An Accessible Solution for Deformable Image Registration Compared with Learning-Based Approaches
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on deformable image registration (DIR), which helps align medical images but is hard to solve because it needs to follow physical rules. They revisit an analytical method called pTVreg based on total variation and improve it by adding a way to automatically tune parameters using Bayesian optimization. Their new version performs better than many deep learning models on a lung image benchmark. This suggests traditional math-based methods can still be very effective compared to newer AI approaches in this task.
Deformable Image RegistrationTotal VariationBayesian OptimizationMedical Image AnalysisParametric MethodsLung ImagingDeep LearningPhysical ConstraintsImage AlignmentBenchmarking
Authors
Onur Ali Zeybekoglu, David Tilly, Orcun Goksel
Abstract
Deformable image registration (DIR) is a core problem in medical image analysis; but, unlike labeling decision problems such as classification and segmentation, registration is a problem class that involves stringent physical constraints. Although deep learning methods have made faster registration possible, the resulting models are often difficult to interpret compared to hand-crafted methods with explicit objectives and interpretable physical meaning. In this work, we show that an analytical method can still yield competitive and superior results to deep learning in a common deformable registration task. We study pTVreg as a parametric total variation based registration in that context. Observing its different implementations to perform at various degrees, we introduce here an accessible implementation of this method, together with a Bayesian optimization framework that automatically sets self-parameters for any DIR task from a set of sample examples. Experiments on Lung250M-4B show that our proposed implementation achieves state-of-the-art results in this benchmark, substantially superior to existing deep learning solutions and other pTVreg variants as baselines. The source code will be made publicly available at https://github.com/oazeybekoglu/ptvreg-python .