PET Quantification-Preserving Registration for Longitudinal Whole-Body PSMA PET/CT

Fryderyk Kögl, Anna Reithmeir, Daniel M. Lang, Emily Chan, Rickmer Braren +1 more
10/15/2026
cs.CV

Official code: koegl/psmareg (0 stars, MIT, last commit 2026-09-23).

Abstract

We adapt the diffeomorphic coarse-to-fine LapIRN architecture for longitudinal whole-body PSMA PET/CT registration in the Learn2Reg 2026 PSMAReg challenge. The method combines affine pre-registration, multi-modal deformable registration, and test-time instance optimization. We further introduce PET biomarker preservation losses for metabolic tumor volume (MTV) and total lesion glycolysis (TLG), including Jacobian-based constraints, and a per-structure rigidity regularization for skeletal structures. The submitted configuration achieved 81.0% DSC and 6.17 mm HD95, with MTV and TLG errors of 3.3% and 3.3%, respectively, on our evaluation protocol. Code is available at https://github.com/koegl/psmareg.

View on arXivView PDF

Code Implementations(1)

koegl/psmaregOfficial100%
MIT
00PythonJun 12, 20263 weeks agoMIT

Similar Papers

Registration is a Representation Problem: Solving Whole-Body PET/CT Registration

81% match2026

Divide to Conquer: A Field Decomposition Approach for Multi-Organ Whole-Body CT Image Registration

79% match2025

MorphSeek: Fine-grained Latent Representation-Level Policy Optimization for Deformable Image Registration

79% match2025

GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration

79% match1 repo182023

SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformation

79% match1 repo352023

RegWSI: Whole Slide Image Registration using Combined Deep Feature- and Intensity-Based Methods: Winner of the ACROBAT 2023 Challenge

78% match2024

Cite this paper

@article{kgl2026quantificationpreserving,
  title  = {PET Quantification-Preserving Registration for Longitudinal Whole-Body PSMA PET/CT},
  author = {Fryderyk Kögl and Anna Reithmeir and Daniel M. Lang and Emily Chan and Rickmer Braren and Julia A. Schnabel},
  year   = {2026},
  eprint = {2610.21451},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2610.21451v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2610.21451.svg)](https://codeofpaper.com/paper/2610.21451)

Discussion