Deep neural networks segment neuronal membranes in electron microscopy images

Dan C. Cireşan, Alessandro Giusti, Luca M. Gambardella, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

985 Scopus citations

Abstract

We address a central problem of neuroanatomy, namely, the automatic segmentation of neuronal structures depicted in stacks of electron microscopy (EM) images. This is necessary to efficiently map 3D brain structure and connectivity. To segment biological neuron membranes, we use a special type of deep artificial neural network as a pixel classifier. The label of each pixel (membrane or nonmembrane) is predicted from raw pixel values in a square window centered on it. The input layer maps each window pixel to a neuron. It is followed by a succession of convolutional and max-pooling layers which preserve 2D information and extract features with increasing levels of abstraction. The output layer produces a calibrated probability for each class. The classifier is trained by plain gradient descent on a 512 × 512 × 30 stack with known ground truth, and tested on a stack of the same size (ground truth unknown to the authors) by the organizers of the ISBI 2012 EM Segmentation Challenge. Even without problem-specific postprocessing, our approach outperforms competing techniques by a large margin in all three considered metrics, i.e. rand error, warping error and pixel error. For pixel error, our approach is the only one outperforming a second human observer.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
Pages2843-2851
Number of pages9
StatePublished - Dec 1 2012
Externally publishedYes

Fingerprint

Dive into the research topics of 'Deep neural networks segment neuronal membranes in electron microscopy images'. Together they form a unique fingerprint.

Cite this