Classification and Karyotyping of Human Chromosome Images with Convolutional Neural Networks and Ensemble Learning

• Francisco das C. Imperes Filho Federal University of Piauí (UFPI)
• Vinicius P. Machado Federal University of Piauí (UFPI)
• Arlino Magalhães Federal University of Piauí (UFPI)
• Rodrigo de M. S. Veras Federal University of Piauí (UFPI)

DOI: https://doi.org/10.5753/sbbd_estendido.2025.247654

Abstract

Chromosome classification constitutes an essential undertaking in the identification of genetic anomalies, a task conventionally executed by geneticists via manual karyotype analysis. This study puts forth an approach to leverage pre-trained Convolutional Neural Networks for the development of a model. This model utilizes images featuring overlapping chromosomes to simulate clinical scenarios and is designed to execute the classification of chromosomes into their respective karyotype classes derived from microscopic imagery. The ultimate objective is the development of a system capable of the automated identification, classification, and assembly of karyotypes from complex images, concurrently investigating the potential of Ensemble Learning and interpretability tools, such as Saliency Maps.

Keywords: Chromosome Classification, Convolutional Neural Networks, Ensemble Learning, Biomedical Data Analysis

References

Anh, L., Thanh, V., Son, N., Phuong, D. K., Anh, L., Ram, T., Minh, B., Tung, H., Thinh, N., Ha, V., and Ha, M. (2022). Efficient type and polarity classification of chromosome images using cnns: a primary evaluation on multiple datasets. In 2022 IEEE Ninth International Conference on Communications and Electronics (ICCE), pages 400–405.

Imperes, F. D. C. F., Machado, V. P., do Monte, S. J. H., dos Santos, A. R., de Sousa, L. P., da Silva, A. S., Pereira, E. M., and Veras, R. M. S. (2024). Explorando arquiteturas de redes neurais profundas na classificação de imagens de cariótipos humanos. Anais do XXIV Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS 2024).

Lin, C., Chen, H., Huang, J., Peng, J., Guo, L., Yang, Z., Du, J., Li, S., Yin, A., and Zhao, G. (2022). Chromosomenet: A massive dataset enabling benchmarking and building basedlines of clinical chromosome classification. Computational Biology and Chemistry, 100:107731.

Magalhães, A., Monteiro, J., and Ângelo Brayner (2023). Main memory database instant recovery. In Anais Estendidos do XXXVIII Simpósio Brasileiro de Bancos de Dados (SBBD), pages 255–269, Porto Alegre, RS, Brasil. SBC.

Saranya, S. and Lakshmi, S. (2023). Classification of chromosomes to diagnose chromosomal abnormalities using cnn. In 2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF), pages 1–5.

Xia, C., Wang, J., Qin, Y., Wen, J., Liu, Z., Song, N., Wu, L., Chen, B., Gu, Y., and Yang, J. (2023). Karyonet: Chromosome recognition with end-to-end combinatorial optimization network. IEEE Transactions on Medical Imaging, 42(10):2899–2911.