This Indico installation shall not be used to organise MPI-CBG courses and events from beginning of 2024 on. Please use MPG Indico instead.
12-15 August 2018
MPI-CBG
Europe/Berlin timezone

Combining Deep Learning and Active Contours Opens The Way to Robust, Automated Analysis of Brain Cytoarchitectonics.

Not scheduled
15m
MPI-CBG

MPI-CBG

Pfotenhauerstraße 108 01307 Dresden Germany
Poster Posters

Speaker

Dr Nico Scherf (MPI CBS)

Description

Deep learning has thoroughly changed the field of image analysis yielding impressive results whenever enough annotated data can be gathered. While partial annotation can be very fast, manual segmentation of 3D biological structures is tedious and error-prone. Additionally, high-level shape concepts such as topology or boundary smoothness are hard if not impossible to encode in Feedforward Neural Networks. Here we present a modular strategy for the accurate segmentation of neural cell bodies from light-sheet microscopy combining mixed-scale convolutional neural networks and topology-preserving geometric deformable models. We show that the network can be trained efficiently from simple cell centroid annotations, and that the final segmentation provides accurate cell detection and smooth segmentations that do not introduce further cell splitting or merging.

Affiliation Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig
Terms and Conditions Yes

Primary authors

Mr Konstantin Thierbach (MPI CBS) Dr Pierre-Louis Bazin (MPI CBS / Netherlands Institute for Neuroscience) Dr Walter De Back (TUD) Mr Filippos Gavriilidis (MPI CBS) Dr Carsten Jaeger (MPI CBS) Dr Stefan Geyer (MPI CBS) Dr Evgeniya Kirilina (MPI CBS) Dr Markus Morawski (PFI, Uni Leipzig) Prof. Nikolaus Weiskopf (MPI CBS) Dr Nico Scherf (MPI CBS)

Presentation Materials

There are no materials yet.
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now

×