Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Skin Cancer01:30

Skin Cancer

4.0K
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...
4.0K
Papillary Dermis01:11

Papillary Dermis

2.8K
Dermis
The dermis might be considered the "core" of the integumentary system, as distinct from the epidermis and hypodermis. It contains blood and lymph vessels, nerves, and other structures, such as hair follicles and sweat glands. The dermis is made of two layers of connective tissue that comprise an interconnected mesh of elastin and collagenous fibers, produced by fibroblasts.
Papillary Layer
The papillary layer is made of loose, areolar connective tissue, which means the collagen...
2.8K
Reticular Dermis01:15

Reticular Dermis

2.5K
The papillary and reticular dermis are the two layers of the dermis. They are made of connective tissue with fibers of collagen extending from one to the other, making the border between the two somewhat indistinct. The dermal papillae extending into the epidermis belong to the papillary layer, whereas the dense collagen fiber bundles below belong to the reticular layer.
Reticular Layer
Underlying the papillary layer is the much thicker reticular layer, composed of dense, irregular connective...
2.5K

You might also read

Related Articles

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

Sort by
Same author

Development of Mobile Software "SRCardioCare" Prototype for Implementing Home-Based Exercise Program Among Patients After Adult Cardiac Surgical Revascularization: Qualitative Feasibility Study.

JMIR rehabilitation and assistive technologies·2026
Same author

Industrial engineering solutions enhance operational efficiency in human and veterinary hospitals: a scoping review.

American journal of veterinary research·2025
Same author

Multi-modal transformer architecture for medical image analysis and automated report generation.

Scientific reports·2024
Same author

A hybrid model for the classification of Autism Spectrum Disorder using Mu rhythm in EEG.

Technology and health care : official journal of the European Society for Engineering and Medicine·2024
Same author

AHANet: Adaptive Hybrid Attention Network for Alzheimer's Disease Classification Using Brain Magnetic Resonance Imaging.

Bioengineering (Basel, Switzerland)·2023
Same author

A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images.

Diagnostics (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jun 21, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

515

Integration of Localized, Contextual, and Hierarchical Features in Deep Learning for Improved Skin Lesion

Karthik Ramamurthy1, Illakiya Thayumanaswamy2, Menaka Radhakrishnan1

  • 1Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai 600127, India.

Diagnostics (Basel, Switzerland)
|July 13, 2024
PubMed
Summary

This study introduces a novel dual-track deep learning model for improved skin lesion classification. The model enhances feature representation, achieving 93.2% accuracy on the HAM10000 dataset for early skin disease detection.

Keywords:
convolutional neural networkdeep learningdermoscopic imagesimage processingskin cancer

More Related Videos

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

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

Published on: August 18, 2022

2.3K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

Related Experiment Videos

Last Updated: Jun 21, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

515
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

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

Published on: August 18, 2022

2.3K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

Area of Science:

  • Dermatology
  • Computer Science
  • Artificial Intelligence

Background:

  • Skin lesion classification is crucial for early disease detection.
  • Current methods struggle with complex dermoscopic image data and long-range dependencies.

Purpose of the Study:

  • To enhance skin lesion classification by improving feature representation.
  • To develop a novel dual-track deep learning model for improved performance.

Main Methods:

  • A dual-track deep learning model was developed.
  • Track 1: Modified DenseNet-169 with Coordinate Attention Module (CoAM) for local features.
  • Track 2: Customized CNN with Feature Pyramid Network (FPN) and Global Context Network (GCN) for multiscale and global features.

Main Results:

  • The dual-track model effectively integrates local and global features.
  • Achieved a classification accuracy of 93.2% on the HAM10000 dataset.
  • Demonstrated superior performance compared to previous skin lesion classification approaches.

Conclusions:

  • The proposed dual-track deep learning model significantly improves skin lesion classification accuracy.
  • Incorporating local, global, and hierarchical features enhances diagnostic capabilities.
  • This approach holds promise for early and accurate detection of skin diseases.