Related Experiment Video
Updated: Aug 5, 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
Image Processing for Diagnosing Psoriasis: A Machine Learning Approach to Classify Skin Lesions into Psoriasis
Hoorie Masoorian1, Marsa Gholamzadeh1, Alireza Firooz2
1Health Information Management and Medical informatics Department, School of Allied Medical Science, Tehran University of Medical Sciences, Tehran, Iran.
Medical Journal of the Islamic Republic of Iran
|July 28, 2026
Summary
A new AI model accurately classifies psoriasis subtypes using deep learning, aiding clinicians in diagnosis and treatment. This tool offers scalable solutions for psoriasis management, improving patient care.
Area of Science:
- Dermatology
- Artificial Intelligence
- Medical Imaging
Background:
- Psoriasis affects 2-3% of the global population with diverse subtypes.
- Accurate psoriasis subtype classification is vital for effective treatment.
- Traditional diagnostic methods face challenges in speed and observer variability.
Purpose of the Study:
- To develop a machine learning model for classifying five primary psoriasis subtypes.
- To leverage convolutional neural networks (CNNs) and transfer learning for accurate classification.
- To create a scalable tool to assist clinicians in psoriasis diagnosis and treatment decisions.
Main Methods:
- A deep learning model was developed using a VGG16 architecture.
- Image augmentation techniques enhanced dataset diversity.
- The model was trained and evaluated using accuracy and loss metrics, with optimization techniques.
Main Results:
- The model achieved 96% accuracy on the training dataset and 90% on the test dataset.
- A confusion matrix confirmed accurate differentiation among the five psoriasis subtypes.
- The model demonstrated strong generalization capabilities.
Conclusions:
- A deep learning model was successfully developed for accurate psoriasis subtype classification.
- The model was integrated into a web-based tool for real-time clinical assistance.
- This AI-driven system can enhance diagnostic accuracy and improve clinical workflows for psoriasis management.