Related Experiment Video
Updated: Oct 22, 2025
09:33
Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
Published on: May 3, 2018
8.3K
Automated Cervical Digitized Histology Whole-Slide Image Analysis Toolbox
Sudhir Sornapudi1, Ravitej Addanki1, R Joe Stanley1
1Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA.
Journal of Pathology Informatics
|August 27, 2021
Summary
Automated analysis of cervical tissue images aids in diagnosing cervical intraepithelial neoplasia (CIN). This deep learning tool shows promise in assisting pathologists with accurate and efficient CIN grading.
Area of Science:
- Digital pathology
- Computational biology
- Oncology
Background:
- Cervical intraepithelial neoplasia (CIN) is a precancerous condition of the cervix.
- Early detection and treatment of CIN are crucial for reducing cervical cancer mortality.
- Accurate CIN grading, correlated with human papillomavirus (HPV) type, informs patient risk assessment.
Purpose of the Study:
- To develop and evaluate a novel image analysis toolbox for automated CIN diagnosis.
- To improve the accuracy and efficiency of CIN grading from digitized cervical tissue samples.
Main Methods:
- A four-step deep learning model was developed for automated CIN diagnosis.
- The model includes epithelium detection, segmentation, local region analysis, and classification.
- The study utilized whole slide images of cervical tissue biopsies.
Main Results:
- Automated epithelium detection and segmentation achieved results comparable to manual methods.
- The deep learning approach demonstrated effectiveness in classifying CIN from digitized histology slides.
Conclusions:
- The developed image analysis toolbox shows potential for assisting expert pathologists in diagnosing CIN.
- Automated analysis of digitized histology slides can enhance the efficiency and accuracy of cervical cancer screening.
