Comparing Deep Learning Performance for Chronic Lymphocytic Leukaemia Cell Segmentation in Brightfield Microscopy Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00098892%3A_____%2F24%3A10158756" target="_blank" >RIV/00098892:_____/24:10158756 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989592:15110/24:73627307

Výsledek na webu

<a href="https://journals.sagepub.com/doi/10.1177/11779322241272387" target="_blank" >https://journals.sagepub.com/doi/10.1177/11779322241272387</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1177/11779322241272387" target="_blank" >10.1177/11779322241272387</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparing Deep Learning Performance for Chronic Lymphocytic Leukaemia Cell Segmentation in Brightfield Microscopy Images

Popis výsledku v původním jazyce

Objectives: This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions. Methods: We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes. Results: The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann–Whitney U test, P &lt; .0001). Conclusion: We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated.

Název v anglickém jazyce

Comparing Deep Learning Performance for Chronic Lymphocytic Leukaemia Cell Segmentation in Brightfield Microscopy Images

Popis výsledku anglicky

Objectives: This article focuses on the detection of cells in low-contrast brightfield microscopy images; in our case, it is chronic lymphocytic leukaemia cells. The automatic detection of cells from brightfield time-lapse microscopic images brings new opportunities in cell morphology and migration studies; to achieve the desired results, it is advisable to use state-of-the-art image segmentation methods that not only detect the cell but also detect its boundaries with the highest possible accuracy, thus defining its shape and dimensions. Methods: We compared eight state-of-the-art neural network architectures with different backbone encoders for image data segmentation, namely U-net, U-net++, the Pyramid Attention Network, the Multi-Attention Network, LinkNet, the Feature Pyramid Network, DeepLabV3, and DeepLabV3+. The training process involved training each of these networks for 1000 epochs using the PyTorch and PyTorch Lightning libraries. For instance segmentation, the watershed algorithm and three-class image semantic segmentation were used. We also used StarDist, a deep learning-based tool for object detection with star-convex shapes. Results: The optimal combination for semantic segmentation was the U-net++ architecture with a ResNeSt-269 background with a data set intersection over a union score of 0.8902. For the cell characteristics examined (area, circularity, solidity, perimeter, radius, and shape index), the difference in mean value using different chronic lymphocytic leukaemia cell segmentation approaches appeared to be statistically significant (Mann–Whitney U test, P &lt; .0001). Conclusion: We found that overall, the algorithms demonstrate equal agreement with ground truth, but with the comparison, it can be seen that the different approaches prefer different morphological features of the cells. Consequently, choosing the most suitable method for instance-based cell segmentation depends on the particular application, namely, the specific cellular traits being investigated.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10609 - Biochemical research methods

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Bioinformatics and Biology Insights

ISSN

1177-9322

e-ISSN

1177-9322

Svazek periodika

18

Číslo periodika v rámci svazku

2024

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

14

Strana od-do

11779322241272387

Kód UT WoS článku

001307771800001

EID výsledku v databázi Scopus

2-s2.0-85203140912