What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

To develop a photonumeric scale and CNN for automated assessment of photodamage using 3D total body photography.

December 10, 2025British Journal of Dermatology

Automated classification of site-specific cutaneous photodamage using a convolutional neural network and 3D total body photography

View Full Paper

Ask AI

Bookmark

Authors

SKSam KahlerThe University of Queensland SYSiyuan YanAustralian Regenerative Medicine Institute AMAdam MothershawThe University of Queensland

Discussion

Member takes

Implication

Automated classification of melanoma risk in individuals using artificial intelligence and 3D total body photography, indicating improved assessment accuracy.

Key Points

To develop a photonumeric scale and CNN for automated assessment of photodamage using 3D total body photography.
Developed a photonumeric scale validated against inter-rater reproducibility
Annotated 24,720 image tiles from high-risk and population-risk individuals
Trained a CNN using a multi-task learning strategy to enhance performance
Achieved substantial agreement between laypeople and dermatology students (κ=0.77-0.83)
MTL-CNN improved ROC-AUC from 0.91 to 0.96 (p<0.01)
Class-specific accuracy improved for mild, moderate, and severe photodamage categories

Cite This Study

Kahler et al. (2025) studied this question.

synapsesocial.com/papers/69401d412d562116f28f84a3 https://doi.org/10.1093/bjd/ljaf516

View Full Paper

Ask AI

Bookmark

December 10, 2025British Journal of Dermatology

Automated classification of site-specific cutaneous photodamage using a convolutional neural network and 3D total body photography

View Full Paper

Ask AI

Bookmark

Authors

SKSam KahlerThe University of Queensland SYSiyuan YanAustralian Regenerative Medicine Institute AMAdam MothershawThe University of Queensland

Discussion

Member takes

Implication

Automated classification of melanoma risk in individuals using artificial intelligence and 3D total body photography, indicating improved assessment accuracy.

Key Points

To develop a photonumeric scale and CNN for automated assessment of photodamage using 3D total body photography.
Developed a photonumeric scale validated against inter-rater reproducibility
Annotated 24,720 image tiles from high-risk and population-risk individuals
Trained a CNN using a multi-task learning strategy to enhance performance
Achieved substantial agreement between laypeople and dermatology students (κ=0.77-0.83)
MTL-CNN improved ROC-AUC from 0.91 to 0.96 (p<0.01)
Class-specific accuracy improved for mild, moderate, and severe photodamage categories

Cite This Study

Kahler et al. (2025) studied this question.

synapsesocial.com/papers/69401d412d562116f28f84a3 https://doi.org/10.1093/bjd/ljaf516

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark