Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces.

We present a novel algorithm for the registration of pulmonary CT scans. Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework. The detection of keypoint correspondences enables robustness against large deformations by jointly optimizing over a large number of potential discrete displacements, whereas the dense continuous registration achieves subvoxel alignment with smooth transformations. Both steps are driven by the same normalized gradient fields data term. We employ curvature regularization and a volume change control mechanism to prevent foldings of the deformation grid and restrict the determinant of the Jacobian to physiologically meaningful values. Keypoint correspondences are integrated into the dense registration by a quadratic penalty with adaptively determined weight. Using a parallel matrix-free derivative calculation scheme, a runtime of about 5 min was realized on a standard PC. The proposed algorithm ranks first in the EMPIRE10 challenge on pulmonary image registration. Moreover, it achieves an average landmark distance of 0.82 mm on the DIR-Lab COPD database, thereby improving upon the state of the art in accuracy by 15%. Our algorithm is the first to reach the inter-observer variability in landmark annotation on this dataset.

Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

The treatment of cancer with proton radiation therapy was first suggested in 1946 followed by the first treatments in the 1950s. As of 2020, almost 200,000 patients have been treated with proton beams worldwide and the number of operating proton therapy facilities will soon reach one hundred. Proton therapy has long moved from research institutions into hospital-based facilities that are increasingly being utilized with workflows similar to conventional radiation therapy. While proton therapy has become mainstream and has established itself as a treatment option for many cancers, it is still an area of active research for various reasons: the advanced dose shaping capabilities of proton therapy cause susceptibility to uncertainties, the high degrees of freedom in dose delivery offer room for further improvements, the limited experience and understanding of optimizing pencil beam scanning, and the biological effects differ from photon radiation. In addition to these challenges and opportunities currently being investigated, there is an economic aspect because proton therapy treatments are, on average, still more expensive compared to conventional photon based treatment options. This roadmap highlights the current state and future direction in proton therapy categorized into four different themes, "improving efficiency", "improving planning and delivery", "improving imaging", and "improving patient selection".

/pdf/roadmap-proton-therapy-physics-and-biology-7we91n1uu8.pdf

Roadmap: proton therapy physics and biology

Advances and challenges in deformable image registration: From image fusion to complex motion modelling.

Image-guided interventions often rely on deformable multimodal registration to align pre-treatment and intra-operative scans. There are a number of requirements for automated image registration for this task, such as a robust similarity metric for scans of different modalities with different noise distributions and contrast, an efficient optimisation of the cost function to enable fast registration for this time-sensitive application, and an insensitive choice of registration parameters to avoid delays in practical clinical use. In this work, we build upon the concept of structural image representation for multi-modal similarity. Discriminative descriptors are densely extracted for the multi-modal scans based on the "self-similarity context". An efficient quantised representation is derived that enables very fast computation of point-wise distances between descriptors. A symmetric multi-scale discrete optimisation with diffusion reguIarisation is used to find smooth transformations. The method is evaluated for the registration of 3D ultrasound and MRI brain scans for neurosurgery and demonstrates a significantly reduced registration error (on average 2.1 mm) compared to commonly used similarity metrics and computation times of less than 30 seconds per 3D registration.

BartŁomiej W. Papież

Papers

Deformable image registration by combining uncertainty estimates from supervoxel belief propagation