Details
| Original language | English |
|---|---|
| Title of host publication | 8th European Medical and Biological Engineering Conference |
| Subtitle of host publication | Proceedings of the EMBEC 2020 |
| Editors | Tomaz Jarm, Aleksandra Cvetkoska, Samo Mahnič-Kalamiza, Damijan Miklavcic |
| Publisher | Springer Science and Business Media Deutschland GmbH |
| Pages | 102-111 |
| Number of pages | 10 |
| ISBN (electronic) | 978-3-030-64610-3 |
| ISBN (print) | 9783030646097 |
| Publication status | Published - 30 Nov 2020 |
| Event | 8th European Medical and Biological Engineering Conference, EMBEC 2020 - Portorož, Slovenia Duration: 29 Nov 2020 → 3 Dec 2020 |
Publication series
| Name | IFMBE Proceedings |
|---|---|
| Volume | 80 |
| ISSN (Print) | 1680-0737 |
| ISSN (electronic) | 1433-9277 |
Abstract
Cryomicroscopy is one of the main techniques to visualize freezing and thawing events taking place during cryopreservation of cells, native and artificial tissues with the ultimate goal to provide cell- and tissue-specific cryogenic preservation. However, there is currently no unified software tool for the automated analysis of ice recrystallization kinetics for a variety of cryoprotective agents used in the cryobiological practice. In this regard, we focused on the particular aspect of image analysis in the course of ice recrystallization, i.e. the possibility of using a neural network for the segmentation of ice crystals during isothermal annealing. In the work, the U-Net deep neural network was used for segmentation of ice crystals on cryomicroscopic images. Using 100 images as training set, the resulting accuracy of ice crystal segmentation was about 74% on the test sample (30 images). The obtained results show the possibility of segmentation of ice crystals in cryomicroscopic images taking into account the overlapping of intensity levels of an object and background. Further improvement of the model through the use of an additional training data as well as augmentation techniques is required to more efficiently validate this approach.
Keywords
- Artificial neural network, Cryomicroscopy, Cryopreservation, Ice recrystallization, Image processing, Segmentation, U-Net
ASJC Scopus subject areas
- Chemical Engineering(all)
- Bioengineering
- Engineering(all)
- Biomedical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
8th European Medical and Biological Engineering Conference: Proceedings of the EMBEC 2020. ed. / Tomaz Jarm; Aleksandra Cvetkoska; Samo Mahnič-Kalamiza; Damijan Miklavcic. Springer Science and Business Media Deutschland GmbH, 2020. p. 102-111 (IFMBE Proceedings; Vol. 80).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Application of Artificial Neural Networks for Analysis of Ice Recrystallization Process for Cryopreservation
AU - Tymkovych, Maksym
AU - Gryshkov, Oleksandr
AU - Selivanova, Karina
AU - Mutsenko, Vitalii
AU - Avrunin, Oleg
AU - Glasmacher, Birgit
N1 - Funding Information: Acknowledgments. The authors would like to thank the exchange program with East European Countries funded by the German Academic Exchange Service (DAAD, project number 54364768) and the joint German-Ukrainian Grant funded by Federal Ministry of Education and Research of Germany (BMBF, 01DK20017) and Ministry of Education and Science of Ukraine (project ID 100445538).
PY - 2020/11/30
Y1 - 2020/11/30
N2 - Cryomicroscopy is one of the main techniques to visualize freezing and thawing events taking place during cryopreservation of cells, native and artificial tissues with the ultimate goal to provide cell- and tissue-specific cryogenic preservation. However, there is currently no unified software tool for the automated analysis of ice recrystallization kinetics for a variety of cryoprotective agents used in the cryobiological practice. In this regard, we focused on the particular aspect of image analysis in the course of ice recrystallization, i.e. the possibility of using a neural network for the segmentation of ice crystals during isothermal annealing. In the work, the U-Net deep neural network was used for segmentation of ice crystals on cryomicroscopic images. Using 100 images as training set, the resulting accuracy of ice crystal segmentation was about 74% on the test sample (30 images). The obtained results show the possibility of segmentation of ice crystals in cryomicroscopic images taking into account the overlapping of intensity levels of an object and background. Further improvement of the model through the use of an additional training data as well as augmentation techniques is required to more efficiently validate this approach.
AB - Cryomicroscopy is one of the main techniques to visualize freezing and thawing events taking place during cryopreservation of cells, native and artificial tissues with the ultimate goal to provide cell- and tissue-specific cryogenic preservation. However, there is currently no unified software tool for the automated analysis of ice recrystallization kinetics for a variety of cryoprotective agents used in the cryobiological practice. In this regard, we focused on the particular aspect of image analysis in the course of ice recrystallization, i.e. the possibility of using a neural network for the segmentation of ice crystals during isothermal annealing. In the work, the U-Net deep neural network was used for segmentation of ice crystals on cryomicroscopic images. Using 100 images as training set, the resulting accuracy of ice crystal segmentation was about 74% on the test sample (30 images). The obtained results show the possibility of segmentation of ice crystals in cryomicroscopic images taking into account the overlapping of intensity levels of an object and background. Further improvement of the model through the use of an additional training data as well as augmentation techniques is required to more efficiently validate this approach.
KW - Artificial neural network
KW - Cryomicroscopy
KW - Cryopreservation
KW - Ice recrystallization
KW - Image processing
KW - Segmentation
KW - U-Net
UR - http://www.scopus.com/inward/record.url?scp=85097625206&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-64610-3_13
DO - 10.1007/978-3-030-64610-3_13
M3 - Conference contribution
AN - SCOPUS:85097625206
SN - 9783030646097
T3 - IFMBE Proceedings
SP - 102
EP - 111
BT - 8th European Medical and Biological Engineering Conference
A2 - Jarm, Tomaz
A2 - Cvetkoska, Aleksandra
A2 - Mahnič-Kalamiza, Samo
A2 - Miklavcic, Damijan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th European Medical and Biological Engineering Conference, EMBEC 2020
Y2 - 29 November 2020 through 3 December 2020
ER -