Details
| Original language | English |
|---|---|
| Pages (from-to) | 123–126 |
| Number of pages | 4 |
| Journal | Current Directions in Biomedical Engineering |
| Volume | 10 |
| Issue number | 4 |
| Publication status | Published - 19 Dec 2024 |
Abstract
Core-shell capsules (CSC) are a promising approach for 3D cell culture because they overcome the challenges of traditional large-scale cell cultivation techniques used in tissue engineering. Currently, CSC are segmented from microscopic images in a cumbersome manual procedure to evaluate their properties, such as size or complete encapsulation of the core compartment. In this paper, we propose an automated segmentation process of CSC based on an unmodified YOLOv8 instance segmentation model. We train the model exclusively on synthetic CSC images created from 10 manually annotated real images and evaluate its performance using the common Intersection over Union (IoU) metric on a test set consisting of 181 real images. Without modifying the model or tuning the hyperparameters, we achieve a mean IoU of 0.86, underlining the potential of deep-learning-based CSC segmentation relying entirely on synthetic training data.
Keywords
- Cell Segmentation, Synthetic Data, YOLOv8
ASJC Scopus subject areas
- Engineering(all)
- Biomedical Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Current Directions in Biomedical Engineering, Vol. 10, No. 4, 19.12.2024, p. 123–126.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Core-Shell Capsule Image Segmentation through Deep Learning with Synthetic Training Data
AU - Budde, Leon
AU - Dreger, Julia
AU - Egger, Dominik
AU - Seel, Thomas
N1 - Publisher Copyright: © 2024 by Walter de Gruyter Berlin/Boston.
PY - 2024/12/19
Y1 - 2024/12/19
N2 - Core-shell capsules (CSC) are a promising approach for 3D cell culture because they overcome the challenges of traditional large-scale cell cultivation techniques used in tissue engineering. Currently, CSC are segmented from microscopic images in a cumbersome manual procedure to evaluate their properties, such as size or complete encapsulation of the core compartment. In this paper, we propose an automated segmentation process of CSC based on an unmodified YOLOv8 instance segmentation model. We train the model exclusively on synthetic CSC images created from 10 manually annotated real images and evaluate its performance using the common Intersection over Union (IoU) metric on a test set consisting of 181 real images. Without modifying the model or tuning the hyperparameters, we achieve a mean IoU of 0.86, underlining the potential of deep-learning-based CSC segmentation relying entirely on synthetic training data.
AB - Core-shell capsules (CSC) are a promising approach for 3D cell culture because they overcome the challenges of traditional large-scale cell cultivation techniques used in tissue engineering. Currently, CSC are segmented from microscopic images in a cumbersome manual procedure to evaluate their properties, such as size or complete encapsulation of the core compartment. In this paper, we propose an automated segmentation process of CSC based on an unmodified YOLOv8 instance segmentation model. We train the model exclusively on synthetic CSC images created from 10 manually annotated real images and evaluate its performance using the common Intersection over Union (IoU) metric on a test set consisting of 181 real images. Without modifying the model or tuning the hyperparameters, we achieve a mean IoU of 0.86, underlining the potential of deep-learning-based CSC segmentation relying entirely on synthetic training data.
KW - Cell Segmentation
KW - Synthetic Data
KW - YOLOv8
UR - http://www.scopus.com/inward/record.url?scp=85218096235&partnerID=8YFLogxK
U2 - 10.1515/cdbme-2024-2030
DO - 10.1515/cdbme-2024-2030
M3 - Article
VL - 10
SP - 123
EP - 126
JO - Current Directions in Biomedical Engineering
JF - Current Directions in Biomedical Engineering
IS - 4
ER -