Related Experiment Video
Updated: Jan 16, 2026
06:34
SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
Published on: August 8, 2025
533
Automated Cervical Nuclei Segmentation in Pap Smear Images Using Enhanced Morphological Thresholding Techniques.
Wan Azani Mustafa1,2, Khalis Khiruddin1, Syahrul Affandi Saidi1
1Faculty of Electrical Engineering & Technology, Universiti Malaysia Perlis, Pauh Putra Campus, Arau 02600, Perlis, Malaysia.
Diagnostics (Basel, Switzerland)
|September 27, 2025
Summary
This study presents an improved algorithm for segmenting cervical cell nuclei in Pap smear images, enhancing accuracy for automated screening and aiding early cervical cancer detection.
Area of Science:
- Medical Imaging
- Computational Pathology
- Biomedical Engineering
Background:
- Cervical cancer is a leading global cause of death, especially where screening access is limited.
- Manual Pap smear analysis is subjective and prone to errors, necessitating automated solutions.
- Accurate segmentation of cervical cell nuclei is crucial for automated analysis but challenging due to image artifacts.
Purpose of the Study:
- To develop an improved algorithm for accurate cervical nucleus segmentation.
- To support automated Pap smear analysis and enhance diagnostic reliability.
- To address challenges like overlapping cells, poor contrast, and staining variability.
Main Methods:
- Adaptive gamma correction for contrast enhancement.
- Otsu thresholding for initial segmentation.
- Adaptive morphological operations for post-processing refinement.
- Evaluation using image quality metrics and ground truth validation.
Main Results:
- Achieved high performance with Precision (0.9965), F-measure (97.29%), and Accuracy (98.39%).
- Demonstrated improved image clarity (PSNR 16.62) and sensitivity.
- Showed effectiveness across varying cell overlaps and staining conditions, outperforming traditional methods.
Conclusions:
- The algorithm provides robust and accurate cervical nucleus segmentation for automated Pap smear analysis.
- It offers a consistent framework for automated screening tools, enhancing diagnostic reliability.
- This work lays the foundation for broader applications in medical image analysis.
