Ensemble of Pre-Learned Deep Learning Model and an Optimized LSTM for Alopecia Areata Classification

October 2023 in “ Journal of Intelligent & Fuzzy Systems ”

C. Saraswathi, B. Pushpa

Alopecia Areata deep learning Long Short-Term Memory LSTM Computer Aided Diagnosis CAD Convolutional Neural Network CNN AlexNet ResNet InceptionNet Battle Royale Optimization fuzzy-softmax Figaro1k DermNet AA

Studysummary This study proposed and tested an Ensemble Pre-Learned Deep Learning and Optimized Long Short-Term Memory (EPL-OLSTM) model for classifying Alopecia Areata, achieving a 93.1% accuracy in differentiating healthy from varying severity levels of AA scalp hair using specific datasets.

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

The study proposes an Ensemble Pre-Learned Deep Learning and Optimized Long Short-Term Memory (EPL-OLSTM) model to improve the classification of Alopecia Areata (AA) using medical imaging. By integrating pre-learned CNN structures like AlexNet, ResNet, and InceptionNet with an optimized LSTM using the Battle Royale Optimization algorithm, the model enhances the accuracy of differentiating between healthy and various AA scalp hair classes. The model's performance was validated using the Figaro1k and DermNet datasets, achieving a 93.1% accuracy, surpassing existing deep learning models. This approach aims to address the limitations of current Computer Aided Diagnosis models, which require skilled radiologists and have limited interoperability.

View this study on doi.org →

Discuss this study in the Community →

Research cited in this study

9 / 9 results

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

3 citations , January 2023 in “European Journal of Information Technologies and Computer Science”

This study found that a deep learning approach successfully predicted three types of hair and scalp diseases with high accuracy, despite challenges in dataset availability and image variety.

research Alopecia Areata: Current Understanding and Management

11 citations , January 2022 in “Journal der Deutschen Dermatologischen Gesellschaft”

This review discusses current and emerging therapies for alopecia areata, highlights the challenges in managing this chronic disease, and emphasizes the importance of addressing its psychosocial impacts; it reports no new clinical 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 How Good Is Artificial Intelligence at Solving Hairy Problems? A Review of AI Applications in Hair Restoration and Hair Disorders

4 citations , January 2021 in “Dermatologic Therapy”

This review highlights current and future AI applications in hair restoration and diagnosis of hair disorders, including automated systems for hair detection and self-diagnosis, emphasizing the need for experts to understand their benefits and limitations.

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

74 citations , January 2020 in “IEEE Access”

This study reports that the ScalpEye system accurately diagnosed dandruff, folliculitis, hair loss, and oily hair with a precision range of 97.41% to 99.09%.

research Trichoscopy of Dark Scalp: A Review of Trichoscopic Features in Hair and Scalp Disorders in Dark-Skinned Individuals

18 citations , July 2018 in “Skin appendage disorders”

This review discusses trichoscopic features of hair disorders in individuals with dark skin phototypes and reports no new clinical results; the authors emphasize the need for more specific diagnostic criteria for these populations.

research Hair Loss Diagnosis and Treatment Expert System

2 citations , January 2017

This abstract reviews existing hair loss treatments, highlighting FDA-approved drugs like Minoxidil and Finasteride while noting growing interest in herbal alternatives due to concerns about potential long-term side effects.