Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning
- Author
- Taewoo Jung, Esla Timothy Anzaku (UGent) , Utku Özbulak, Stefan Magez (UGent) , Arnout Van Messem (UGent) and Wesley De Neve (UGent)
- Organization
- Abstract
- Trypanosomosis, which is caused by the Trypanosoma parasite, is an infectious disease that affects both humans and animals. Today, the microscopic examination of a Giemsa or Wright stained blood smear from an infected individual is the standard procedure for diagnosis because of the straightforward nature of sample preparation. Unfortunately, this method is labor-intensive and prone to error, particularly resulting in false-negative scoring when parasite levels are low during chronic infections. Automating the detection of parasites in blood smear images can overcome sensitivity limitations related to a microscopic examination. We therefore propose a deep learning approach that aims at automatically classifying microscope images in terms of parasite presence or absence. To that end, we applied a ResNet18 model using a pre-processed dataset derived from microscope videos of unstained thick blood smears, with the blood smears originating from a mouse infected with Trypanosoma brucei. Our pre-processing strategy mainly involved image cropping and the application of a thresholding algorithm for facilitating effective model training. Moreover, our thresholding approach made it possible to observe a positive correlation between the percentage of parasite-related pixels in an image and the classification effectiveness.
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 2.73 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8696749
- MLA
- Jung, Taewoo, et al. “Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-Processing and Deep Learning.” Intelligent Human Computer Interaction 12th International Conference, IHCI 2020, vol. 12616, Springer, 2021, pp. 254–66, doi:10.1007/978-3-030-68452-5_27.
- APA
- Jung, T., Anzaku, E. T., Özbulak, U., Magez, S., Van Messem, A., & De Neve, W. (2021). Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning. Intelligent Human Computer Interaction 12th International Conference, IHCI 2020, 12616, 254–266. https://doi.org/10.1007/978-3-030-68452-5_27
- Chicago author-date
- Jung, Taewoo, Esla Timothy Anzaku, Utku Özbulak, Stefan Magez, Arnout Van Messem, and Wesley De Neve. 2021. “Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-Processing and Deep Learning.” In Intelligent Human Computer Interaction 12th International Conference, IHCI 2020, 12616:254–66. Cham: Springer. https://doi.org/10.1007/978-3-030-68452-5_27.
- Chicago author-date (all authors)
- Jung, Taewoo, Esla Timothy Anzaku, Utku Özbulak, Stefan Magez, Arnout Van Messem, and Wesley De Neve. 2021. “Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-Processing and Deep Learning.” In Intelligent Human Computer Interaction 12th International Conference, IHCI 2020, 12616:254–266. Cham: Springer. doi:10.1007/978-3-030-68452-5_27.
- Vancouver
- 1.Jung T, Anzaku ET, Özbulak U, Magez S, Van Messem A, De Neve W. Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning. In: Intelligent Human Computer Interaction 12th International Conference, IHCI 2020. Cham: Springer; 2021. p. 254–66.
- IEEE
- [1]T. Jung, E. T. Anzaku, U. Özbulak, S. Magez, A. Van Messem, and W. De Neve, “Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning,” in Intelligent Human Computer Interaction 12th International Conference, IHCI 2020, South Korea, 2021, vol. 12616, pp. 254–266.
@inproceedings{8696749,
abstract = {{Trypanosomosis, which is caused by the Trypanosoma parasite, is an infectious disease that affects both humans and animals. Today, the microscopic examination of a Giemsa or Wright stained blood smear from an infected individual is the standard procedure for diagnosis because of the straightforward nature of sample preparation. Unfortunately, this method is labor-intensive and prone to error, particularly resulting in false-negative scoring when parasite levels are low during chronic infections. Automating the detection of parasites in blood smear images can overcome sensitivity limitations related to a microscopic examination. We therefore propose a deep learning approach that aims at automatically classifying microscope images in terms of parasite presence or absence. To that end, we applied a ResNet18 model using a pre-processed dataset derived from microscope videos of unstained thick blood smears, with the blood smears originating from a mouse infected with Trypanosoma brucei. Our pre-processing strategy mainly involved image cropping and the application of a thresholding algorithm for facilitating effective model training. Moreover, our thresholding approach made it possible to observe a positive correlation between the percentage of parasite-related pixels in an image and the classification effectiveness.}},
author = {{Jung, Taewoo and Anzaku, Esla Timothy and Özbulak, Utku and Magez, Stefan and Van Messem, Arnout and De Neve, Wesley}},
booktitle = {{Intelligent Human Computer Interaction 12th International Conference, IHCI 2020}},
isbn = {{9783030684518}},
issn = {{0302-9743}},
language = {{eng}},
location = {{South Korea}},
pages = {{254--266}},
publisher = {{Springer}},
title = {{Automatic detection of Trypanosomosis in thick blood smears using image pre-processing and deep learning}},
url = {{http://doi.org/10.1007/978-3-030-68452-5_27}},
volume = {{12616}},
year = {{2021}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: