Enhanced Hair Disease Classification Using Deep Learning

March 2024

Deepak Banerjee, Vinay Kukreja, Dibyahash Bordoloi, Ankur Choudhary

hair conditions hair disease classification deep learning machine learning dataset precision recall F1-Score accuracy

TLDR The model accurately classifies hair conditions with 97% accuracy.

The study "Enhanced Hair Disease Classification Using Deep Learning" demonstrates the effectiveness of a machine-learning model in categorizing various hair conditions, such as Alopecia Areata, Tinea Capitis, and Psoriasis, using a dataset of 8,550 images. The model achieved high performance with accuracy values between 88.04% and 88.89%, recall values from 87.80% to 89.19%, and balanced F1 scores ranging from 88.02% to 88.99%. The overall accuracy was 97%, highlighting the model's reliability and efficacy in diagnosing hair diseases, which can significantly improve patient care and quality of life.

View this study on ieeexplore.ieee.org →

Discuss this study in the Community →

Research cited in this study

3 / 3 results

research Integrated Single-Cell Chromatin and Transcriptomic Analyses of Human Scalp Identify Gene-Regulatory Programs and Critical Cell Types for Hair and Skin Diseases

47 citations , July 2023 in “Nature Genetics”

research An Approach to Detect Alopecia Areata Hair Disease Using Deep Learning

January 2021 in “Lecture notes in networks and systems”

Deep learning can accurately detect Alopecia Areata with up to 98.3% accuracy.

research ScalpEye: A Deep Learning-Based Scalp Hair Inspection and Diagnosis System for Scalp Health

74 citations , January 2020 in “IEEE Access”

ScalpEye accurately diagnoses scalp issues like dandruff and hair loss.