Related Experiment Video
Updated: Oct 3, 2025
Author Spotlight: Self-Assessment Protocol for Predicting Psoriatic Arthritis in Psoriasis Patients
Published on: March 1, 2024
A mask R-CNN based automatic assessment system for nail psoriasis severity.
Kuan Yu Hsieh1, Hung-Yi Chen2, Sung-Cheol Kim3
1Department of Electrical and Computer Engineering, College of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, 30010, Taiwan; Institute of Biomedical Engineering, College of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, 30010, Taiwan.
Nail psoriasis assessment is challenging in busy clinics. A new AI system using mask R-CNN and standard photography offers a fast, automatic solution for evaluating nail psoriasis severity.
Area of Science:
- Dermatology
- Artificial Intelligence
- Medical Imaging
Background:
- Nail psoriasis significantly impacts patient quality of life.
- Current assessment tools like Nail Psoriasis Severity Index (NAPSI) are time-consuming, hindering clinical application.
- Healthcare systems, particularly in Taiwan, face challenges with high patient loads, necessitating efficient assessment methods.
Purpose of the Study:
- To develop a simple, fast, and automatic system for assessing nail psoriasis severity.
- To overcome the limitations of traditional, time-intensive assessment tools in daily clinical practice.
- To aid dermatologists in accurate diagnosis, assessment, and treatment decisions for nail psoriasis.
Main Methods:
- Development of a standard photography capturing system.
- Utilization of a deep learning architecture, specifically mask R-CNN, for image analysis.
- Automatic feature extraction from image data without pre-processing.
Main Results:
- The developed system enables efficient and automatic assessment of nail psoriasis severity.
- It assists clinicians in capturing disease signs and normal skin features.
- The system streamlines the extraction of relevant image features.
Conclusions:
- The novel system provides an efficient and accurate method for nail psoriasis severity assessment.
- It addresses the practical challenges faced by dermatologists in high-volume clinics.
- This AI-driven approach has the potential to improve diagnostic accuracy and treatment planning for nail psoriasis.
