Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Self-supervised pretraining for transferable quantitative phase image cell segmentation

T. Vicar, J. Chmelik, R. Jakubicek, L. Chmelikova, J. Gumulec, J. Balvan, I. Provaznik, R. Kolar

. 2021 ; 12 (10) : 6514-6528. [pub] 20210924

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc22001695

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.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22001695
003      
CZ-PrNML
005      
20250507102612.0
007      
ta
008      
220107s2021 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1364/BOE.433212 $2 doi
035    __
$a (PubMed)34745753
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Vicar, Tomas $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic $u Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Brno, Czech Republic
245    10
$a Self-supervised pretraining for transferable quantitative phase image cell segmentation / $c T. Vicar, J. Chmelik, R. Jakubicek, L. Chmelikova, J. Gumulec, J. Balvan, I. Provaznik, R. Kolar
520    9_
$a 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.
655    _2
$a časopisecké články $7 D016428
700    1_
$a Chmelík, Jiří $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic $7 xx0331819
700    1_
$a Jakubicek, Roman $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
700    1_
$a Chmelikova, Larisa $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
700    1_
$a Gumulec, Jaromir $u Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Brno, Czech Republic
700    1_
$a Balvan, Jan $u Department of Pathological Physiology, Faculty of Medicine, Masaryk University, Brno, Czech Republic
700    1_
$a Provaznik, Ivo $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
700    1_
$a Kolar, Radim $u Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic
773    0_
$w MED00189502 $t Biomedical optics express $x 2156-7085 $g Roč. 12, č. 10 (2021), s. 6514-6528
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34745753 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20220107 $b ABA008
991    __
$a 20250507102610 $b ABA008
999    __
$a ind $b bmc $g 1745577 $s 1152842
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2021 $b 12 $c 10 $d 6514-6528 $e 20210924 $i 2156-7085 $m Biomedical optics express $n Biomed Opt Express $x MED00189502
LZP    __
$a Pubmed-20220107

Najít záznam

Citační ukazatele

Možnosti archivace