GLIDE-Reg: Global-to-Local Deformable Registration Using Co-Optimized Foundation and Handcrafted Features

TL;DR

GLIDE-Reg introduces a novel deformable registration method combining global semantic features and local descriptors, achieving superior accuracy and robustness in medical imaging across multiple datasets and anatomical structures.

Contribution

It jointly optimizes a registration field and a learnable dimensionality reduction module to enhance robustness and generalizability in deformable registration tasks.

Findings

Achieves higher dice similarity coefficients than state-of-the-art methods.

Demonstrates improved target registration errors across datasets.

Shows robustness in challenging downstream tasks like nodule tracking.

Abstract

Deformable registration is crucial in medical imaging. Several existing applications include lesion tracking, probabilistic atlas generation, and treatment response evaluation. However, current methods often lack robustness and generalizability across two key factors: spatial resolution and differences in anatomical coverage. We jointly optimize a registration field and a learnable dimensionality reduction module so that compressed VFM embeddings remain registration-relevant, and fuse these global semantic cues with MIND local descriptors. GLIDE-Reg achieves average dice similarity coefficients (DSC) across 6 anatomical structures of 0.859, 0.862, and 0.901 in two public cohorts (Lung250M and NLST) and one institution cohort (UCLA5DCT), and outperforms the state-of-the-art DEEDS (0.834, 0.858, 0.900) with relative improvements of 3.0%, 0.5%, and 0.1%. For target registration errors, GLIDE-Reg achieves 1.58 mm on Lung250M landmarks (compared to 1.25 mm on corrField and 1.91 mm on DEEDS) and 1.11 mm on NLST nodule centers (compared to 1.11 mm on DEEDS). The substantiated performance on the nodule centers also demonstrates its robustness across challenging downstream tasks, such as nodule tracking, which is an essential prior step for early-stage lung cancer diagnosis.