Ideal Registration? Segmentation is All You Need
This work solves the problem of improving registration accuracy for medical imaging applications, such as cardiac, abdominal, and lung images, by transforming it into a segmentation task, representing a novel method for a known bottleneck.
The paper tackled the problem of image registration by addressing the limitations of globally uniform smoothness constraints in handling regionally varying anatomical deformations, proposing SegReg, a segmentation-driven framework that achieved near-perfect structural alignment (98.23% Dice on critical anatomies) and outperformed existing methods by 2-12% across clinical scenarios.
Deep learning has revolutionized image registration by its ability to handle diverse tasks while achieving significant speed advantages over conventional approaches. Current approaches, however, often employ globally uniform smoothness constraints that fail to accommodate the complex, regionally varying deformations characteristic of anatomical motion. To address this limitation, we propose SegReg, a Segmentation-driven Registration framework that implements anatomically adaptive regularization by exploiting region-specific deformation patterns. Our SegReg first decomposes input moving and fixed images into anatomically coherent subregions through segmentation. These localized domains are then processed by the same registration backbone to compute optimized partial deformation fields, which are subsequently integrated into a global deformation field. SegReg achieves near-perfect structural alignment (98.23% Dice on critical anatomies) using ground-truth segmentation, and outperforms existing methods by 2-12% across three clinical registration scenarios (cardiac, abdominal, and lung images) even with automatic segmentation. Our SegReg demonstrates a near-linear dependence of registration accuracy on segmentation quality, transforming the registration challenge into a segmentation problem. The source code will be released upon manuscript acceptance.