Related Experiment Video
Updated: May 4, 2026
09:33
Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System
Published on: May 3, 2018
8.7K
An automated blur detection method for histological whole slide imaging
Xavier Moles Lopez1, Etienne D'Andrea1, Paul Barbot2
1Laboratories of Image, Signal processing and Acoustics (LISA), Université Libre de Bruxelles, Brussels, Belgium ; DIAPath - Center for Microscopy and Molecular Imaging, Université Libre de Bruxelles, Gosselies, Belgium.
Plos One
|December 19, 2013
Summary
Whole slide scanners create high-resolution images for research but can have blurred areas. A new statistical method offers early image quality feedback, automatically finding areas needing better focus.
Area of Science:
- Digital pathology
- Biomedical imaging
- Computational pathology
Background:
- Whole slide imaging (WSI) enables high-resolution, rapid digitization of histological slides.
- WSI is crucial for large-scale studies using multiple immunohistochemistry biomarkers.
- Image artifacts, particularly blur from poor focusing, can compromise data integrity.
Purpose of the Study:
- To develop a method for early detection of image quality issues in whole slide imaging.
- To automate the identification of regions requiring re-focusing during the slide scanning process.
Main Methods:
- A statistical learning approach was employed to analyze image quality.
- The method provides real-time feedback on focus quality during scanning.
- Automated identification of blurred regions needing focus point adjustment.
Main Results:
- The proposed method successfully identifies regions with suboptimal focus.
- Early image quality feedback minimizes the need for manual slide review.
- Automated focus point suggestions streamline the scanning workflow.
Conclusions:
- The statistical learning method enhances the efficiency and reliability of whole slide imaging.
- Automating focus correction improves data quality and reduces manual workload in digital pathology.
- This approach addresses a key challenge in large-scale WSI analysis.
