Deformable Registration Using Average Geometric Transformations for Brain MR Images
This addresses medical image registration for brain MRI diagnosis, representing an incremental improvement over existing methods.
The paper tackles brain MRI registration by proposing a deformable method using average geometric transformations and VoxelMorph CNN, achieving excellent improvement with average Dice scores and non-negative Jacobian locations compared to MIT's original method on ADNI and MRBrainS18 datasets.
Accurate registration of medical images is vital for doctor's diagnosis and quantitative analysis. In this paper, we propose a new deformable medical image registration method based on average geometric transformations and VoxelMorph CNN architecture. We compute the differential geometric information including Jacobian determinant(JD) and the curl vector(CV) of diffeomorphic registration field and use them as multi-channel of VoxelMorph CNN for second train. In addition, we use the average transformation to construct a standard brain MRI atlas which can be used as fixed image. We verify our method on two datasets including ADNI dataset and MRBrainS18 Challenge dataset, and obtain excellent improvement on MR image registration with average Dice scores and non-negative Jacobian locations compared with MIT's original method. The experimental results show the method can achieve better performance in brain MRI diagnosis.