EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GLIMPSE: Generalized Locality for Scalable and Robust CT

AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmanic

IEEE Transactions on Medical Imaging · 2025

DOI: 10.1109/tmi.2025.3575071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von AmirEhsan Khorashadizadeh und 3 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Image Processing, Computer-Assisted, Neural Networks, Computer, Deep Learning. Die Arbeit nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council Starting.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has become the state-of-the-art approach to medical tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection, to a multiscale convolutional neural network (CNN) which computes the final reconstruction. Despite good results on in-distribution test data, this often results in overfitting certain large-scale structures and poor generalization on out-of-distribution (OOD) samples. Moreover, the memory and computational complexity of multiscale CNNs scale unfavorably with image resolution, making them impractical for application at realistic clinical resolutions. In this paper, we introduce Glimpse, a local coordinate-based neural network for computed tomography which reconstructs a pixel value by processing only the measurements associated with the neighborhood of the pixel. Glimpse significantly outperforms successful CNNs on OOD samples, while achieving comparable or better performance on in-distribution test data and maintaining a memory footprint almost independent of image resolution; 5GB memory suffices to train on $1024\times 1024$ images which is orders of magnitude less than CNNs. Glimpse is fully differentiable and can be used plug-and-play in arbitrary deep learning architectures, enabling feats such as correcting miscalibrated projection orientations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, X-Ray ComputedImage Processing, Computer-AssistedNeural Networks, ComputerDeep LearningHumansAlgorithmsPhantoms, Imaging

Förderung

  • European Research Council Starting

Zitieren

APA

Khorashadizadeh, A., Debarnot, V., Liu, T., & Dokmanic, I. (2025). GLIMPSE: Generalized Locality for Scalable and Robust CT. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3575071

Vancouver

Khorashadizadeh A, Debarnot V, Liu T, Dokmanic I. GLIMPSE: Generalized Locality for Scalable and Robust CT. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3575071

BibTeX
@article{Khorashadizadeh2025,
  author = {Khorashadizadeh, AmirEhsan and Debarnot, Valentin and Liu, Tianlin and Dokmanic, Ivan},
  title = {GLIMPSE: Generalized Locality for Scalable and Robust CT},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  doi = {10.1109/tmi.2025.3575071}
}
Kostenlos starten →