Scientific Results

Deep learning strategies for scalable analysis of high-resolution brain imagery

Year: 2019

Authors: Mazzamuto G., Orsini F., Roffilli M., Frasconi P., Pavone F. S., Silvestri S.

Autors Affiliation: European Laboratory for Non-linear Spectroscopy (LENS)
University of Florence, Department of Physics and Astronomy
University of Florence, Department of Information Engineering (DINFO)
Bioretics Srl
National Institute of Optics, National Research Council (INO-CNR)

Abstract: Deciphering brain architecture at a system level requires the ability to quantitatively map its structure with cellular and
subcellular resolution. Besides posing significant challenges to current optical microscopy methods, this ambitious goal
requires the development of a new generation of tools to make sense of the huge number of raw images generated, which
can easily exceed several TeraBytes for a single sample. We present an integrated pipeline enabling transformation of the
acquired dataset from a collection of voxel gray levels to a semantic representation of the sample. This pipeline starts
with a software for image stitching that computes global optimal alignment of the 3D tiles. The fused volume is then
accessed virtually by means of a dedicated API (Application Programming Interface). The virtually fused volume is then
processed to extract meaningful information. We demonstrate two complementary approaches based on deep
convolutional networks. In one case, a 3D conv-net is used to ‘semantically deconvolve’ the image, allowing accurate
localization of neuronal bodies with standard clustering algorithms (e.g. mean shift). The scalability of this approach is
demonstrated by mapping the spatial distribution of different neuronal populations in a whole mouse brain with singlecell
resolution. To go beyond simple localization, we exploited a 2D conv-net estimating for each pixel the probability of
being part of a neuron. The output of the net is then processed with a contour finding algorithm, obtaining reliable
segmentation of cell morphology. This information can be used to classify neurons, expanding the potential of chemical
labeling strategies.

Conference title:
Place:

KeyWords: Image analysis, deep learning, machine learning, segmentation, light-sheet microscopy, whole-brain imaging

gdpr-image
This site uses cookies. If you decide to continue browsing we consider that you accept their use. For more information about cookies and how to delete them please read our Info Policy on cookies use.
Read more