Related Experiment Video
Updated: Jul 5, 2025
09:11
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
Published on: January 27, 2023
2.1K
An automated cervical cancer diagnosis using genetic algorithm and CANFIS approaches
Elayaraja P1, Kumarganesh S2, K Martin Sagayam3
1Department of Electronics and Communication Engineering, Kongunadu College of Engineering and Technology, Trichy, India.
Summary
This study introduces an automated system for segmenting cervical cancer regions, achieving high accuracy. The advanced method enhances early detection and diagnosis of cervical malignancy in women.
Area of Science:
- Medical Imaging
- Computational Pathology
- Artificial Intelligence in Healthcare
Background:
- Cervical malignancy is a leading cause of cancer-related deaths among women in East Africa and South Asia.
- Early and accurate detection of cervical cancer is crucial for improving patient outcomes and reducing mortality rates.
Purpose of the Study:
- To develop an efficient automated system for segmenting cancerous regions in cervical images.
- To enhance the diagnostic capabilities for cervical malignancy through advanced image analysis.
Main Methods:
- Image preprocessing using Gaussian Filter.
- Feature extraction using Local Binary Pattern (LBP) and Grey Level Co-occurrence Matrix (GLCM).
- Feature optimization via Genetic Algorithm (GA) and classification using Co-Active Adaptive Neuro-Fuzzy Inference System (CANFIS).
- Segmentation of malignant regions using morphological techniques.
Main Results:
- The automated system achieved high performance metrics: 99.09% sensitivity, 99.39% specificity, and 99.36% accuracy.
- The proposed method effectively distinguishes between normal and abnormal cervical tissues.
Conclusions:
- The developed automated system demonstrates superior performance in segmenting cervical cancerous regions.
- The findings were validated by expert radiologists, confirming the clinical relevance and potential of the approach.
