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

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

A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises.

IEEE journal of biomedical and health informatics·2026

Same author

Comparative Evaluation of Vision-Language Models for Detecting and Localizing Dental Lesions from Intraoral Images.

Journal of imaging·2026

Same author

A triple pronged approach for ulcerative colitis severity classification using multimodal, meta, and transformer based learning.

Scientific reports·2025

Same author

Unsupervised tooth segmentation from three dimensional scans of the dental arch using domain adaptation of synthetic data.

International journal of medical informatics·2024

Same author

OptimCLM: Optimizing clinical language models for predicting patient outcomes via knowledge distillation, pruning and quantization.

International journal of medical informatics·2024

Same author

Predicting life satisfaction using machine learning and explainable AI.

Heliyon·2024

Search research articles

Related Experiment Video

Updated: Sep 22, 2025

A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

Published on: March 8, 2022

Knowledge distillation approach towards melanoma detection.

Md Shakib Khan¹, Kazi Nabiul Alam¹, Abdur Rab Dhruba¹

¹North South University, Dhaka, Bangladesh.

Computers in Biology and Medicine

|May 20, 2022

Summary

This summary is machine-generated.

We developed a lightweight AI model, Distilled Student Network (DSNet), for early melanoma detection from dermoscopic images. DSNet achieves 91.7% accuracy with significantly fewer parameters and faster inference, making it suitable for clinical use.

Keywords:

Deep learning Knowledge distillation Melanoma detection Skin lesion analysis

More Related Videos

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Detection and Isolation of Circulating Melanoma Cells using Photoacoustic Flowmetry

Detection and Isolation of Circulating Melanoma Cells using Photoacoustic Flowmetry

Published on: November 25, 2011

Related Experiment Videos

Last Updated: Sep 22, 2025

A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

Published on: March 8, 2022

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Detection and Isolation of Circulating Melanoma Cells using Photoacoustic Flowmetry

Detection and Isolation of Circulating Melanoma Cells using Photoacoustic Flowmetry

Published on: November 25, 2011

Area of Science:

Dermatology
Artificial Intelligence
Medical Imaging

Background:

Melanoma is the deadliest skin cancer, necessitating early detection systems.
Current machine learning models for melanoma detection are often computationally expensive, limiting clinical deployment.
There is a need for efficient and accurate AI models for melanoma diagnosis.

Purpose of the Study:

To develop a computationally efficient and performant AI model for melanoma detection from dermoscopic images.
To address the limitations of large, resource-intensive models in clinical settings.
To investigate the effectiveness of knowledge distillation in creating a compact yet accurate melanoma detection model.

Main Methods:

A teacher model (ResNet-50) was trained for melanoma detection.
Knowledge distillation was employed to train a smaller student model, Distilled Student Network (DSNet), with 0.26 million parameters.
DSNet's performance was compared against various ImageNet pre-trained models, including MobileNet, VGG-16, Inception-V3, EfficientNet-B0, ResNet-50, and ResNet-101.

Main Results:

DSNet achieved an accuracy of 91.7% in detecting melanoma.
DSNet demonstrated a significantly faster inference runtime (2.57s) compared to other models (e.g., 14.55s).
DSNet, despite being 15 times smaller than EfficientNet-B0, consistently outperformed it in Precision, Recall, and F1 scores for both melanoma and non-melanoma detection.

Conclusions:

DSNet offers a highly efficient and accurate solution for melanoma detection from dermoscopic images.
The knowledge distillation approach successfully created a lightweight model suitable for resource-constrained environments and clinical settings.
DSNet presents a promising alternative to larger, computationally demanding models for early skin cancer diagnosis.