EUVIMEDEUVIMED entdecken
Crossref

Random Convolutions for Domain Generalization of Deep Learning–based Medical Image Segmentation Models

Daniel Scholz iD, Ayhan Can Erdur iD, Jan C Peeken iD, Aswathi Varma iD, Robert Graf iD, Jan S Kirschke iD, Daniel Rueckert iD, Benedikt Wiestler iD

Radiology: Artificial Intelligence · 2026

DOI: 10.1148/ryai.240502 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology: Artificial Intelligence, 2026. Verfasst von Daniel Scholz und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, Technical University of Munich, Neuro-Kopf-Zentrum, Ismaninger …. Hauptthemen laut MEDLINE: Deep Learning, Magnetic Resonance Imaging, Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: DFG.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Domain shift hindered clinical translation of deep learning segmentation models in medical imaging; random convolutions improved segmentation generalization by compelling models to prioritize shape over texture features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMagnetic Resonance ImagingTomography, X-Ray ComputedImage Processing, Computer-AssistedHumansRetrospective StudiesBrainAbdomen

Stichwörter der Autor:innen

Abdomen/GICTExperimental InvestigationsMR-ImagingSegmentationSupervised Learning

Autor:innen und Institutionen

  • Institute for Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, Technical University of Munich, Neuro-Kopf-Zentrum, Ismaninger Str 22, 81675 Munich, Germany.
  • Institute for Artificial Intelligence and Informatics in Medicine, Technical University of Munich, Munich, Germany.
  • Department of Radiation Oncology, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany.

ORCID-Profile: Daniel Scholz, Ayhan Can Erdur, Jan C Peeken, Aswathi Varma, Robert Graf, Jan S Kirschke, Daniel Rueckert, Benedikt Wiestler

Förderung

  • DFG

Zitieren

APA

Scholz, D., Erdur, A. C., Peeken, J. C., Varma, A., Graf, R., Kirschke, J. S., Rueckert, D., & Wiestler, B. (2026). Random Convolutions for Domain Generalization of Deep Learning–based Medical Image Segmentation Models. Radiology: Artificial Intelligence. https://doi.org/10.1148/ryai.240502

Vancouver

Scholz D, Erdur AC, Peeken JC, Varma A, Graf R, Kirschke JS, et al. Random Convolutions for Domain Generalization of Deep Learning–based Medical Image Segmentation Models. Radiology: Artificial Intelligence. 2026. doi:10.1148/ryai.240502

BibTeX
@article{Scholz2026,
  author = {Scholz, Daniel and Erdur, Ayhan Can and Peeken, Jan C and Varma, Aswathi and Graf, Robert and Kirschke, Jan S and Rueckert, Daniel and Wiestler, Benedikt},
  title = {Random Convolutions for Domain Generalization of Deep Learning–based Medical Image Segmentation Models},
  journal = {Radiology: Artificial Intelligence},
  year = {2026},
  doi = {10.1148/ryai.240502}
}
Kostenlos starten →