cs.CVNov 19, 2026

AdaptReg: Skip-level FiLM Adapter for Task-Specific Adaptation of a Frozen Registration Foundation Model

Authors: Shuyue Shi, Rong Yuan, Lin Tian

Organizations: Shanghai Medical Image Insights Intelligent Technology Co., Ltd. · Hong Kong Baptist University

Abstract

Longitudinal PSMA-PET/CT registration is a key step in assessing treatment response in prostate cancer, and it requires more than generic alignment accuracy: the deformation must preserve lesion volume, so that measured changes in metabolic tumor volume (MTV) and total lesion glycolysis (TLG) reflect treatment response rather than registration artifacts. We propose AdaptReg, which adapts a frozen registration foundation model to such task-specific requirements through a lightweight trainable adapter branch with identity-preserving initialization. Keeping uniGradICON fully frozen, we apply FiLM-style per-voxel affine modulation (γγ, ββ) to its decoder skip connections; the modulation is generated from anatomical semantic features of a frozen TotalSegmentator encoder and supervised by a lesion volume-preservation loss. On the official Codabench validation set (20 pairs), AdaptReg achieves DSC 0.7585, HD95 6.33 mm, MTV/TLG errors of 1.68%/2.11%, and 0.0022% non-diffeomorphic voxels, improving on the uniGradICON + instance optimization baseline by +0.05+0.05 DSC and reducing the MTV/TLG errors by 70.9%/67.7%. On the hidden official test set (160 pairs), AdaptReg achieves CT DSC 0.816, PET DSC 0.598, and MTV/TLG errors of 4.02%/3.46%, ranking fourth among 16 teams in the final PSMAReg evaluation. Code: https://github.com/shishuyue/AdaptReg

Figures & tables

Explore similar work

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

    Oct 15, 2026Fryderyk Kögl, Anna Reithmeir, Daniel M. Lang +3Medical Image RegistrationDeformable Image Registration

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

    Oct 13, 2026Neel Dey, Adrian V. DalcaMedical Image RegistrationDeformable Image Registration

  3. FlexiMIND: Combined Pretrained Vision Features and Local Structure for Training-Free Deformable Medical Image Registration

    Oct 25, 2026Mojtaba Safari, Mingzhe Hu, Shansong Wang +6Medical Image RegistrationDeformable Image Registration