|
|
**Emmanuel Moebel**
|
|
|
|
|
|
Inria Rennes Bretagne Atlantique, Serpico Group
|
|
|
|
|
|
Seminar on
|
|
|
|
|
|
**Exploring cellular landscapes with deep learning**
|
|
|
|
|
|
A method for identifying macromolecules in cryo-electron tomography images Cryo-electron tomography (cryo-ET) allows one to capture 3D images of cells in a close to native state, at sub-nanometer resolution. However, noise and artifact levels are such that heavy computational processing is needed to access the image content.
|
|
|
Deep learning (DL) is a set of machine learning techniques capable to produce state-of-the-art results in various fields (e.g. image analysis, pattern recognition, language processing). We therefore anticipate an increasing success of deep learning methods for cryo-ET analysis.
|
|
|
In this work, we propose a deep learning framework to accurately and jointly localize multiple types of macromolecules in cryo-ET. The method is based on image segmentation using a 3D convolutional neural network, therefore it also allows structures such as cell membranes to be identified. We evaluate our method on both synthetic and experimental data, and compare this framework to the commonly-used template matching.
|
|
|
|
|
|
* Date: Tuesday, April 30th, 2019
|
|
|
* Time: 10:30 am
|
|
|
* Place: ER-C-3, Building 05.2. Room 4016
|
|
|
|
|
|
* Host: Carsten Sachse/ Julio Ortiz (ER-C-3)
|
|
|
* Telefon: 02461 61-2032
|
|
|
* E-Mail: j.ortiz@fz-juelich.de |
|
|
\ No newline at end of file |