World-class research. Ultimate impact.
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Comput. Sci. | doi: 10.3389/fcomp.2019.00006

Leveraging Domain Knowledge to Improve Microscopy Image Segmentation with Lifted Multicuts

 Constantin Pape1, 2, Alex Matskevych2,  Adrian Wolny2,  Julian Hennies2, Giulia Mizzon2,  Marion Louveaux3, Jacob Musser2,  Alexis Maizel3, Detlev Arendt2 and  Anna Kreshuk2*
  • 1Heidelberg University, Germany
  • 2European Molecular Biology Laboratory Heidelberg, Germany
  • 3Center for Organismic Studies, University of Heidelberg, Germany

The throughput of electron microscopes has increased significantly in recent years,
enabling detailed analysis of cell morphology and ultrastructure in fairly large tissue volumes. Analysis of neural circuits at single-synapse resolution remains the flagship target of this technique, but applications to cell and developmental biology are also starting to emerge at scale. On the light microscopy side, continuous development of light-sheet microscopes has led to a rapid increase in imaged volume dimensions, making Terabyte-scale acquisitions routine in the field.

The amount of data acquired in such studies makes manual instance segmentation, a fundamental
step in many analysis pipelines, impossible.
While automatic segmentation approaches have improved significantly thanks to the
adoption of convolutional neural networks, their accuracy still lags behind human annotations
and requires additional manual proof-reading.
A major hindrance to further improvements is the limited field of view of the segmentation networks
preventing them from learning to exploit the expected cell morphology or other prior biological knowledge which
humans use to inform their segmentation decisions.
In this contribution, we show how such domain-specific information can be leveraged by expressing it as long-range interactions
in a graph partitioning problem known as the lifted multicut problem.
Using this formulation, we demonstrate significant improvement in segmentation accuracy for four challenging boundary-based
segmentation problems from neuroscience and developmental biology.

Keywords: biomedical image analysis, Instance segmentation, biological priors, EM segmentation, LM segmentation, connectomics, Lifted multicut

Received: 05 Aug 2019; Accepted: 01 Oct 2019.

Copyright: © 2019 Pape, Matskevych, Wolny, Hennies, Mizzon, Louveaux, Musser, Maizel, Arendt and Kreshuk. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Mx. Anna Kreshuk, European Molecular Biology Laboratory Heidelberg, Heidelberg, 69117, Baden-Württemberg, Germany, anna.kreshuk@embl.de