A Symmetric Dynamic Learning Framework for Diffeomorphic Medical Image Registration
This work addresses the need for topology-preserving image registration in medical imaging, though it appears incremental as it builds on existing deep learning and diffeomorphic techniques.
The paper tackles the problem of diffeomorphic medical image registration by introducing DCCNN-LSTM-Reg, a dynamic learning framework that achieves symmetric deformations, and it outperforms existing methods in experiments on three 3D registration tasks.
Diffeomorphic image registration is crucial for various medical imaging applications because it can preserve the topology of the transformation. This study introduces DCCNN-LSTM-Reg, a learning framework that evolves dynamically and learns a symmetrical registration path by satisfying a specified control increment system. This framework aims to obtain symmetric diffeomorphic deformations between moving and fixed images. To achieve this, we combine deep learning networks with diffeomorphic mathematical mechanisms to create a continuous and dynamic registration architecture, which consists of multiple Symmetric Registration (SR) modules cascaded on five different scales. Specifically, our method first uses two U-nets with shared parameters to extract multiscale feature pyramids from the images. We then develop an SR-module comprising a sequential CNN-LSTM architecture to progressively correct the forward and reverse multiscale deformation fields using control increment learning and the homotopy continuation technique. Through extensive experiments on three 3D registration tasks, we demonstrate that our method outperforms existing approaches in both quantitative and qualitative evaluations.