Prediction of Alopecia Areata Using CNN

May 2023

Anmol Mittal, Debodyuti Bidyut Biswas, U Karthikeyan

Alopecia Areata Convolutional Neural Network CNN autoimmune disease hair loss image-based dataset machine learning models Naive Bayes Support Vector Machine Logistic Regression Decision Tree image preprocessing

Studysummary The authors of this study developed a novel CNN architecture aimed at improving detection of Alopecia Areata through image-based datasets, achieving a top accuracy of 98% compared to four other machine learning models.

Our plain-language summary. Not medical advice or a treatment recommendation. Consult a qualified healthcare professional before changing treatment. Full disclaimer

This study introduces a novel Convolutional Neural Network (CNN) architecture to improve the detection of Alopecia Areata, an autoimmune disease causing hair loss, by using an image-based dataset. Traditional diagnosis relies heavily on visual examination by doctors, which can lead to low credibility. The CNN model's performance was compared with four machine learning models: Naive Bayes, Support Vector Machine, Logistic Regression, and Decision Tree. The dataset was enhanced through image preprocessing techniques, and the CNN achieved a best accuracy of 98%, indicating its potential to streamline and enhance the reliability of Alopecia Areata detection.

View this study on ieeexplore.ieee.org →

Discuss this study in the Community →

Research cited in this study

4 / 4 results

research Classification Framework for Healthy Hair and Alopecia Areata: A Machine Learning Approach

8 citations , August 2021 in “Computational and Mathematical Methods in Medicine”

This article proposes a machine learning framework for classifying healthy hair and alopecia areata using image processing and classification techniques, but does not report new clinical findings.

research Trichoscopy of Alopecia Areata: Hair Loss Feature Extraction and Computation Using Grid Line Selection and Eigenvalue

10 citations , September 2020 in “Computational and Mathematical Methods in Medicine”

This paper introduces an algorithm for using smart device-mounted microscopes to analyze scalp images and diagnose hair loss by extracting specific hair loss features.

research Pre-Trained Classification of Scalp Conditions Using Image Processing

15 citations , August 2020 in “Indonesian Journal of Electrical Engineering and Computer Science”

This study found that a pre-trained image processing technique accurately classified scalp conditions with 85% accuracy, suggesting potential for automated diagnosis and treatment selection.

research Quantifying Alopecia Areata via Texture Analysis to Automate the SALT Score Computation

20 citations , December 2017 in “Journal of Investigative Dermatology Symposium Proceedings”

This article presents a computer imaging algorithm that may automate and enhance the Severity of Alopecia Tool scoring for alopecia areata through texture analysis of pediatric images.