Related Experiment Video
Updated: Aug 10, 2025
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
43.0K
Local-Ternary-Pattern-Based Associated Histogram Equalization Technique for Cervical Cancer Detection
Saravanan Srinivasan1, Aravind Britto Karuppanan Raju2, Sandeep Kumar Mathivanan3
1Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai 600062, India.
Diagnostics (Basel, Switzerland)
|February 11, 2023
Summary
This study introduces an advanced method for early cervical cancer detection using cervigram images. The novel approach achieves high accuracy in identifying and segmenting cancerous regions, outperforming traditional techniques.
Area of Science:
- Medical Imaging
- Computational Pathology
- Biomedical Engineering
Background:
- Cervical cancer remains a significant global health concern for women.
- Early detection and prompt treatment are crucial for improving patient outcomes and survival rates.
Purpose of the Study:
- To develop and validate a novel strategy for enhanced cervical cancer detection using cervigram images.
- To improve the accuracy and efficiency of identifying and segmenting cancerous regions in cervical images.
Main Methods:
- Image preprocessing using Adaptive Histogram Equalization (AHE) and Finite Ridgelet Transform for multi-resolution analysis.
- Feature extraction including ridgelets, gray-level run-length matrices, moment invariants, and enhanced local ternary patterns.
- Classification using a feed-forward backpropagation neural network and segmentation via morphological operations.
Main Results:
- The proposed system achieved high performance metrics: 98.11% sensitivity, 98.97% specificity, and 99.19% accuracy.
- Positive Predictive Value (PPV) was 98.88%, Negative Predictive Value (NPV) was 91.91%, and precision reached 98.13%.
- The method demonstrated superior performance in detecting and segmenting cervical cancer compared to traditional approaches.
Conclusions:
- The developed system offers a promising and effective tool for early and accurate cervical cancer detection.
- The integration of advanced image processing and machine learning techniques significantly enhances diagnostic capabilities.
