English

Deep learning-based group-wise registration for longitudinal MRI analysis in glioma

Image and Video Processing 2023-06-21 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Glioma growth may be quantified with longitudinal image registration. However, the large mass-effects and tissue changes across images pose an added challenge. Here, we propose a longitudinal, learning-based, and groupwise registration method for the accurate and unbiased registration of glioma MRI. We evaluate on a dataset from the Glioma Longitudinal AnalySiS consortium and compare it to classical registration methods. We achieve comparable Dice coefficients, with more detailed registrations, while significantly reducing the runtime to under a minute. The proposed methods may serve as an alternative to classical toolboxes, to provide further insight into glioma growth.

Keywords

Cite

@article{arxiv.2306.10611,
  title  = {Deep learning-based group-wise registration for longitudinal MRI analysis in glioma},
  author = {Claudia Chinea Hammecher and Karin van Garderen and Marion Smits and Pieter Wesseling and Bart Westerman and Pim French and Mathilde Kouwenhoven and Roel Verhaak and Frans Vos and Esther Bron and Bo Li},
  journal= {arXiv preprint arXiv:2306.10611},
  year   = {2023}
}

Comments

Digital poster presented at the annual meeting of the International Society for Magnetic Resonance in Medicine (ISMRM) 2023. A 6 minute video about this work is available for browsing by the conference website (Program number: 4361)

R2 v1 2026-06-28T11:08:19.283Z