinity learning of image segmentation

Images can be segmented by first using a classifier to predict an affini...
research
09/21/2019

Learning Dense Voxel Embeddings for 3D Neuron Reconstruction

We show dense voxel embeddings learned via deep metric learning can be e...
research
09/09/2017

A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs

We present a deep structured learning method for neuron segmentation fro...
research
03/15/2020

Deep Affinity Net: Instance Segmentation via Affinity

Most of the modern instance segmentation approaches fall into two catego...
research
05/10/2019

Supervized Segmentation with Graph-Structured Deep Metric Learning

We present a fully-supervized method for learning to segment data struct...
research
04/22/2021

VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution

We present the system that we have developed for the identification and ...

Please sign up or login with your details

Forgot password? Click here to reset