Deep Deformable Registration: Enhancing Accuracy by Fully Convolutional Neural Net
This work addresses a domain-specific problem in medical image analysis, offering an incremental improvement to existing deformable registration methods.
The authors tackled the problem of improving deformable registration accuracy in medical image analysis by constructing a tight upper bound of the SSD registration cost using a fully convolutional neural network, and demonstrated significant accuracy enhancements on two 3D brain MRI datasets.
Deformable registration is ubiquitous in medical image analysis. Many deformable registration methods minimize sum of squared difference (SSD) as the registration cost with respect to deformable model parameters. In this work, we construct a tight upper bound of the SSD registration cost by using a fully convolutional neural network (FCNN) in the registration pipeline. The upper bound SSD (UB-SSD) enhances the original deformable model parameter space by adding a heatmap output from FCNN. Next, we minimize this UB-SSD by adjusting both the parameters of the FCNN and the parameters of the deformable model in coordinate descent. Our coordinate descent framework is end-to-end and can work with any deformable registration method that uses SSD. We demonstrate experimentally that our method enhances the accuracy of deformable registration algorithms significantly on two publicly available 3D brain MRI data sets.