MSCAReg‐Net: Multi‐scale complexity‐aware convolutional neural network for deformable image registration

Abstract

Abstract Deep learning‐based image registration (DLIR) has been widely developed, but it remains challenging in perceiving small and large deformations. Besides, the effectiveness of the DLIR methods was also rarely validated on the downstream tasks. In the study, a multi‐scale complexity‐aware registration network (MSCAReg‐Net) was proposed by devising a complexity‐aware technique to facilitate DLIR under a single‐resolution framework. Specifically, the complexity‐aware technique devised a multi‐scale complexity‐aware module (MSCA‐Module) to perceive deformations with distinct complexities, and employed a feature calibration module (FC‐Module) and a feature aggregation module (FA‐Module) to facilitate the MSCA‐Module by generating more distinguishable deformation features. Experimental results demonstrated the superiority of the proposed MSCAReg‐Net over the existing methods in terms of registration accuracy. Besides, other than the indices of Dice similarity coefficient (DSC) and percentage of voxels with non‐positive Jacobian determinant (|Jϕ|≤0), a comprehensive evaluation of the registration performance was performed by applying this method on a downstream task of multi‐atlas hippocampus segmentation (MAHS). Experimental results demonstrated that this method contributed to a better hippocampus segmentation over other DLIR methods, and a comparable segmentation performance with the leading SyN method. The comprehensive assessment including DSC, |Jϕ|≤0, and the downstream application on MAHS demonstrated the advances of this method.

Keywords

• biomedical MRI
• computer vision
• convolutional neural nets
• image registration
• medical image processing
• unsupervised learning