Biomedical Imaging Algorithms

Biomedical Imaging Algorithms Research Group

InfoPeopleResearchProjectsNewsStudent topicsTheses

We’re a group researching in the areas of humanoid, cognitive developmental, neuro-, and collaborative robotics. Robots with artificial electronic skins are one of our specialties.

In our research, we employ the so-called synthetic methodology, or “understanding by building”, with two main goals:

  1. Understanding cognition and its development. In particular, we’re interested in the “body in the brain“: how do babies learn to represent their bodies and the space around it (peripersonal space) and what are the mechanisms in the brain. We build embodied computational models on humanoid robots to uncover how these representations operate.
  2. Robots safe and natural around humans. Taking inspiration from humans, we make robots exploit multimodal information (mostly vision and touch) to share space with humans. We’re interested in physical and social human-robot interaction.

For more details about our Research see the corresponding tab.

Our full affiliation is Vision for Robotics and Autonomous Systems, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague.

Humanoids group

Matej Hoffmann (Assistant Professor, coordinator)
Google Scholar profile
Tomas Svoboda (Associate Professor)
Google Scholar profile
Karla Stepanova (Postdoc)
Google Scholar profile
.
Zdenek Straka (PhD Student)
Google Scholar profile
Petr Svarny (PhD Student)
Google Scholar profile
Filipe Gama (PhD Student)
.
Shubhan Patni (PhD Student)

 

For our publications, please see the Google Scholar profiles of individual group members. For demos see our YouTube channel.
More information can also be found here.

Models of body representations

How do babies learn about their bodies? Newborns probably do not have a holistic perception of their body; instead they are starting to pick up correlations in the streams of individual sensory modalities (in particular visual, tactile, proprioceptive). The structure in these streams allows them to learn the first models of their bodies. The mechanisms behind these processes are largely unclear. In collaboration with developmental and cognitive psychologists, we want to shed more light on this topic by developing robotic models.

Safe physical human-robot interaction

Robots are leaving the factory, entering domains that are far less structured and starting to share living spaces with humans. As a consequence, they need to dynamically adapt to unpredictable interactions with people and guarantee safety at every moment. “Body awareness” acquired through artificial skin can be used not only to improve reactions to collisions, but when coupled with vision, it can be extended to a surface around the body (so-called peripersonal space), facilitating collision avoidance and contact anticipation, eventually leading to safer and more natural interaction of the robot with objects, including humans.

Automatic robot self-calibration

Standard robot calibration procedures require prior knowledge of a number of quantities from the robot’s environment. These conditions have to be present for recalibration to be performed. This has motivated alternative solutions to the self-calibration problem that are more “self-contained” and can be performed automatically by the robot. These typically rely on self-observation of specific points on the robot using the robot’s own camera(s). The advent of robotic skin technologies opens up the possibility of completely new approaches. In particular, the kinematic chain can be closed and the necessary redundant information obtained through self-touch, broadening the sample collection from end-effector to whole body surface. Furthermore, the possibility of truly multimodal calibration – using visual, proprioceptive, tactile, and inertial information – is open.

  • whatever…

IBM Great Minds

IBM, as every year, opens the prestigious Great Minds internships at IBM’s laboratories in Zürich, Johannesburg and Nairobi https://www.zurich.ibm.com/greatminds/ To apply and for more information about the cooperation, please contact Jan Louda (jan_louda@cz.ibm.com) Applications are accepted until March  4, 2019. Who interested in biomedical applications may apply for a recommendation to prof. Jan Kybic http://cmp.felk.cvut.cz/~kybic

Interview with prof. Chang-hee (Andy) Won, Ph.D.

From February to July 2019, prof. Chang-hee Won of Temple University in Pennsylvania, USA will be visiting CTU as a holder of the Fulbright-CTU Distinguished Chair fellowship. His professional interests include sensors and image processing and advanced control theory. His host will be prof. Jan Kybic from the Department of Cybernetics of the Faculty of …read more

Ing. Jiří Borovec defended his Ph.D. thesis

Ing. Jiří Borovec successfully defended his Ph.D. thesis entitled Analysis of microscopy images (supervisor: prof. Dr. Ing. Jan Kybic). Congratulations!

Miguel Amável dos Santos Pinheiro defended his Ph.D. thesis

Miguel Amável dos Santos Pinheiro successfully defended his Ph.D. thesis entitled Graph and Point Cloud Matching for Image Registration (supervisor: Prof. Jan Kybic). Congratulations!

Best paper award for Jiří Borovec and Jan Kybic

Paper “Binary pattern dictionary learning for gene expression representation in drosophila imaginal discs” by Jiří Borovec and Jan Kybic received Best Paper Award at MCBMIIA 2016. Congratulations!

Results of our BIA research group presented in Technicall magazine

The results of the Biomedical Imaging Algorithms (BIA) research group headed by doc. Jan Kybic are presented in Technicall magazine (1/2014). To learn more, see the articles (in Czech) called Počítač v roli patologa and Užitečný nástroj pro genetiky.

Juan David Garcia-Arteaga defended his Ph.D. thesis

Juan David Garcia-Arteaga successfully defended his Ph.D. thesis entitled Multichannel Image Information Similarity Measures: Applications to Colposcopy Image Registrations (supervisor: doc. Jan Kybic). Congratulations!
DP,BP,SP Analyza obrazu gelove elektroforezy Kybic Jan
DP,BP,SP Aplikace hlubokého učení pro detekci vícečetného myelomu v CT snímcích dlouhých kostí Hering Jan
DP,BP,SP Aplikace nelineárních parametrů pro hodnocení pohybových dat et. Ing. Jan Hejda, Ph.D. Ing.
DP,BP,SP Automatic analysis of gel electrophoresis data Kybic Jan
DP,BP,SP Automatic event recognition for CERN Sopczak Andre
DP,BP,SP Automatic nuchal translucency measurements Kybic Jan
BP,SP Automatická detekce cizích objektů z rentgenových snímků Kybic Jan
DP,BP,SP Cartilage and bone segmentation in ultrasound images of the knee Kybic Jan
DP,BP,SP Creation of 3D meshes for mechanical modeling from 3D medical data Kybic Jan
DP,BP,SP Deep learning for 3D drosophila egg segmentation Kybic Jan
DP,BP,SP Deep learning for automatic detection of multiple myeloma from CT images Kybic Jan
DP,BP,SP Deep learning for skin cancer classification Kybic Jan
DP,BP,SP Deep learning for tumor detection from histopathological images Kybic Jan
DP,BP,SP Deep learning for tumor type classification from histopathological images Kybic Jan
DP,BP,SP Digital histology microscopy image processing Kybic Jan
DP,BP,SP Efficient finding of nearest neighbors for binary vectors Kybic Jan
DP,BP,SP Elastická registrace obrazů za použití kritéria vzájemne informace ve vysoké dimenzi Kybic Jan
DP,BP,SP Fast sparse hierarchical B-spline interpolation Kybic Jan
DP,BP,SP Finding objects of known shapes from oversegmentation Kybic Jan
DP,BP,SP From pairwise image registration to sequence image registration Kybic Jan
DP,SP Functional MRI of hypercapnia data Kybic Jan
DP,SP Generování syntetických mikroskopických obrázků pomocí GAN Kybic Jan
BP,SP Hluboké učení pro klasifikaci histopatologických dat Hering Jan
DP,SP Kalibrace metody MRI "Arterial spin labeling" z M0 skenů s potlačením pozadí Jan Petr, Ph.D. mgr.
DP,BP,SP Learning multilayer classifiers with weak annotations Kybic Jan
DP,BP,SP Learning to segment from object counts Kybic Jan
DP,SP Lokalizace a segmentace karotidy z in-vivo ultrazvukových obrazů Kybic Jan
DP,BP,SP Lung nodule analysis from time series Kybic Jan
DP,BP,SP Magnetic particle imaging - using automatically calibrated test targets Kybic Jan
DP,BP,SP Markov chain Monte Carlo segmentation for fitting geometrical model Kybic Jan
DP,BP,SP Metody hodnocení pohybu při útocích ručními zbraněmi Ing. Patrik Kutílek, Ph.D. doc.
DP,BP,SP Odhadování dešťových srážek z dat mikrovlnných spojů Kybic Jan
DP,BP,SP Odhadování entropie pro vysocedimenzionální data s konečnou přesností Kybic Jan
DP,BP,SP Optimal MRI acquisition times for brain tissue segmentation from signal relaxation curve Petr Jan
DP,BP,SP Piecewise registration for histological slices Kybic Jan
DP,BP,SP Registration of ophthalmological sequences Kybic Jan
BP,SP Robustní a rychlá registrace obrazů metodou "Local All Pass" Kybic Jan
DP,BP,SP Rychlá registrace obrazů pomocí lineárního programování a řídkého vzorkování Kybic Jan
DP,SP Segmentace pediatrických mozků u pacientů s kraniosynostózou Jan Petr, Ph.D. Mgr.
DP,BP,SP Segmentation and joint-segmentation of aorta from histological and ultrasound images Kybic Jan
DP,BP,SP Softwarová aplikace pro přenos dat mezi cloudem a chytrým mobilním telefonem pro aplikace v home care et. Ing. Jan Hejda, Ph.D. Ing.
DP,BP,SP Softwarová aplikace pro real time analýzu fyziologických signálů využitím AI čipu Ing. Patrik Kutílek, Ph.D. doc.
DP,BP,SP Soutěže analýzy biomedicínských obrazů Kybic Jan
DP,BP,SP Surface registration for 3D breast images Kybic Jan
DP,BP,SP Thickness measurement from ultrasound RF images Kybic Jan
DP,BP,SP Ultrasound vessel wall texture classification Kybic Jan
DP,BP,SP Unsupervised joint segmentation of two images Kybic Jan
DP,BP,SP Určování duševního stavu mluvčího z hlasu et. Ing. Jan Hejda, Ph.D. Ing.
DP,BP,SP Určování lidských emocí z obrazu et. Ing. Jan Hejda, Ph.D. Ing.
DP,BP,SP Web based infrastructure for image processing and analysis Kybic Jan
Nenalezena žádná práce splňující Vaše kritéria.
Responsible person: Jan Kybic