We present a novel deep learning-based framework: Embedded Feature Similarity Optimization with Specific Parameter Initialization (SOPI) for 2D/3D medical image registration which is a most challenging problem due to the difficulty such as dimensional mismatch, heavy computation load and lack of golden evaluation standard. The framework we design includes a parameter specification module to efficiently choose initialization pose parameter and a fine-registration module to align images. The proposed framework takes extracting multi-scale features into consideration using a novel composite connection encoder with special training techniques. We compare the method with both learning-based methods and optimization-based methods on a in-house CT/X-ray dataset as well as simulated data to further evaluate performance. Our experiments demonstrate that the method in this paper has improved the registration performance, and thereby outperforms the existing methods in terms of accuracy and running time. We also show the potential of the proposed method as an initial pose estimator. The code is available at https://github.com/m1nhengChen/SOPI
@article{arxiv.2305.06252,
title = {Embedded Feature Similarity Optimization with Specific Parameter Initialization for 2D/3D Medical Image Registration},
author = {Minheng Chen and Zhirun Zhang and Shuheng Gu and Youyong Kong},
journal= {arXiv preprint arXiv:2305.06252},
year = {2023}
}