EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Exploring Differential Diagnosis-Based Explainable AI: A Case Study in Melanoma Detection

Bjorn Buijing, Danielle Sent

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250389 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Bjorn Buijing und 1 weiteren Autor:innen. Beteiligte Einrichtung: HU University of Applied Sciences Utrecht, Research Group Artificial Intelligence, Utrecht, The Netherlands. Hauptthemen laut MEDLINE: Melanoma, Artificial Intelligence, Skin Neoplasms, Diagnosis, Computer-Assisted. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Melanoma is a significant global health concern, with rising incidence rates and high mortality when diagnosed late. Artificial Intelligence (AI) models, especially models using deep learning techniques, have shown promising results in melanoma detection. However, the complexity of these models often leads to a lack of transparency, making it difficult for clinicians to understand and trust AI-based diagnoses. This paper presents a novel Explainable AI (XAI) method that aligns with differential diagnosis techniques commonly used in clinical settings, providing more comprehensive explanations. The novel XAI method and four commonly used XAI methods were evaluated with intended users with respect to perceived useability and trust. We found that the new method was considered more useful than other methods tested. Notably, the widely used saliency mapping technique received the lowest ratings, performing even worse than providing no explanation at all.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MelanomaArtificial IntelligenceSkin NeoplasmsDiagnosis, Computer-AssistedHumansDiagnosis, Differential

Stichwörter der Autor:innen

Explainable AIMelanoma detectiondifferential diagnosishuman-centred evaluationimaging

Autor:innen und Institutionen

  • HU University of Applied Sciences Utrecht, Research Group Artificial Intelligence, Utrecht, The Netherlands.
  • Jheronimus Academy of Data Science, Eindhoven University of Technology, Tilburg University, 's-Hertogenbosch, The Netherlands.

Zitieren

APA

Buijing, B., & Sent, D. (2025). Exploring Differential Diagnosis-Based Explainable AI: A Case Study in Melanoma Detection. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250389

Vancouver

Buijing B, Sent D. Exploring Differential Diagnosis-Based Explainable AI: A Case Study in Melanoma Detection. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250389

BibTeX
@article{Buijing2025,
  author = {Buijing, Bjorn and Sent, Danielle},
  title = {Exploring Differential Diagnosis-Based Explainable AI: A Case Study in Melanoma Detection},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250389}
}
Kostenlos starten →