Classification of Visually Similar Scalp Diseases Using Deep Learning: A Hybrid CNN-VIT Approach with Cross-Attention Fusion

June 2026 in “ Zenodo (CERN European Organization for Nuclear Research) ”

Ayushi Dixit, Dr. Brij Mohan Singh

New to Alopecia Areata? There is a guide in the encyclopedia. Read the guide →

Psoriasis Seborrheic Dermatitis Tinea Capitis Alopecia Areata Folliculitis Eczema ScalpViT Vision Transformer Convolutional Neural Network ResNet-50 EfficientNet-B3 GradCAM Attention Rollout CNN ViT

Preprint — not peer reviewed. This was posted to a preprint server or data repository. It has not been through a journal's review process, and its findings may change or not hold up.

Studysummary In this study, researchers developed ScalpViT, a novel deep learning model, to improve the automated diagnosis of visually similar scalp diseases, achieving 94.3% accuracy and outperforming existing models like ResNet-50 and EfficientNet-B3 when tested on a diverse dataset of 7,000 images.

Automatically generated from the study's abstract, not written by a person, and not a review of the full paper. Not medical advice or a treatment recommendation. Read the original study, and consult a qualified healthcare professional before changing treatment. Full disclaimer ·

View this study on zenodo.org →

Discuss this study in the Community →

Similar Research

5 / 1000+ results

research Classification of Visually Similar Scalp Diseases using Deep Learning: A Hybrid CNN-VIT Approach with Cross-Attention Fusion

June 2026 in “Zenodo (CERN European Organization for Nuclear Research)”

In this study, researchers developed a hybrid deep learning model called ScalpViT that accurately diagnosed scalp diseases with 94.3% accuracy, surpassing existing methods like ResNet-50 and EfficientNet-B3, and providing visual explainability for clinicians using GradCAM and Attention Rollout techniques.

research Classification of Visually Similar Scalp Diseases using Deep Learning: A Hybrid CNN-VIT Approach with Cross-Attention Fusion

June 2026 in “Zenodo (CERN European Organization for Nuclear Research)”

This study introduces ScalpViT, a new deep learning model that accurately diagnoses visually similar scalp diseases with 94.3% accuracy, outperforming other methods like ResNet-50 and EfficientNet-B3, and providing dual visual explainability through GradCAM and Attention Rollout, potentially benefiting diagnosis in resource-limited settings in India.

research A Hybrid Deep Learning System for Automatic Detection of Scalp Diseases and Hair Fall Stage Classification

March 2026

This study introduced a deep learning framework combining multiple convolutional neural networks to detect scalp and hair disorders and classify hair fall stages, reporting higher precision and robustness in detection and classification compared to individual CNN models.

research Hair and Scalp Disease Detection using Machine Learning and Image Processing

5 citations , December 2022 in “arXiv (Cornell University)”

This study used a deep learning approach that successfully predicts alopecia, psoriasis, and folliculitis with a 2D convolutional neural network, achieving a training accuracy of 96.2% and validation accuracy of 91.1%.

research Scalp disease analysis using deep learning models

March 2023 in “Applied and Computational Engineering”

This study proposes a deep learning model using CNN with VGG16, VGG19, and MobileNetV2 architectures, achieving high accuracy in classifying scalp diseases from images, potentially facilitating diagnosis and treatment via mobile devices.