EUVIMEDEUVIMED entdecken
Crossref

CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs

Qiang Ma, Liu Li, Emma C Robinson, Bernhard Kainz, Daniel Rueckert, Amir Alansary

IEEE Transactions on Medical Imaging · 2023-02 · 42 (2) · 430-443

DOI: 10.1109/tmi.2022.3206221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023-02. Verfasst von Qiang Ma und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, White Matter. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: President’s Ph.D. Scholarships at Imperial College London.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present CortexODE, a deep learning framework for cortical surface reconstruction. CortexODE leverages neural ordinary differential equations (ODEs) to deform an input surface into a target shape by learning a diffeomorphic flow. The trajectories of the points on the surface are modeled as ODEs, where the derivatives of their coordinates are parameterized via a learnable Lipschitz-continuous deformation network. This provides theoretical guarantees for the prevention of self-intersections. CortexODE can be integrated to an automatic learning-based pipeline, which reconstructs cortical surfaces efficiently in less than 5 seconds. The pipeline utilizes a 3D U-Net to predict a white matter segmentation from brain Magnetic Resonance Imaging (MRI) scans, and further generates a signed distance function that represents an initial surface. Fast topology correction is introduced to guarantee homeomorphism to a sphere. Following the isosurface extraction step, two CortexODE models are trained to deform the initial surface to white matter and pial surfaces respectively. The proposed pipeline is evaluated on large-scale neuroimage datasets in various age groups including neonates (25-45 weeks), young adults (22-36 years) and elderly subjects (55-90 years). Our experiments demonstrate that the CortexODE-based pipeline can achieve less than 0.2mm average geometric error while being orders of magnitude faster compared to conventional processing pipelines.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedWhite MatterInfant, NewbornYoung AdultHumansAgedInfantBrainMagnetic Resonance Imaging

Förderung

  • President’s Ph.D. Scholarships at Imperial College London

Zitieren

APA

Ma, Q., Li, L., Robinson, E. C., Kainz, B., Rueckert, D., & Alansary, A. (2023). CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs. IEEE Transactions on Medical Imaging, 42(2), 430-443. https://doi.org/10.1109/tmi.2022.3206221

Vancouver

Ma Q, Li L, Robinson EC, Kainz B, Rueckert D, Alansary A. CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs. IEEE Transactions on Medical Imaging. 2023;42(2):430-443. doi:10.1109/tmi.2022.3206221

BibTeX
@article{Ma2023,
  author = {Ma, Qiang and Li, Liu and Robinson, Emma C and Kainz, Bernhard and Rueckert, Daniel and Alansary, Amir},
  title = {CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2023},
  volume = {42},
  number = {2},
  pages = {430--443},
  doi = {10.1109/tmi.2022.3206221}
}
Kostenlos starten →