EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable multimodal classification for age-related macular degeneration diagnosis

Carla Vairetti iD, Sebastián Maldonado, Loreto Cuitino, Cristhian A Urzua

PLOS ONE · 11.11.2024 · 19 (11) · e0311811

DOI: 10.1371/journal.pone.0311811 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 11.11.2024. Verfasst von Carla Vairetti und 3 weiteren Autor:innen. Beteiligte Einrichtung: Facultad de Ingeniería y Ciencias Aplicadas, Santiago, Chile. Hauptthemen laut MEDLINE: Macular Degeneration, Tomography, Optical Coherence. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Nacional de Investigación y Desarrollo, FONDECYT-Chile.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable Artificial Intelligence (XAI) is an emerging machine learning field that has been successful in medical image analysis. Interpretable approaches are able to “unbox” the black-box decisions made by AI systems, aiding medical doctors to justify their diagnostics better. In this paper, we analyze the performance of three different XAI strategies for medical image analysis in ophthalmology. We consider a multimodal deep learning model that combines optical coherence tomography (OCT) and infrared reflectance (IR) imaging for the diagnosis of age-related macular degeneration (AMD). The classification model is able to achieve an accuracy of 0.94, performing better than other unimodal alternatives. We analyze the XAI methods in terms of their ability to identify retinal damage and ease of interpretation, concluding that grad-CAM and guided grad-CAM can be combined to have both a coarse visual justification and a fine-grained analysis of the retinal layers. We provide important insights and recommendations for practitioners on how to design automated and explainable screening tests based on the combination of two image sources.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Macular DegenerationTomography, Optical CoherenceHumansArtificial IntelligenceDeep LearningRetinaMultimodal ImagingImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Facultad de Ingeniería y Ciencias Aplicadas, Santiago, Chile.
  • Instituto Sistemas Complejos de Ingeniería (ISCI), Santiago, Chile.
  • Department of Management Control and Information Systems, School of Economics and Business, University of Chile, Santiago, Chile.
  • Laboratory of Ocular and Systemic Autoimmune Diseases, Faculty of Medicine, University of Chile, Santiago, Chile.
  • Servicio de Oftalmología, Hospital Clínico Universidad de Chile, Santiago, Chile.
  • Faculty of Medicine, Clinica Alemana-Universidad del Desarrollo, Santiago, Chile.

ORCID-Profile: Carla Vairetti

Förderung

  • Agencia Nacional de Investigación y Desarrollo
  • FONDECYT-Chile

Zitieren

APA

Vairetti, C., Maldonado, S., Cuitino, L., & Urzua, C. A. (2024). Interpretable multimodal classification for age-related macular degeneration diagnosis. PLOS ONE, 19(11), e0311811. https://doi.org/10.1371/journal.pone.0311811

Vancouver

Vairetti C, Maldonado S, Cuitino L, Urzua CA. Interpretable multimodal classification for age-related macular degeneration diagnosis. PLOS ONE. 2024;19(11):e0311811. doi:10.1371/journal.pone.0311811

BibTeX
@article{Vairetti2024,
  author = {Vairetti, Carla and Maldonado, Sebastián and Cuitino, Loreto and Urzua, Cristhian A},
  title = {Interpretable multimodal classification for age-related macular degeneration diagnosis},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {11},
  pages = {e0311811},
  doi = {10.1371/journal.pone.0311811}
}
Kostenlos starten →