Jiri Chmelik

Mr. Jiri Chmelik

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2018 in Medical Image Analysis
Verified
Journal Article
Closed access
JCJiri Chmelik
Jiri Chmelik
RJRoman Jakubicek
Roman Jakubicek
PWPetr Walek
Petr Walek
JJJiri Jan
Jiri Jan
POPetr Ourednicek
Petr Ourednicek
GGGiampaolo Gavelli
Giampaolo Gavelli

1 January 2020 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
RJRoman Jakubicek
Roman Jakubicek
JCJiri Chmelik
Jiri Chmelik
JJJiri Jan
Jiri Jan
POPetr Ourednicek
Petr Ourednicek
LLLukas Lambert
Lukas Lambert
GGGiampaolo Gavelli
Giampaolo Gavelli

6 May 2016 in Journal of Materials Science: Materials in Medicine
Verified
Journal Article
Closed access
PDF file
JZJan Zidek
Jan Zidek
Lucy VojtovaLucy Vojtova
Lucy Vojtova
Abdelmohsen AbdellatifAbdelmohsen Abdellatif
Abdelmohsen Abdellatif
JCJiri Chmelik
Jiri Chmelik
TZTomas Zikmund
Tomas Zikmund
Jozef KaiserJozef Kaiser
Jozef Kaiser

4 April 2022 in Biophysical Journal
Verified
Journal Article
Closed access
TVTomáš Vičar
Tomáš Vičar
JCJiri Chmelik
Jiri Chmelik
JNJiri Navratil
Jiri Navratil
RKRadim Kolář
Radim Kolář
LCLarisa Chmelikova
Larisa Chmelikova
JGJaromir Gumulec
Jaromir Gumulec

24 September 2021 in Biomedical Optics Express
Verified
Journal Article
Closed access
TVTomáš Vičar
Tomáš Vičar
JCJiri Chmelik
Jiri Chmelik
RJRoman Jakubicek
Roman Jakubicek
LCLarisa Chmelikova
Larisa Chmelikova
JGJaromir Gumulec
Jaromir Gumulec
RKRadim Kolář
Radim Kolář
In this paper, a novel U-Net-based method for robust adherent cell segmentation for quantitative phase microscopy image is designed and optimised. We designed and evaluated four specific post-processing pipelines. To increase the transferability to different cell types, non-deep learning transfer with adjustable parameters is used in the post-processing step. Additionally, we proposed a self-supervised pretraining technique using nonlabelled data, which is trained to reconstruct multiple image distortions and improved the segmentation performance from 0.67 to 0.70 of object-wise intersection over union. Moreover, we publish a new dataset of manually labelled images suitable for this task together with the unlabelled data for self-supervised pretraining.

1 July 2019
Verified
Conference Paper
Closed access
RJRoman Jakubicek
Roman Jakubicek
JCJiri Chmelik
Jiri Chmelik
POPetr Ourednicek
Petr Ourednicek
JJJiri Jan
Jiri Jan
In this contribution, we present a fully automatic approach, that is based on two convolution neural networks (CNN) together with a spine tracing algorithm utilizing a population optimization algorithm. Based on the evaluation of 130 CT scans including heavily distorted and complicated cases, it turned out that this new combination enables fast and robust detection with almost 90% of correctly determined spinal centerlines with computing time of fewer than 20 seconds.