CERCA
09-10-2018 10:18

SEMINARIO PROF. PETER HORVATH

Martedì 16 Ottobre 2018, 10:00-11:00

Aula 3.7, Via Machiavelli - Via Pavese

Scuola di Ingegneria ed Architettura, Cesena

Università di Bologna

 

"Life beyond the pixels: single-cell analysis of cancer using machine learning and image analysis methods"

 Il Prof. Peter Horvath è Direttore dell’Istituto di Biochimica del Biological Research Centre (BRC), Hungarian Academy of Sciences, Szeged, Ungheria; Professore in Finlandia nell’Institute for Molecular Medicine Finland (FIMM) di Helsinki; Team Leader del Biological Image Analysis and Machine Learning Group (BIOMAG) a Szeged; Fondatore, Consigliere e Membro di varie società Europee tra cui European Cell-based Assays Interest Group (EUCAI), Society of Biomolecular Imaging and Informatics (SBI2) e Network of European BioImage Analysts (NEUBIAS). Opera principalmente nel campo della Computer Vision, Machine Learning e Big-Data Analysis, con applicazioni in Microscopy e High-Content Screening, e vanta lavori pubblicati in riviste di alto prestigio, tra cui Science Nature Reviews Drug Discovery

Con queste parole Peter descrive il contenuto del seminario: “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 vignetting and uneven background effects which, left uncorrected, corrupt intensity-based measurements. Then, new single-cell image segmentation methods will be presented using energy minimization methods. I will discuss 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 a graphical user interface 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 recently developed 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, dPCR, and targeted electrophysiology measurements on the selected cells.”


Siete caldamente invitati a partecipare.