89 papers with code • 1 benchmarks • 2 datasets
Image Registration is a key component for multimodal image fusion, which generally refers to the process by which two or more image volumes and their corresponding features (acquired from different sensors, points of view, imaging modalities, etc.) are aligned into the same coordinate space. Medical images that are acquired from different imaging modalities use different imaging physics, which creates unique advantages and disadvantages. Relatively unique information about the imaged volume is provided by each modality. Image fusion through registration can integrate the complementary information from multimodal images to help achieve more accurate diagnosis and treatment.
We present HyperMorph, a learning-based strategy for deformable image registration that removes the need to tune important registration hyperparameters during training.
To develop a deep learning-based segmentation model for a new image dataset (e. g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches.
We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs).
In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images.
Ranked #1 on Diffeomorphic Medical Image Registration on OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP (Dice metric)
This comparison shows that, of the three methods tested, SyN's volume measurements are the most strongly correlated with volume measurements gained by expert labeling.
Ranked #1 on BIRL on CIMA-10k
DeepReg (https://github. com/DeepRegNet/DeepReg) is a community-supported open-source toolkit for research and education in medical image registration using deep learning.
With the "Autograd Image Registration Laboratory" (AIRLab), we introduce an open laboratory for image registration tasks, where the analytic gradients of the objective function are computed automatically and the device where the computations are performed, on a CPU or a GPU, is transparent.
We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration.
3D medical image registration is of great clinical importance.