Concordance in Basal Cell Carcinoma Diagnosis. Building a Proper Standard Reference to Train Artificial Intelligence Tools
Skin Research and Technology · 2025
DOI: 10.1111/srt.70277 ↗Kurz gefasst
Fachartikel in der Zeitschrift Skin Research and Technology, 2025. Verfasst von Francisca Silva-Clavería und 5 weiteren Autor:innen. Beteiligte Einrichtung: Dermatology Service, Hospital Universitario Virgen Macarena, Seville, Spain. Hauptthemen laut MEDLINE: Basal Cell Carcinoma, Skin Neoplasms, Artificial Intelligence, Dermoscopy. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Regional Development Fund, Ministerio de ciencia e innovación, Gobierno de España, Consejería de Conocimiento, Investigación y Universidad. Junta de Andalucía.
Abstract (Originalsprache)
Background
Reliable labels are essential when training Artificial Intelligence (AI) tools. Whereas some diseases allow biopsy‐based labeling, others rely on subjective criteria. For the diagnosis of basal cell carcinoma (BCC), dermatologists detect certain dermoscopic criteria, whose presence (or absence) serves as the basis for determining a diagnosis of BCC. Therefore, an AI tool assisting in BCC diagnosis should provide such criteria to explain its output. Materials and Methods This study analyzes the agreement among four dermatologists in detecting dermoscopic criteria and compares the performance of an AI model trained with labels from a single dermatologist versus a consensus‐based standard. A total of1230 dermoscopic images, collected in around 60 primary health centers, sent via teledermatology, and diagnosed by four dermatologists, were used to train an AI tool. They were randomly selected from the teledermatology platform (2019–2021). Subsequently, 204 new images were used to test the AI tool prospectively. A standard reference (SR) was built using Expectation Maximization on the four diagnoses. The performance of the AI tool trained using the reference standard of one dermatologist versus the reference standard statistically inferred from the consensus of four dermatologists was analyzed using McNemar's test and Hamming distance.
Results
Agreement among dermatologists was high for BCC versus non‐BCC (Kappa = 0.9079; PPV = 0.9670), but lower for specific criteria. Statistical differences were found in the performance of AI models trained with individual and consensus labels.
Conclusion
Deriving an SR from multiple expert opinions mitigates individual bias and enhances AI interpretability, key for its clinical adoption.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Dermatology Service, Hospital Universitario Virgen Macarena, Seville, Spain.
- Department of Signal Theory and Communications, Escuela Técnica Superior De Ingeniería, Universidad de Sevilla, Seville, Spain.
- Quironsalud Hospitales Infanta Luisa y Sagrado Corazón, Seville, Spain.
Förderung
- European Regional Development Fund
- Ministerio de ciencia e innovación, Gobierno de España
- Consejería de Conocimiento, Investigación y Universidad. Junta de Andalucía
Zitieren
APA
Silva-Clavería, F., Serrano, C., Matas, I., Serrano, A., Toledo-Pastrana, T., & Acha, B. (2025). Concordance in Basal Cell Carcinoma Diagnosis. Building a Proper Standard Reference to Train Artificial Intelligence Tools. Skin Research and Technology. https://doi.org/10.1111/srt.70277
Vancouver
Silva-Clavería F, Serrano C, Matas I, Serrano A, Toledo-Pastrana T, Acha B. Concordance in Basal Cell Carcinoma Diagnosis. Building a Proper Standard Reference to Train Artificial Intelligence Tools. Skin Research and Technology. 2025. doi:10.1111/srt.70277
BibTeX
@article{SilvaClavera2025,
author = {Silva-Clavería, Francisca and Serrano, Carmen and Matas, Iván and Serrano, Amalia and Toledo-Pastrana, Tomás and Acha, Begoña},
title = {Concordance in Basal Cell Carcinoma Diagnosis. Building a Proper Standard Reference to Train Artificial Intelligence Tools},
journal = {Skin Research and Technology},
year = {2025},
doi = {10.1111/srt.70277}
}
EUVIMED