Related Experiment Video
Updated: Sep 22, 2025
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
Published on: January 27, 2023
Automatic recognition of micronucleus by combining attention mechanism and AlexNet
Weiyi Wei1, Hong Tao2, Wenxia Chen1
1College of Computer Science and Engineering, Northwest Normal University, Lanzhou, China.
Background:
Micronucleus (MN) is an abnormal fragment in a human cell caused by disorders in the mechanism regulating chromosome segregation. It can be used as a biomarker for genotoxicity, tumor risk, and tumor malignancy. The in vitro micronucleus assay is a commonly used method to detect micronucleus. However, it is time-consuming and the visual scoring can be inconsistent.
Methods:
To alleviate this issue, we proposed a computer-aided diagnosis method combining convolutional neural networks and visual attention for micronucleus recognition. The backbone of our model is AlexNet without any dense layers and it is pretrained on the ImageNet dataset. Two attention modules are applied to extract cell image features and generate attention maps highlighting the region of interest to improve the interpretability of the network. Given the problems in the data set, we leverage data augmentation and focal loss to alleviate the impact.
Results:
Experiments show that the proposed network yields better performance with fewer parameters. The AP value, F1 value and AUC value reach 0.932, 0.811 and 0.995, respectively.
Conclusion:
In conclusion, the proposed network can effectively recognize micronucleus, and it can play an auxiliary role in clinical diagnosis by doctors.
Insights
This study introduces an AI model for faster and more accurate micronucleus detection in human cells. The computer-aided diagnosis method improves genotoxicity and tumor risk assessment in clinical settings.
Area of Science:
- Biomedical Engineering
- Computational Biology
- Genetics
Background:
- Micronuclei (MN) are biomarkers for genotoxicity, tumor risk, and malignancy, detected via in vitro micronucleus assays.
- Traditional visual scoring of micronuclei is time-consuming and prone to inconsistency.
Purpose of the Study:
- To develop an automated computer-aided diagnosis method for efficient and reliable micronucleus recognition.
- To enhance the interpretability and accuracy of micronucleus detection in cell images.
Main Methods:
- A convolutional neural network (AlexNet) combined with visual attention modules was employed for micronucleus recognition.
- Data augmentation and focal loss were utilized to address dataset limitations and improve model robustness.
- Attention maps were generated to highlight regions of interest, enhancing network interpretability.
Main Results:
- The proposed network achieved superior performance with fewer parameters compared to traditional methods.
- Key performance metrics included an AP value of 0.932, F1 value of 0.811, and AUC value of 0.995.
- The model demonstrated effective feature extraction and accurate localization of micronuclei.
Conclusions:
- The developed network effectively recognizes micronuclei, offering a significant advancement in automated cell analysis.
- This AI-driven approach can serve as a valuable auxiliary tool for clinicians in diagnosing genotoxicity and tumor-related conditions.
