Hubless keypoint-based 3D deformable groupwise registration - Physics, Radiobiology, Medical Imaging, and Simulation (PRIMES) Access content directly
Journal Articles Medical Image Analysis Year : 2019

Hubless keypoint-based 3D deformable groupwise registration

Abstract

We present a novel deformable groupwise registration method, applied to large 3D image groups. Our approach extracts 3D SURF keypoints from images, computes matched pairs of keypoints and registers the group by minimizing pair distances in a hubless way i.e. without computing any central mean image. Using keypoints significantly reduces the problem complexity compared to voxel-based approaches, and enables us to provide an in-core global optimization, similar to the Bundle Adjustment for 3D reconstruction. As we aim at registering images of different patients, the matching step yields many outliers. Then we propose a new EM-weighting algorithm which efficiently discards outliers. Global optimization is carried out with a fast gradient descent algorithm. This allows our approach to robustly register large datasets. The result is a set of half transforms which link the volumes together and can be subsequently exploited for computational anatomy, landmark detection or image segmentation. We show experimental results on whole-body CT scans, with groups of up to 103 volumes. On a benchmark based on anatomical landmarks, our algorithm compares favorably with the star-groupwise voxel-based ANTs and NiftyReg approaches while being much faster. We also discuss the limitations of our approach for lower resolution images such as brain MRI.
Fichier principal
Vignette du fichier
S1361841518306625.pdf (5.99 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01977879 , version 1 (20-07-2022)

Licence

Attribution - NonCommercial

Identifiers

Cite

Rémi Agier, Sébastien Valette, Razmig Kéchichian, Laurent Fanton, Rémy Prost. Hubless keypoint-based 3D deformable groupwise registration. Medical Image Analysis, 2019, ⟨10.1016/j.media.2019.101564⟩. ⟨hal-01977879⟩
122 View
18 Download

Altmetric

Share

Gmail Facebook X LinkedIn More