Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same journal

Deep Learning Based Framework for Detection and Classification of Leukemia Using Microscopic Images.

Microscopy research and technique·2026

Same journal

Externally Controlled In Situ SEM: Multi-Rate Scanning With Signal Regulation and Spatiotemporal Fusion.

Microscopy research and technique·2026

Same journal

In Situ TEM Observation of Phase Transformation Nucleation at the Near-Surface of Synthetic Aragonite.

Microscopy research and technique·2026

Same journal

Morpho-Anatomical and HPTLC Investigations of Lysimachia nummularia L. (Primulaceae) Grown in Switzerland.

Microscopy research and technique·2026

Same journal

Macroscopic, Histological and Ultrastructural Features of the Tongue of the Anatolian Wild Boar (Sus scrofa libycus).

Microscopy research and technique·2026

Same journal

Ultrastructural Insights Into the Reproductive Anatomy and Eggs of Cotton Pink Bollworm, Pectinophora gossypiella Saunders (Lepidoptera: Gelechiidae).

Microscopy research and technique·2026

Search research articles

Related Experiment Video

Updated: May 23, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

MOAT: MobileNet-Optimized Attention Transfer for Robust and Scalable Dermatology Image Classification.

Pradeep Radhakrishnan¹, Praveen Kumar Sukumar²

¹Computer Science and Engineering, Saveetha Engineering College, Chennai, Tamil Nadu, India.

Microscopy Research and Technique

|March 8, 2025

Summary

A new MobileNet-Optimized Attention Transfer framework accurately classifies skin disease using image analysis. This method achieves high accuracy and low computational time, offering a scalable solution for clinical dermatology.

Keywords:

MobileNet attention mechanism optical microscope algorithm skin disease transfer learning

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: May 23, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Dermatology
Artificial Intelligence
Medical Imaging

Background:

Dermatological diseases are a global health concern requiring accurate detection for effective treatment.
Existing methods for skin disease detection from images often suffer from low accuracy and high computational demands.
Accurate and timely diagnosis is crucial for improving patient outcomes in dermatology.

Purpose of the Study:

To propose a novel MobileNet-Optimized Attention Transfer framework for accurate skin disease classification.
To enhance feature extraction in dermatological images using self-attention and cross-attention mechanisms.
To improve the efficiency and accuracy of automated skin disease detection systems.

Main Methods:

Utilized the MobileNet model for feature extraction, incorporating self-attention and cross-attention mechanisms.
Employed an Optical Microscope Algorithm for hyperparameter tuning to optimize model performance.
Validated the framework on the Skin Cancer ISIC and HAM10000 datasets.

Main Results:

Achieved a high classification accuracy of 98.89% for dermatological diseases.
Demonstrated a low mean squared error of 0.186.
Recorded a significantly low computational time of 1.53 seconds.

Conclusions:

The MobileNet-Optimized Attention Transfer framework offers a scalable and adaptable solution for clinical applications.
The proposed method provides reliable diagnostic support for dermatologists, facilitating early intervention.
This advanced framework outperforms existing methodologies in accuracy and efficiency for skin disease classification.