Related Experiment Video
Updated: Jan 1, 2026
09:32
Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach
Published on: September 26, 2019
7.6K
Computer Aided Diagnosis of Atopic Dermatitis
Joanna Czajkowska1, Szymon Korzekwa2, Ewa Pietka1
1Faculty of Biomedical Engineering, Silesian University of Technology.
Summary
This study introduces an automated method using high-frequency ultrasound to precisely measure a skin abnormality linked to allergic skin conditions like atopic dermatitis in children. This non-invasive technique aids in objective assessment before and during treatment.
Area of Science:
- Dermatology
- Medical Imaging
- Biomedical Engineering
Background:
- Allergic skin diseases, such as atopic dermatitis, are prevalent in children, necessitating objective, non-invasive assessment methods.
- Current diagnostic approaches for inflammatory dermatoses lack objective, non-invasive tools for evaluating skin conditions during therapy.
- High-frequency ultrasound (HFUS) shows promise for imaging skin inflammation, with a characteristic superficial hypoechoic band observed in inflammatory dermatoses.
Purpose of the Study:
- To develop and validate a fully automatic method for segmenting the superficial hypoechoic band in high-frequency ultrasound images.
- To provide an objective, non-invasive tool for assessing inflammatory skin conditions, specifically atopic dermatitis, in pediatric patients.
- To enhance the clinical utility of high-frequency ultrasound in dermatology by automating the analysis of key diagnostic features.
Main Methods:
- A novel three-step automated algorithm was developed for segmenting the hypoechoic band.
- The methodology involved epidermis echo entry layer detection and segmentation, followed by segmentation of the target skin abnormality.
- The algorithm was specifically designed for a 75MHz ultrasound probe, capable of visualizing a 12mm length and 4mm depth skin area.
Main Results:
- The proposed automated segmentation method demonstrated high accuracy in identifying the characteristic hypoechoic band.
- Validation was performed on 45 clinical ultrasound images, with annotations provided by two independent experts.
- The results confirm the framework's effectiveness in objectively assessing skin abnormalities indicative of inflammatory dermatoses.
Conclusions:
- The developed automated high-frequency ultrasound segmentation framework offers a reliable and non-invasive method for assessing inflammatory skin conditions.
- This approach can significantly aid in the objective evaluation and management of pediatric allergic skin diseases like atopic dermatitis.
- The study highlights the potential of advanced imaging analysis techniques to improve dermatological diagnostics and patient care.
