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

You might also read

Related Articles

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

Sort by
Same author

The Role of RCM and LC-OCT in Genodermatoses Associated with Skin Cancer: A Narrative Review.

Acta dermato-venereologica·2026
Same author

Long Distance Non-Contact Dermoscopy: Technological Foundations, Clinical Applications, and Future Directions.

International journal of dermatology·2026
Same author

Uncovering a Dual Th17/Type 2 Transcriptomic Endotype in Psoriasis.

Journal of the American Academy of Dermatology·2026
Same author

The Influence of Dietary and Physical Exercise Habits on Melanoma Risk: A Case-Control Study.

Nutrients·2026
Same author

Benralizumab relieves Eosinophil-Related Cutaneous Adverse Events from Cancer Therapy: A Nonrandomized Phase 2 Trial.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

Transcriptomic meta-analysis identifies core molecular pathways in plaque psoriasis.

Journal of the European Academy of Dermatology and Venereology : JEADV·2026

Related Experiment Video

Updated: Oct 30, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.2K

Deep learning automated pathology in ex vivo microscopy.

Marc Combalia1, Sergio Garcia1, Josep Malvehy1

  • 1Department of Dermatology, Hospital Clinic de Barcelona, Universitat de Barcelona, Barcelona, Spain.

Biomedical Optics Express
|July 5, 2021
PubMed
Summary

Artificial intelligence (AI) transforms ex vivo confocal microscopy (XVM) images into standard histopathology views for skin cancer margin assessment. This AI-driven approach enhances diagnostic accuracy, potentially streamlining Mohs surgery workflows.

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.1K

Related Experiment Videos

Last Updated: Oct 30, 2025

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning
09:31

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

3.2K
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

4.1K

Area of Science:

  • Dermatology and Pathology
  • Medical Imaging
  • Artificial Intelligence in Medicine

Background:

  • Standard histopathology is the gold standard for assessing margin status in Mohs surgery for skin cancer.
  • Ex vivo confocal microscopy (XVM) offers potential advantages in speed, cost, and digital imaging but requires specialized pathologist training.
  • Widespread adoption of XVM is limited by the learning curve for image interpretation.

Purpose of the Study:

  • To develop and validate an artificial intelligence (AI)-driven approach for ex vivo confocal microscopy (XVM) pathology.
  • To create intuitive XVM pathology images that mimic standard histopathology and generate automated tumor positivity maps.
  • To assess the diagnostic performance of AI-processed XVM for basal cell carcinoma detection.

Main Methods:

  • Developed a 4-stage XVM data pipeline including flattening, colorizing, enhancement, and automated diagnosis.
  • Utilized novel deterministic image processing algorithms for flattening and colorizing.
  • Employed AI algorithms for image enhancement and automated diagnosis, including image transformation and binary segmentation.
  • Calculated diagnostic sensitivity and specificity for basal cell carcinoma detection using processed XVM images.

Main Results:

  • The AI-driven pipeline successfully rendered XVM images that mimicked standard histopathology.
  • Automated tumor positivity maps were generated, aiding in margin status determination.
  • Diagnostic sensitivity and specificity for basal cell carcinoma detection were 88% and 91%, respectively.
  • The processing involved collapsing confocal stacks, colorizing transformations, and AI-based image analysis.

Conclusions:

  • AI-driven XVM pathology can produce intuitive images comparable to standard histopathology.
  • This technology shows feasibility in aiding margin status determination during micrographic surgery for skin cancer.
  • The developed pipeline offers a potential solution to overcome training barriers for XVM interpretation.