Segmentation of weakly visible environmental microorganism images using pair-wise deep learning features

Frank Kulwa; Chen Li; Marcin Grzegorzek; Md Mamunur Rahaman; Kimiaki Shirahama; Sergey Kosov

doi:10.1016/j.bspc.2022.104168

Segmentation of weakly visible environmental microorganism images using pair-wise deep learning features

Frank Kulwa, Chen Li^*, Marcin Grzegorzek, Md Mamunur Rahaman, Kimiaki Shirahama, Sergey Kosov

^*Corresponding author for this work

13 Citations (Scopus)

Abstract

The use of Environmental Microorganisms (EMs) offers a highly efficient, low cost and harmless remedy to environmental pollution, by monitoring and decomposing of pollutants. This relies on how the EMs are correctly segmented and identified. With the aim of enhancing the segmentation of weakly visible EM images which are transparent, noisy and have low contrast, a Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. Leveraging the Shi and Tomas descriptors, we extract each image's deep features on the patches, which are centred at each descriptor using the VGG-16 model. Then, to learn the intermediate characteristics between the descriptors, pairing of the features is performed based on the Delaunay triangulation theorem to form pairwise deep learning features. In this experiment, the PDLF-Net achieves outstanding segmentation results of 89.24%, 63.20%, 77.27%, 35.15%, 89.72%, 91.44% and 89.30% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.

Original language	English
Article number	104168
Journal	Biomedical Signal Processing and Control
Volume	79
Pages (from-to)	104168
Number of pages	1
ISSN	1746-8094
DOIs	https://doi.org/10.1016/j.bspc.2022.104168
Publication status	Published - 01.2023

Funding

We thank Prof. B. Zhou, Dr. F. Ma (University of Science and Technology Beijing, China), Prof. Y. Zou (Freiburg University, Germany), B.E. X. Zhu (Johns Hopkins University, US) and B.E. B. Lu (Huazhong University of Science and Technology, China) for their previous cooperations in this work. We also thank Miss Z. Li and Mr. G. Li, for their important discussion. This work is supported by “ National Natural Science Foundation of China ” (No. 61806047 ). We thank Prof. B. Zhou, Dr. F. Ma (University of Science and Technology Beijing, China), Prof. Y. Zou (Freiburg University, Germany), B.E. X. Zhu (Johns Hopkins University, US) and B.E. B. Lu (Huazhong University of Science and Technology, China) for their previous cooperations in this work. We also thank Miss Z. Li and Mr. G. Li, for their important discussion. This work is supported by “National Natural Science Foundation of China ” (No. 61806047).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Centers: Center for Artificial Intelligence Luebeck (ZKIL)

Access to Document

10.1016/j.bspc.2022.104168

Cite this

@article{b3314247013349219e29a62a79decef7,

title = "Segmentation of weakly visible environmental microorganism images using pair-wise deep learning features",

abstract = "The use of Environmental Microorganisms (EMs) offers a highly efficient, low cost and harmless remedy to environmental pollution, by monitoring and decomposing of pollutants. This relies on how the EMs are correctly segmented and identified. With the aim of enhancing the segmentation of weakly visible EM images which are transparent, noisy and have low contrast, a Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. Leveraging the Shi and Tomas descriptors, we extract each image's deep features on the patches, which are centred at each descriptor using the VGG-16 model. Then, to learn the intermediate characteristics between the descriptors, pairing of the features is performed based on the Delaunay triangulation theorem to form pairwise deep learning features. In this experiment, the PDLF-Net achieves outstanding segmentation results of 89.24\%, 63.20\%, 77.27\%, 35.15\%, 89.72\%, 91.44\% and 89.30\% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.",

author = "Frank Kulwa and Chen Li and Marcin Grzegorzek and Rahaman, \{Md Mamunur\} and Kimiaki Shirahama and Sergey Kosov",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier Ltd",

year = "2023",

month = jan,

doi = "10.1016/j.bspc.2022.104168",

language = "English",

volume = "79",

pages = "104168",

journal = "Biomedical Signal Processing and Control",

issn = "1746-8094",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Segmentation of weakly visible environmental microorganism images using pair-wise deep learning features

AU - Kulwa, Frank

AU - Li, Chen

AU - Grzegorzek, Marcin

AU - Rahaman, Md Mamunur

AU - Shirahama, Kimiaki

AU - Kosov, Sergey

PY - 2023/1

Y1 - 2023/1

N2 - The use of Environmental Microorganisms (EMs) offers a highly efficient, low cost and harmless remedy to environmental pollution, by monitoring and decomposing of pollutants. This relies on how the EMs are correctly segmented and identified. With the aim of enhancing the segmentation of weakly visible EM images which are transparent, noisy and have low contrast, a Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. Leveraging the Shi and Tomas descriptors, we extract each image's deep features on the patches, which are centred at each descriptor using the VGG-16 model. Then, to learn the intermediate characteristics between the descriptors, pairing of the features is performed based on the Delaunay triangulation theorem to form pairwise deep learning features. In this experiment, the PDLF-Net achieves outstanding segmentation results of 89.24%, 63.20%, 77.27%, 35.15%, 89.72%, 91.44% and 89.30% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.

AB - The use of Environmental Microorganisms (EMs) offers a highly efficient, low cost and harmless remedy to environmental pollution, by monitoring and decomposing of pollutants. This relies on how the EMs are correctly segmented and identified. With the aim of enhancing the segmentation of weakly visible EM images which are transparent, noisy and have low contrast, a Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. Leveraging the Shi and Tomas descriptors, we extract each image's deep features on the patches, which are centred at each descriptor using the VGG-16 model. Then, to learn the intermediate characteristics between the descriptors, pairing of the features is performed based on the Delaunay triangulation theorem to form pairwise deep learning features. In this experiment, the PDLF-Net achieves outstanding segmentation results of 89.24%, 63.20%, 77.27%, 35.15%, 89.72%, 91.44% and 89.30% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.

UR - https://www.scopus.com/pages/publications/85138124000

UR - https://www.mendeley.com/catalogue/262c1054-f590-32dc-8415-442e2d446aba/

U2 - 10.1016/j.bspc.2022.104168

DO - 10.1016/j.bspc.2022.104168

M3 - Journal articles

AN - SCOPUS:85138124000

SN - 1746-8094

VL - 79

SP - 104168

JO - Biomedical Signal Processing and Control

JF - Biomedical Signal Processing and Control

M1 - 104168

ER -

Segmentation of weakly visible environmental microorganism images using pair-wise deep learning features

Abstract

Funding

UN SDGs

Research Areas and Centers

Access to Document

Other files and links

Fingerprint

Cite this