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

Search research articles

Related Experiment Videos

Multimodal Deep Learning with Attention-Based Fusion for Skin Cancer Diagnosis.

Wiem Abdelbaki¹, Hend Alshaya², Inzamam Mashood Nasir³

¹College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait.

Bioengineering (Basel, Switzerland)

|May 27, 2026

Summary

Related Concept Videos

Skin Cancer

Skin Cancer

Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...

You might also read

Related Articles

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

Sort by

Same author

Transformer-Driven Explainable Deep Learning with Quantitative Attribution Validation for Liver Tumor Detection.

Bioengineering (Basel, Switzerland)·2026

Same author

Handcrafted Versus Deep Feature Extraction Methods for MRI-Based Multiple Sclerosis Diagnosis.

Diagnostics (Basel, Switzerland)·2026

Same author

Transformer-Based Deep Learning for Population-Scale Retinal Image Screening of Ophthalmic Disorders.

Bioengineering (Basel, Switzerland)·2026

Same author

Improving Deep Learning Based Lung Nodule Classification Through Optimized Adaptive Intensity Correction.

Bioengineering (Basel, Switzerland)·2026

Same author

Transformer-Based Foundation Learning for Robust and Data-Efficient Skin Disease Imaging.

Diagnostics (Basel, Switzerland)·2026

Same author

Domain-Adaptive MRI Learning Model for Precision Diagnosis of CNS Tumors.

Biomedicines·2026

This study introduces a multimodal deep learning framework for improved skin cancer diagnosis, combining clinical data and dermoscopic images. The model shows high accuracy and robustness across datasets, outperforming baseline methods.

Area of Science:

Medical Imaging
Artificial Intelligence
Dermatology

Background:

Skin cancer diagnosis is challenging due to variable imaging conditions.
Existing methods struggle with the high variability in clinical settings.

Purpose of the Study:

To develop a multimodal deep learning framework for enhanced skin cancer diagnosis.
To integrate auxiliary clinical information with dermoscopic image features.

Main Methods:

Proposed an attention-based feature encoder with structured multimodal fusion.
Evaluated the framework on ISIC 2019, ISIC 2020, and HAM10000 datasets.
Utilized a unified experimental approach for consistent evaluation.

Main Results:

Keywords:

attention mechanisms clinical data fusion cross-dataset generalization dermoscopic image analysis multimodal deep learning skin cancer diagnosis

Related Experiment Videos

Achieved high accuracies (up to 91.8%) and AUCs (up to 96.3%) on benchmark datasets.

Outperformed baseline models (ResNet50, EfficientNet-B4) with increased AUC (6.5%) and F1 score (8.0%).

Demonstrated strong generalization with an overall AUC of 90.9% and statistically significant improvements (p=0.01).

Conclusions:

The multimodal deep learning framework effectively addresses challenges in skin cancer diagnosis.
Attention and multimodal fusion mechanisms are crucial for performance.
The model is robust, generalizable, and suitable for clinical deployment.