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 Experiment Videos

Automated assessment of skin histological tissue structures by artificial intelligence in cutaneous melanoma.

Thamila Kerkour1, Loes Hollestein1, Alex Nigg2

  • 1Department of Dermatology, Erasmus MC, Rotterdam, the Netherlands.

Pathology, Research and Practice
|March 30, 2025
PubMed
Summary
This summary is machine-generated.

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

Evaluation of Lentigo Maligna With Additional Immunohistochemical Staining on Frozen Sections With PRAME, Melan-A, and SOX10.

Dermatologic surgery : official publication for American Society for Dermatologic Surgery [et al.]·2026
Same author

Weighted single-step GWAS identified candidate genes associated with semen traits in Rhode Island Red chickens.

Poultry science·2026
Same author

Assessing Intraoperative Tumor-to-Background Ratios Across Different Subsites of the Oral Cavity Using an Integrin-Specific Fluorescent Tracer.

Cancers·2026
Same author

Pulmonary Neuroendocrine Tumor Artificial Intelligence-Assisted Prediction of Postoperative Recurrence From Tumor Biopsy Specimens.

Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc·2026
Same author

Expanding histopathological assessment may provide limited prognostic value for metastatic cutaneous squamous cell carcinoma: insights from two nationwide nested case-control studies.

The British journal of dermatology·2026
Same author

The SALV-Dataset Registry: An Expertly Curated Digital Clinicopathological Dataset for Salivary Gland Tumor Research and AI-Assisted Diagnostic Tools.

Head and neck pathology·2026

This study developed an AI framework to automatically segment melanoma tissue structures, improving analysis of key features for potential melanoma staging refinement. The AI achieved high accuracy and F1-scores, validated by dermatopathologists.

Area of Science:

  • Digital pathology
  • Artificial intelligence in oncology
  • Histopathology image analysis

Background:

  • Melanoma prognostic features like mitosis are excluded from staging due to variability and time constraints.
  • Existing AI algorithms for melanoma are limited in scope and clinical utility.
  • Digital pathology and AI offer potential solutions for objective histopathological analysis.

Purpose of the Study:

  • To develop and validate an automated AI-driven segmentation framework for multiple histological tissue structures in cutaneous melanoma.
  • To create an AI tool that overcomes limitations of manual analysis and existing algorithms.
  • To enhance the identification and analysis of histopathological features in melanoma.

Main Methods:

  • Utilized 157 melanoma whole slide images for training U-Net and DeepLab3+ classifiers on the Oncotopix® platform.
Keywords:
Automated segmentationCutaneous melanomaHistopathologySkin

Related Experiment Videos

  • Developed seven AI applications for progressive automated detection of tissue structures, including tumor microenvironment and mitosis.
  • Validated model performance using accuracy and F1-score on independent datasets and through dermatopathologist review of 442 images.

    • Main Results:

    • Seven AI applications achieved >92% accuracy and >80% F1-score, with ulceration detection at 75% F1-score.
    • The AI successfully segmented whole tissue, tumor microenvironment, hair follicles, sebaceous glands, epidermis, melanoma cells, and mitosis.
    • Dermatopathologist review confirmed high accuracy, with 92% of 442 images showing correct segmentations.

    Conclusions:

    • The developed AI framework demonstrates high performance in analyzing complex histological features.
    • Automated segmentation of time-consuming features enhances large-scale dataset analysis.
    • This tool has the potential to refine melanoma staging by providing objective histopathological insights.