TY  - JOUR
AU  - Ćirković-Veličković, Tanja
AU  - Park, Ho-Min
AU  - de Guzman, Maria Krishna
AU  - de Neve, Wesley
AU  - Van Messem, Arnout
AU  - Baek, Ji Yeon
AU  - Park, Sanghyeon
PY  - 2022
UR  - http://cherry.chem.bg.ac.rs/handle/123456789/5733
AB  - Environmental monitoring of microplastics (MP) contamination has become an area of great research interest, given potential hazards associated with human ingestion of MP. In this context, determination of MP concentration is essential. However, cheap, rapid, and accurate quantification of MP remains a challenge to this date. This study proposes a deep learning-based image segmentation method that properly distinguishes fluorescent MP from other elements in a given microscopy image. A total of nine different deep learning models, six of which are based on U-Net, were investigated. These models were trained using at least 20,000 patches sampled from 99 fluorescence microscopy images of MP and their corresponding binary masks. MP-Net, which is derived from U-Net, was found to be the best performing model, exhibiting the highest mean F1-score (0.736) and mean IoU value (0.617). Test-time augmentation (using brightness, contrast, and HSV) was applied to MP-Net for robust learning. However, compared to the results obtained without augmentation, no clear improvement in predictive performance could be observed. Recovery assessment for both spiked and real images showed that, compared to already existing tools for MP quantification, the MP quantities predicted by MP-Net are those closest to the ground truth. This observation suggests that MP-Net allows creating masks that more accurately reflect the quantitative presence of fluorescent MP in microscopy images. Finally, MAP (Microplastics Annotation Package) is introduced, an integrated software environment for automated MP quantification, offering support for MP-Net, already existing MP analysis tools like MP-VAT, manual annotation, and model fine-tuning.
PB  - Public Library of Science
T2  - PLoS ONE
T1  - MP-Net: Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams
VL  - 17
IS  - 6
SP  - e0269449
DO  - 10.1371/journal.pone.0269449
ER  - 

@article{
author = "Ćirković-Veličković, Tanja and Park, Ho-Min and de Guzman, Maria Krishna and de Neve, Wesley and Van Messem, Arnout and Baek, Ji Yeon and Park, Sanghyeon",
year = "2022",
abstract = "Environmental monitoring of microplastics (MP) contamination has become an area of great research interest, given potential hazards associated with human ingestion of MP. In this context, determination of MP concentration is essential. However, cheap, rapid, and accurate quantification of MP remains a challenge to this date. This study proposes a deep learning-based image segmentation method that properly distinguishes fluorescent MP from other elements in a given microscopy image. A total of nine different deep learning models, six of which are based on U-Net, were investigated. These models were trained using at least 20,000 patches sampled from 99 fluorescence microscopy images of MP and their corresponding binary masks. MP-Net, which is derived from U-Net, was found to be the best performing model, exhibiting the highest mean F1-score (0.736) and mean IoU value (0.617). Test-time augmentation (using brightness, contrast, and HSV) was applied to MP-Net for robust learning. However, compared to the results obtained without augmentation, no clear improvement in predictive performance could be observed. Recovery assessment for both spiked and real images showed that, compared to already existing tools for MP quantification, the MP quantities predicted by MP-Net are those closest to the ground truth. This observation suggests that MP-Net allows creating masks that more accurately reflect the quantitative presence of fluorescent MP in microscopy images. Finally, MAP (Microplastics Annotation Package) is introduced, an integrated software environment for automated MP quantification, offering support for MP-Net, already existing MP analysis tools like MP-VAT, manual annotation, and model fine-tuning.",
publisher = "Public Library of Science",
journal = "PLoS ONE",
title = "MP-Net: Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams",
volume = "17",
number = "6",
pages = "e0269449",
doi = "10.1371/journal.pone.0269449"
}

Ćirković-Veličković, T., Park, H., de Guzman, M. K., de Neve, W., Van Messem, A., Baek, J. Y.,& Park, S.. (2022). MP-Net: Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams. in PLoS ONE
Public Library of Science., 17(6), e0269449.
https://doi.org/10.1371/journal.pone.0269449

Ćirković-Veličković T, Park H, de Guzman MK, de Neve W, Van Messem A, Baek JY, Park S. MP-Net: Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams. in PLoS ONE. 2022;17(6):e0269449.
doi:10.1371/journal.pone.0269449 .

Ćirković-Veličković, Tanja, Park, Ho-Min, de Guzman, Maria Krishna, de Neve, Wesley, Van Messem, Arnout, Baek, Ji Yeon, Park, Sanghyeon, "MP-Net: Deep learning-based segmentation for fluorescence microscopy images of microplastics isolated from clams" in PLoS ONE, 17, no. 6 (2022):e0269449,
https://doi.org/10.1371/journal.pone.0269449 . .