Diffeomorphic Multi-Resolution Deep Learning Registration for Applications in Breast MRI
This addresses the challenge of localizing tumors in breast cancer treatment, but it is incremental as it adapts existing learning-based methods to a specific domain with diffeomorphic requirements.
The paper tackled the problem of accurate registration of breast MR images across patient positions for surgical planning by proposing a learning-based registration network with diffeomorphic constraints, achieving superior registration outcomes in in-silico and in-vivo experiments.
In breast surgical planning, accurate registration of MR images across patient positions has the potential to improve the localisation of tumours during breast cancer treatment. While learning-based registration methods have recently become the state-of-the-art approach for most medical image registration tasks, these methods have yet to make inroads into breast image registration due to certain difficulties-the lack of rich texture information in breast MR images and the need for the deformations to be diffeomophic. In this work, we propose learning strategies for breast MR image registration that are amenable to diffeomorphic constraints, together with early experimental results from in-silico and in-vivo experiments. One key contribution of this work is a registration network which produces superior registration outcomes for breast images in addition to providing diffeomorphic guarantees.