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

NetStart 2.0: prediction of eukaryotic translation initiation sites using a protein language model.

BMC bioinformatics·2025
Same author

Predicting the subcellular location of prokaryotic proteins with DeepLocPro.

Bioinformatics (Oxford, England)·2024
Same author

Physician Level Assessment of Hirsute Women and of Their Eligibility for Laser Treatment With Deep Learning.

Lasers in surgery and medicine·2024
Same author

DeepLoc 2.1: multi-label membrane protein type prediction using protein language models.

Nucleic acids research·2024
Same author

Can large language models reason about medical questions?

Patterns (New York, N.Y.)·2024
Same author

DiscoTope-3.0: improved B-cell epitope prediction using inverse folding latent representations.

Frontiers in immunology·2024

Related Experiment Video

Updated: Aug 11, 2025

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

2.4K

Explainable Image Quality Assessments in Teledermatological Photography.

Raluca Jalaboi1,2, Ole Winther1,3,4,5, Alfiia Galimzianova2

  • 1Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark.

Telemedicine Journal and E-Health : the Official Journal of the American Telemedicine Association
|February 3, 2023
PubMed
Summary
This summary is machine-generated.

Image quality is vital for teledermatology. ImageQX, an AI tool, assesses image quality and identifies issues like blur or bad lighting, improving remote consultations.

Keywords:
artificial intelligencedeep learningexplainabilityimage qualityteledermatologytelemedicine

More Related Videos

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus
05:39

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus

Published on: May 16, 2025

151
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

16.9K

Related Experiment Videos

Last Updated: Aug 11, 2025

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

2.4K
Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus
05:39

Dermoscopy Aids in the Diagnosis of Discoid Lupus Erythematosus

Published on: May 16, 2025

151
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

16.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Dermatology

Background:

  • Image quality significantly impacts teledermatology effectiveness, with up to 50% of patient-submitted images having quality issues.
  • Poor image quality prolongs diagnosis and treatment timelines in remote consultations.
  • A need exists for automated, deployable, and explainable image quality assessment methods in teledermatology.

Purpose of the Study:

  • To introduce ImageQX, a convolutional neural network (CNN) for automated image quality assessment in teledermatology.
  • To enable ImageQX to identify common causes of poor image quality, including framing, lighting, blur, resolution, and distance.
  • To develop an easily deployable and explainable AI solution to enhance teledermatology workflows.

Main Methods:

  • Developed ImageQX, a CNN trained on 26,635 photographs and validated on 9,874 photographs.
  • Images were annotated for quality and specific issues by up to 12 board-certified dermatologists.
  • Utilized photographs from a global mobile skin disease tracking application (2017-2019).

Main Results:

  • ImageQX achieved expert-level performance in image quality assessment (macro F1-score of 0.73 ± 0.01).
  • The model demonstrated comparable performance to dermatologists in identifying poor image quality explanations (F1-scores 0.37–0.70).
  • ImageQX is a compact 15 MB model, facilitating easy deployment on mobile devices.

Conclusions:

  • ImageQX offers dermatologists expert-level image quality detection and explanation capabilities.
  • Integration of ImageQX into teledermatology workflows can significantly improve efficiency and speed.
  • The AI tool's performance and deployability support better remote dermatological consultations.