Related Experiment Video
Updated: Oct 29, 2025
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
459
Morphological Based Medical Image Processing on Cervical Cytology Cancer Images Using Connected Component Techniques.
1Department of Information Technology, Vel Tech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College, Avadi, Chennai, Tamilnadu, India.
Current Medical Imaging
|July 9, 2021
Summary
A novel method accurately segments cervical cancer images using HSI color models and thresholding. This technique achieves high peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) values, outperforming existing approaches for improved diagnosis.
Area of Science:
- Medical Imaging
- Computational Pathology
- Oncology
Background:
- Cervical cancer is a significant global health issue, ranking as the fourth most common cancer in women.
- In 2018, cervical cancer led to an estimated 570,000 diagnoses and 311,000 deaths worldwide.
- Accurate image segmentation is crucial for effective cervical cancer diagnosis.
Purpose of the Study:
- To develop an efficient and accurate image segmentation technique for cervical cancer detection.
- To improve the precision of identifying cancerous regions within cervical images.
Main Methods:
- Conversion of RGB cervical cancer images to the HSI (Hue, Saturation, Intensity) color model.
- Application of thresholding on saturation and intensity components to generate binary images.
- Segmentation of nucleus and cytoplasm using the connected component concept on combined binary images.
Main Results:
- The proposed method achieved high peak signal-to-noise ratio (PSNR) values, with some reaching over 60 dB.
- Excellent performance metrics including high precision, recall, and structural similarity index (SSIM) were obtained.
- The technique demonstrated low mean square error (MSE) and average difference (AD), indicating high-quality segmentation.
Conclusions:
- The developed segmentation technique provides accurate and efficient analysis of cervical cancer images.
- The proposed model outperforms existing methods in terms of segmentation quality and diagnostic utility.
- This advancement holds potential for improving the early detection and management of cervical cancer.
