Brain Tumor Sequence Registration with Non-iterative Coarse-to-fine Networks and Dual Deep Supervision
This addresses the problem of quantifying tumor changes for brain glioma patients, but it is incremental as it builds on an existing method with minor enhancements.
The study tackled brain tumor sequence registration between pre-operative and follow-up MRI scans by extending a non-iterative coarse-to-fine network with dual deep supervision, achieving a mean absolute error of 3.387 on the validation set and placing 4th in the BraTS-Reg 2022 challenge.
In this study, we focus on brain tumor sequence registration between pre-operative and follow-up Magnetic Resonance Imaging (MRI) scans of brain glioma patients, in the context of Brain Tumor Sequence Registration challenge (BraTS-Reg 2022). Brain tumor registration is a fundamental requirement in brain image analysis for quantifying tumor changes. This is a challenging task due to large deformations and missing correspondences between pre-operative and follow-up scans. For this task, we adopt our recently proposed Non-Iterative Coarse-to-finE registration Networks (NICE-Net) - a deep learning-based method for coarse-to-fine registering images with large deformations. To overcome missing correspondences, we extend the NICE-Net by introducing dual deep supervision, where a deep self-supervised loss based on image similarity and a deep weakly-supervised loss based on manually annotated landmarks are deeply embedded into the NICE-Net. At the BraTS-Reg 2022, our method achieved a competitive result on the validation set (mean absolute error: 3.387) and placed 4th in the final testing phase (Score: 0.3544).