Multi-Dataset Diagnostic Utility of Clinical Visual Concepts in AI Systems for Dermatology
In this work, we introduce SkinLex, a harmonized dataset of 48 clinical morphological attributes across four public datasets (SkinCon, DermaCon-IN, MM-Skin, and PASSION) for a total of 20,411 records.
ProofPaper ↗
Key points
- The clinical integration of AI systems in digital dermatology relies heavily on human trust.
- Clinically interpretable visual concepts can act as intermediate representations enhancing trust and reliability.
- Supervised nine-partition classification of skin conditions shows that limiting features to specific visual groups, like shapes or colors alone, reduces diagnostic accuracy.
- Bootstrapped backward elimination reveals that the set of 48 visual concepts has some degree of redundancy for algorithmic nine-partition diagnosis on the examined dataset.
Sources (1)
- [1]Multi-Dataset Diagnostic Utility of Clinical Visual Concepts in AI Systems for DermatologyarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 10:17 AM
In this work, we introduce SkinLex, a harmonized dataset of 48 clinical morphological attributes across four public datasets (SkinCon, DermaCon-IN, MM-Skin, and PASSION) for a total of 20,411 records.
The clinical integration of AI systems in digital dermatology relies heavily on human trust.
Extractive summary: sentences quoted from the sources.