Related Experiment Video
Updated: Jan 15, 2026
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
Published on: January 27, 2023
Advanced concept for identifying chemico-biological interactions associated with programmed cell death using a
Igor V Pantic1, Jovana Paunovic Pantic2
1University of Belgrade, Faculty of Medicine, Department of Medical Physiology, Visegradska 26/II, 11129, Belgrade, Serbia; University of Haifa, 199 Abba Hushi Blvd, Mount Carmel, Haifa IL, 3498838, Israel; Ben-Gurion University of the Negev, Faculty of Health Sciences, Department of Physiology and Cell Biology, 84105, Be'er Sheva, Israel.
Abstract:
Early detection of programmed cell death (apoptosis) remains a significant challenge in microscopy and cell biology, particularly when relying on subtle nuclear texture changes observed in stained micrographs. Traditional machine learning models, such as decision trees and random forests, are limited in their methodological capacity and often fail to capture complex spatial relationships within nuclear architecture. Unlike these conventional approaches, our study introduces a novel Multi-Scale Attention Residual Convolutional Neural Network (MSA-RCNN) designed to learn discriminative features from nuclear chromatin patterns associated with early apoptotic changes. We suggest using quantifiers of the Gray-Level Entropy Matrix (GLEM), Run-Length Matrix (RLM), and Discrete Fourier Transform (DFT) as input parameters during training and testing, focusing on the combination of four parameters: RLM Short Run Emphasis, RLM Long Run Emphasis, GLEM Entropy, and DFT Magnitude Spectrum Mean. We also discuss the advantages and limitations of this approach and its potential to be included in future artificial intelligence-based sensing systems for apoptosis detection in research and clinical conditions. Like many deep learning models, the proposed MSA-RCNN is limited by challenges in interpretability and generalization, which future work will address through explainability analyses and validation on different datasets.
Insights
This study introduces a novel Multi-Scale Attention Residual Convolutional Neural Network (MSA-RCNN) for early apoptosis detection using nuclear texture. The AI model analyzes chromatin patterns for improved accuracy in cell biology research.
Area of Science:
- Cell Biology
- Biotechnology
- Computational Biology
Background:
- Early detection of apoptosis is crucial but challenging using traditional microscopy and machine learning.
- Conventional models struggle with complex spatial relationships in nuclear architecture.
- Subtle nuclear texture changes in stained micrographs are key indicators of early apoptosis.
Purpose of the Study:
- To introduce a novel Multi-Scale Attention Residual Convolutional Neural Network (MSA-RCNN) for enhanced apoptosis detection.
- To leverage nuclear chromatin patterns and texture features for identifying early apoptotic changes.
- To explore the potential of AI in improving apoptosis detection for research and clinical applications.
Main Methods:
- Developed a novel Multi-Scale Attention Residual Convolutional Neural Network (MSA-RCNN).
- Utilized quantifiers from Gray-Level Entropy Matrix (GLEM), Run-Length Matrix (RLM), and Discrete Fourier Transform (DFT) as input features.
- Focused on specific parameters: RLM Short Run Emphasis, RLM Long Run Emphasis, GLEM Entropy, and DFT Magnitude Spectrum Mean.
Main Results:
- The MSA-RCNN learns discriminative features from nuclear chromatin patterns indicative of early apoptosis.
- The model effectively utilizes GLEM, RLM, and DFT quantifiers for apoptosis detection.
- Demonstrated a novel approach for AI-based sensing systems in cell biology.
Conclusions:
- The proposed MSA-RCNN shows promise for accurate early apoptosis detection.
- This AI approach offers advantages over traditional machine learning methods in capturing complex nuclear features.
- Future work will address model interpretability and generalization through explainability analyses and diverse dataset validation.
