EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Interpretable Similarity of Synthetic Image Utility

Panagiota Gatoula, George Dimas, Dimitris K Iakovidis

IEEE Transactions on Medical Imaging · 2026

DOI: 10.1109/tmi.2026.3679527 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026. Verfasst von Panagiota Gatoula und 2 weiteren Autor:innen. Hauptthemen laut MEDLINE: Deep Learning, Decision Support Systems, Clinical, Diagnostic Imaging, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Innovative Health Initiative Joint Undertaking.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synthetic medical image data can unlock the potential of deep learning (DL)-based clinical decision support (CDS) systems through the creation of large scale, privacy-preserving, training sets. Despite the significant progress in this field, there is still a largely unanswered research question: "How can we quantitatively assess the similarity of a synthetically generated set of images with a set of real images in a given application domain". Today, answers to this question are mainly provided via user evaluation studies, inception-based measures, and the classification performance achieved on synthetic images. This paper proposes a novel measure to assess the similarity between synthetically generated and real sets of images, in terms of their utility for the development of DL-based CDS systems. Inspired by generalized neural additive models, and unlike inception-based measures, the proposed measure is interpretable (Interpretable Utility Similarity, IUS), explaining why a synthetic dataset could be more useful than another one in the context of a CDS system based on clinically relevant image features. The experimental results on publicly available benchmark datasets from various color medical imaging modalities including endoscopic, dermoscopic and fundus imaging, indicate that selecting synthetic images of high utility similarity using IUS can result in relative improvements of up to 54.6% in terms of classification performance. The generality of IUS for synthetic data assessment is demonstrated also for grayscale X-ray and ultrasound imaging modalities. IUS implementation is available at https://github.com/innoisys/ius.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningDecision Support Systems, ClinicalDiagnostic ImagingImage Interpretation, Computer-AssistedHumansAlgorithmsDatabases, Factual

Förderung

  • Innovative Health Initiative Joint Undertaking

Zitieren

APA

Gatoula, P., Dimas, G., & Iakovidis, D. K. (2026). Interpretable Similarity of Synthetic Image Utility. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2026.3679527

Vancouver

Gatoula P, Dimas G, Iakovidis DK. Interpretable Similarity of Synthetic Image Utility. IEEE Transactions on Medical Imaging. 2026. doi:10.1109/tmi.2026.3679527

BibTeX
@article{Gatoula2026,
  author = {Gatoula, Panagiota and Dimas, George and Iakovidis, Dimitris K},
  title = {Interpretable Similarity of Synthetic Image Utility},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2026},
  doi = {10.1109/tmi.2026.3679527}
}
Kostenlos starten →