EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Advancing Dermatological Diagnostics: Interpretable AI for Enhanced Skin Lesion Classification

Carlo Metta iD, Andrea Beretta, Riccardo Guidotti, Yuan Yin, Patrick Gallinari, Salvatore Rinzivillo iD, Fosca Giannotti

Diagnostics · 02.04.2024 · 14 (7) · 753

DOI: 10.3390/diagnostics14070753 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 02.04.2024. Verfasst von Carlo Metta und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information Science and Technologies (ISTI-CNR), 56124 Pisa, Italy. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SoBigData++, HumanE AI Net, CREXDATA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A crucial challenge in critical settings like medical diagnosis is making deep learning models used in decision-making systems interpretable. Efforts in Explainable Artificial Intelligence (XAI) are underway to address this challenge. Yet, many XAI methods are evaluated on broad classifiers and fail to address complex, real-world issues, such as medical diagnosis. In our study, we focus on enhancing user trust and confidence in automated AI decision-making systems, particularly for diagnosing skin lesions, by tailoring an XAI method to explain an AI model’s ability to identify various skin lesion types. We generate explanations using synthetic images of skin lesions as examples and counterexamples, offering a method for practitioners to pinpoint the critical features influencing the classification outcome. A validation survey involving domain experts, novices, and laypersons has demonstrated that explanations increase trust and confidence in the automated decision system. Furthermore, our exploration of the model’s latent space reveals clear separations among the most common skin lesion classes, a distinction that likely arises from the unique characteristics of each class and could assist in correcting frequent misdiagnoses by human professionals.

Schlagwörter

Stichwörter der Autor:innen

AI in healthcareExplainable Artificial Intelligenceadversial autoecnodersdermoscopic imagesskin image analysis

Autor:innen und Institutionen

  • Institute of Information Science and Technologies (ISTI-CNR), 56124 Pisa, Italy.
  • Department of Computer Science, Universitá di Pisa, 56124 Pisa, Italy.
  • Laboratoire d'Informatique de Paris 6, Sorbonne Université, 75005 Paris, Italy.
  • Faculty of Sciences, Scuola Normale Superiore di Pisa, 56126 Paris, Italy.

ORCID-Profile: Carlo Metta, Salvatore Rinzivillo

Förderung

  • SoBigData++
  • HumanE AI Net
  • CREXDATA
  • ERC-2018-ADG XAI
  • TAILOR
  • FAIR
  • XAI
  • NextGenerationEU programme under the funding schemes PNRR-PE-AI scheme (M4C2, investment 1.3, line on AI) FAIR (Future Artificial Intelligence Research)

Zitieren

APA

Metta, C., Beretta, A., Guidotti, R., Yin, Y., Gallinari, P., Rinzivillo, S., & Giannotti, F. (2024). Advancing Dermatological Diagnostics: Interpretable AI for Enhanced Skin Lesion Classification. Diagnostics, 14(7), 753. https://doi.org/10.3390/diagnostics14070753

Vancouver

Metta C, Beretta A, Guidotti R, Yin Y, Gallinari P, Rinzivillo S, et al. Advancing Dermatological Diagnostics: Interpretable AI for Enhanced Skin Lesion Classification. Diagnostics. 2024;14(7):753. doi:10.3390/diagnostics14070753

BibTeX
@article{Metta2024,
  author = {Metta, Carlo and Beretta, Andrea and Guidotti, Riccardo and Yin, Yuan and Gallinari, Patrick and Rinzivillo, Salvatore and Giannotti, Fosca},
  title = {Advancing Dermatological Diagnostics: Interpretable AI for Enhanced Skin Lesion Classification},
  journal = {Diagnostics},
  year = {2024},
  volume = {14},
  number = {7},
  pages = {753},
  doi = {10.3390/diagnostics14070753}
}
Kostenlos starten →