Classification of Cells Infected by Malaria with Vision Transformers Models
DOI:
https://doi.org/10.22456/2175-2745.143548Keywords:
Vision Transformer, Malaria Classification, Cellular Tissue Microscopy, vit-pytorchAbstract
This project develops a system for malaria classification using the Vision Transformer architecture on cellular tissue microscopy images. The implementation aims to assist in medical diagnosis by providing efficient and accurate information, with the potential to contribute to the control of endemic diseases. The system utilizes models from the vit-pytorch library, including the Vision Transformer, Patch Merger, and Vision Transformer for Small Datasets. The Vision Transformer for Small Datasets achieved the highest accuracy of 98.97 for an image size of [150,150].
Downloads
References
World Health Organization, “World Malaria Report 2021,” Geneva, Switzerland: WHO, 2021.
N. J. White and J. G. Breman, “Malaria Parasites,” in Encyclopedia of Malaria, J. G. Breman, M. S. Alilio, and N. J. White, Eds. Springer, 2013.
M. Amexo, R. Tolhurst, G. Barnish, and I. Bates, “Malaria misdiagnosis: effects on the poor and vulnerable,” The Lancet, vol. 364, no. 9448, pp. 1896–1898, 2004.
A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” arXiv preprint arXiv:2010.11929, 2020.
I. R. Dave, “Image analysis for malaria parasite detection from microscopic images of thick blood smear,” in Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India, Mar. 22–24, 2017.
M. M. H. Sifat and M. M. Islam, “A Fully Automated System to Detect Malaria Parasites and their Stages from the Blood Smear,” in Proceedings of the 2020 IEEE Region 10 Symposium (TENSYMP), Dhaka, Bangladesh, Jun. 5–7, 2020.
A. Maqsood, M. S. Farid, M. H. Khan, and M. Grzegorzek, “Deep malaria parasite detection in thin blood smear microscopic images,” Applied Sciences, vol. 11, no. 5, p. 2284, 2021. [Online]. Available: ⟨https://www.mdpi.com/2076-3417/11/5/2284⟩.
S. D. Gummadi, A. Ghosh, and Y. Vootla, “Transfer Learning based Classification of Plasmodium Falciparum Parasitic Blood Smear Images,” in Proceedings of the 2022 10th International Symposium on Digital Forensics and Security (ISDFS), Istanbul, Turkey, Jun. 6–7, 2022.
W. R. W. M. Razin, T. S. Gunawan, M. Kartiwi, and N. M. Yusoff, “Malaria Parasite Detection and Classification using CNN and YOLOv5 Architectures,” in Proceedings of the 2022 IEEE 8th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), Melaka, Malaysia, Sep. 26–28, 2022.
Centro Nacional de Informação sobre Biotecnologia (s.d.). Dataset de imagens de malária. Recuperado de ⟨https://lhncbc.nlm.nih.gov/LHC-research/LHC-projects/image-processing/malaria-datasheet.html⟩.
PYTORCH. ReduceLROnPlateau. Disponível em: ⟨https://pytorch.org/docs/stable/generated/torch.optim.lr_scheduler.ReduceLROnPlateau.html⟩. Acesso em: 23 jul. 2024.
PYTORCH. EarlyStopping. Disponível em: ⟨https://pytorch.org/docs/stable/generated/torch.nn.EarlyStopping.html⟩. Acesso em: 23 jul. 2024.
J. Wang, W. Wang, X. Yang, and W. Zhang, “Attention-based Temporal Context Aggregation for Video Action Recognition,” arXiv preprint arXiv:2202.12015, 2022. [Online]. Available: ⟨https://arxiv.org/abs/2202.12015⟩.
X. Zhang, Y. Zhang, Z. Zhang, and Y. Liu, “Dual Encoder Network for Zero-Shot Video Retrieval,” arXiv preprint arXiv:2112.13492, 2021. [Online]. Available: ⟨https://arxiv.org/abs/2112.13492⟩.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Iago Fonseca Marinho Pereira, Eduardo David Campopiano, Thomas William, Cides Bezerra, Guilherme Ribeiro Sales, Valentino Corso, Douglas Henrique Siqueira Abreu
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autorizo aos editores a publicação de meu artigo, caso seja aceito, em meio eletrônico de acordo com as regras do Public Knowledge Project.Accepted 2024-12-02
Published 2025-02-20
