Life beyond the pixels: single-cell analysis using deep learning and image analysis methods

In this talk I will give an overview of the computational steps in the analysis of a single cell-based large-scale microscopy experiments. First, I will present a novel microscopic image correction method designed to eliminate illumination and uneven background effects which, left uncorrected, corrupt intensity-based measurements. New single-cell image segmentation methods will be presented using differential geometry, energy minimization and deep learning methods (www.nucleAIzer.org) (Hollandi et al. 2022). I will discuss the Advanced Cell Classifier (ACC) (www.cellclassifier.org), a machine learning software tool capable of identifying cellular phenotypes based on features extracted from the image. It provides an interface for a user to efficiently train machine learning methods to predict various phenotypes. For cases where discrete cell-based decisions are not suitable, we propose a method to use multi-parametric regression to analyze continuous biological phenomena. To improve the learning speed and accuracy, we propose an active learning scheme that selects the most informative cell samples. Our recently developed single-cell isolation methods, based on laser-microcapturing and patch clamping, utilize the selection and extraction of specific cell(s) using the above machine learning models (Brasko et al. 2018). I will show that we successfully performed DNA and RNA sequencing, proteomics, lipidomics and targeted electrophysiology measurements on the selected cells (Mund et al. 2022).

Peter Horvath

Director, Group Leader

Institute of Biochemistry, Biological Research Centre, Szeged

Peter Horvath is currently the director and a group leader in the Biological Research Center in Szeged and holds a Finnland Distinguished Professor Fellow position in the Institute for Molecular Medicine Finland, Helsinki. He graduated as a software engineer and received his Ph.D. from INRIA and University of Nice, Sophia Antipois, France in satellite image analysis. Between 2007 and 2013 he was a senior scientist at the ETH Zurich, in the Light Microscopy Centre. He is interested in solving computational cell biology problems related to light microscopy and is involved in four main research fields; 2/3D biological image segmentation and tracking; development of microscopic image correction techniques; machine learning methods applied in high-throughput microscopy and the development of single-cell isolation methods. He is the co-founder of the European Cell-based Assays Interest Group and the councilor of the Society of Biomolecular Imaging and Informatics.

Key:

Complete
Failed
Available
Locked
Life beyond the pixels: single-cell analysis using deep learning and image analysis methods
Open to view video.  |   Closed captions available
Open to view video.  |   Closed captions available In this talk I will give an overview of the computational steps in the analysis of a single cell-based large-scale microscopy experiments. First, I will present a novel microscopic image correction method designed to eliminate illumination and uneven background effects which, left uncorrected, corrupt intensity-based measurements. New single-cell image segmentation methods will be presented using differential geometry, energy minimization and deep learning methods. I will discuss the Advanced Cell Classifier (ACC), a machine learning software tool capable of identifying cellular phenotypes based on features extracted from the image. It provides an interface for a user to efficiently train machine learning methods to predict various phenotypes. For cases where discrete cell-based decisions are not suitable, we propose a method to use multi-parametric regression to analyze continuous biological phenomena. To improve the learning speed and accuracy, we propose an active learning scheme that selects the most informative cell samples. Our recently developed single-cell isolation methods, based on laser-microcapturing and patch clamping, utilize the selection and extraction of specific cell(s) using the above machine learning models. I will show that we successfully performed DNA and RNA sequencing, proteomics, lipidomics and targeted electrophysiology measurements on the selected cells.
You must register to access.