A Spatial Alignment Method for Medical Ear Canal Based on Simplified Transformer Module and MultiScale Iterative Structure

Alignment of deformed medical images is a challenging task in which the images are subject to large deformations due to some constraints in the image acquisition process. In the field of deformation image alignment, convolutional neural network-based methods have a local acceptance domain and cannot handle deformed images. In this regard, we propose a new multi-scale parallel architecture model of Transformer-CNN, which takes advantage of Transformer's goodness at modeling remote dependencies, while simplifying the module and reducing the number of model parameters. The multiscale iterative structure of CNN can acquire local information and connect feature information at different scales. Experimental results on the medical ear canal dataset show that the method has excellent performance in terms of alignment accuracy, outperforming existing deep learning and some traditional alignment methods, while reducing the number of model parameters to some extent, making it lightweight.