A Multiple Decoder CNN for Inverse Consistent 3D Image Registration
This work addresses the need for inverse consistency in medical image registration, which is crucial for procedures requiring bidirectional alignment, though it appears incremental as it builds on existing deep learning approaches.
The paper tackled the problem of bidirectional medical image registration by proposing a deep learning framework that simultaneously learns forward and backward transformations in an unsupervised manner, demonstrating strong performance on the LPBA40 MRI dataset compared to baseline methods.
The recent application of deep learning technologies in medical image registration has exponentially decreased the registration time and gradually increased registration accuracy when compared to their traditional counterparts. Most of the learning-based registration approaches considers this task as a one directional problem. As a result, only correspondence from the moving image to the target image is considered. However, in some medical procedures bidirectional registration is required to be performed. Unlike other learning-based registration, we propose a registration framework with inverse consistency. The proposed method simultaneously learns forward transformation and backward transformation in an unsupervised manner. We perform training and testing of the method on the publicly available LPBA40 MRI dataset and demonstrate strong performance than baseline registration methods.