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

A multi-epitope pan-betacoronavirus vaccine construct predicted to induce broad-spectrum and durable immune responses: an immunoinformatics approach.

Frontiers in bioinformaticsΒ·2026
Same author

Synthesis and characterization of natural biocomposite scaffold for bone repair: A study of gelatin-hydroxyapatite from Aceh-sourced bovine bone.

Dental materials journalΒ·2026
Same author

Enhanced Magnesium Ion Sensing Using Polyurethane Membranes Modified with ΔΈ-Carrageenan and D2EHPA: A Potentiometric Approach.

BiosensorsΒ·2026
Same author

Network Pharmacology-Based Identification of Key Metabolites from Immunized <i>Rhynchophorus</i> Larvae as Therapeutic Agents Against Antibiotic-Resistant <i>Neisseria gonorrhoea</i>.

Pakistan journal of biological sciences : PJBSΒ·2025
Same author

Mechanistic insights into the anticancer, anti-inflammatory, and antioxidant effects of yellowfin tuna collagen peptides using network pharmacology.

Narra JΒ·2025
Same author

Molecular insights into atopic dermatitis treatment: investigating bioactive compounds in Aceh's traditional fermented coconut oil.

Journal of biomolecular structure & dynamicsΒ·2025

Related Experiment Video

Updated: Jun 2, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

947

Psoriasis severity assessment: Optimizing diagnostic models with deep learning.

Aga Maulana1,2, Teuku R Noviandy1, Rivansyah Suhendra3

  • 1Department of Informatics, Faculty of Mathematics and Natural Sciences, Universitas Syiah Kuala, Banda Aceh, Indonesia.

Narra J
|January 16, 2025
PubMed
Summary

Deep learning models can accurately classify psoriasis severity. ResNet50 achieved 92.50% accuracy, offering potential for objective psoriasis assessment and improved treatment planning.

Keywords:
PASIdeep learningdiagnostic modelspsoriasisskin disease classification

More Related Videos

Author Spotlight: Self-Assessment Protocol for Predicting Psoriatic Arthritis in Psoriasis Patients
02:28

Author Spotlight: Self-Assessment Protocol for Predicting Psoriatic Arthritis in Psoriasis Patients

Published on: March 1, 2024

334
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K

Related Experiment Videos

Last Updated: Jun 2, 2025

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

947
Author Spotlight: Self-Assessment Protocol for Predicting Psoriatic Arthritis in Psoriasis Patients
02:28

Author Spotlight: Self-Assessment Protocol for Predicting Psoriatic Arthritis in Psoriasis Patients

Published on: March 1, 2024

334
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K

Area of Science:

  • Dermatology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Psoriasis severity assessment is challenging due to subtle visual differences.
  • Accurate classification is crucial for effective treatment planning.

Purpose of the Study:

  • To evaluate deep learning models for automated psoriasis severity classification.
  • To identify the optimal deep convolutional neural network (DCNN) for this task.

Main Methods:

  • A dataset of 1,546 psoriasis images was pre-processed and categorized into four severity levels (none, mild, moderate, severe).
  • Five DCNNs (ResNet50, VGGNet19, MobileNetV3, MnasNet, EfficientNetB0) were trained and validated.
  • Performance metrics included accuracy, precision, sensitivity, specificity, and F1-score, with statistical tests for comparison.

Main Results:

  • ResNet50 demonstrated superior performance with 92.50% accuracy.
  • ResNet50 achieved high precision (93.10%), sensitivity (92.50%), specificity (97.37%), and F1-score (92.68%).

Conclusions:

  • ResNet50 shows significant potential for consistent and objective psoriasis severity assessment.
  • This automated approach could assist dermatologists in diagnosis and treatment planning.
  • Further clinical validation is recommended for widespread adoption.