Detection of Micronuclei in Lymphocytes: A New Dataset and Case Study Using YOLOv11
Abstract
The detection of micronuclei (MN) in lymphocytes is essential in biomedicine for assessing genetic damage and chromosomal instability, playing a crucial role in toxicological studies and cancer diagnosis. However, manual identification is time-consuming and prone to errors. In this work, we propose an automated approach using the YOLOv11 neural network for detecting micronuclei in binucleated cells. To achieve this, we built an image dataset collected from the Regional Center for Nuclear Sciences of the Northeast (CRCN), comprising 889 images annotated with the locations of binucleated cells and micronuclei. The results of the detection analysis show that the model achieved a precision of 90.8% and a recall of 92.8%, demonstrating reliability for clinical applications. Additionally, the developed dataset contributes to future research in the field, providing a standardized benchmark for evaluating computer vision models applied to cytogenetics. The dataset is available at https://doi.org/10.5281/zenodo.14947933.
References
Ibarra-Arellano, M. A., Caprio, L. A., Hada, A., Stotzem, N., Cai, L., Shah, S., Melms, J. C., Wünneman, F., Izar, B., and Schapiro, D. (2024). micronuclai: Automated quantification of micronuclei for assessment of chromosomal instability. bioRxiv [Pre-print], 2024(05.24.595722). Accessed: 2025-02-09.
Jain, S., Dash, S., Deorari, R., et al. (2022). Object detection using coco dataset. In 2022 International Conference on Cyber Resilience (ICCR), pages 1–4. IEEE.
Jiang, P., Ergu, D., Liu, F., Cai, Y., and Ma, B. (2022). A review of yolo algorithm developments. Procedia computer science, 199:1066–1073.
Jocher, G., Qiu, J., and Chaurasia, A. (2023). Ultralytics YOLO.
Kaggle (2025). Kaggle notebooks. url: [link]. Acessado em: 20/02/2025.
Krupina, K., Goginashvili, A., and Cleveland, D. W. (2021). Causes and consequences of micronuclei. Current Opinion in Cell Biology, 70:91–99. Accessed: 2025-02-09.
Padilla, R., Netto, S. L., and Da Silva, E. A. (2020). A survey on performance metrics for object-detection algorithms. In 2020 international conference on systems, signals and image processing (IWSSIP), pages 237–242. IEEE.
Panchbhai, A., Ishanzadeh, M. C. S., Sidali, A., Solaiman, N., Pankanti, S., Kanagaraj, R., Murphy, J. J., and Surendranath, K. (2023). A deep learning workflow for quantification of micronuclei in dna damage studies in cultured cancer cell lines: a proof of principle investigation. Computer Methods and Programs in Biomedicine, 232:107447.
Rohr, P., da Silva, G. F., Vicentini, V. E. P., de Almeida, I. V., Dos Santos, R. A., Takahashi, C. S., Goulart, M. O., da Silva, G. N., de Oliveira, L. B., Grisolia, C. K., et al. (2020). Buccal micronucleus cytome assay: Inter-laboratory scoring exercise and micronucleus and nuclear abnormalities frequencies in different populations from brazil. Toxicology Letters, 333:242–250.
Wei, W., Leng, Y., Cao, L., et al. (2024). Std-yolov7: A small target detector for micronucleus based on yolov7. Accessed: 2025-02-09.
Wei, W., Li, J., Wu, X., and Zhang, H. (2023). High-through cell micronucleus image detection method combining multi-attention mechanism and yolov5. Biomedical Signal Processing and Control, 87:105496. Accessed: 2025-02-09.
Yoda, H., Abe, K., Takeo, H., Takamura-Enya, T., and Koike-Takeshita, A. (2024). Application of image-recognition techniques to automated micronucleus detection in the in vitro micronucleus assay. Genes and Environment, 46(1):11.
