Deformable Medical Image Registration Using a Randomly-Initialized CNN as Regularization Prior

Laves, Max-Heinrich; Ihler, Sontje; Ortmaier, Tobias

doi:10.48550/arxiv.1908.00788

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is possible within our presented Bayesian framework and should enable much faster convergence without showing the aforementioned pitfalls of methods trained with full supervision. Besides the addressed inverse tasks, POTOBIM could further be applied to unsupervised deformable registration (Laves et al, 2019) or any other inverse task as long as the forward operator (e.g., point spread function for fluorescence microscopy) can be implemented in a differentiable manner w.r.t. the network weights to obtain a solution for the ill-posed reverse operator.…”

Section: Limitations and Future Workmentioning

confidence: 99%

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

Laves¹,

Tölle²,

Schlaefer³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We present Posterior Temperature Optimized Bayesian Inverse Models (POTOBIM), an unsupervised Bayesian approach to inverse problems in medical imaging using mean-field variational inference with a fully tempered posterior. Bayesian methods exhibit useful properties for approaching inverse tasks, such as tomographic reconstruction or image denoising. A suitable prior distribution introduces regularization, which is needed to solve the ill-posed problem and reduces overfitting the data. In practice, however, this often results in a suboptimal posterior temperature, and the full potential of the Bayesian approach is not being exploited. In POTOBIM, we optimize both the parameters of the prior distribution and the posterior temperature with respect to reconstruction accuracy using Bayesian optimization with Gaussian process regression. Our method is extensively evaluated on four different inverse tasks on a variety of modalities with images from public data sets and we demonstrate that an optimized posterior temperature outperforms both non-Bayesian and Bayesian approaches without temperature optimization. The use of an optimized prior distribution and posterior temperature leads to improved accuracy and uncertainty estimation and we show that it is sufficient to find these hyperparameters per task domain. Well-tempered posteriors yield calibrated uncertainty, which increases the reliability in the predictions. Our source code is publicly available at github.com/Cardio-AI/mfvi-dip-mia.

show abstract

Section: Limitations and Future Workmentioning

confidence: 99%

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

Laves¹,

Tölle²,

Schlaefer³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides, occasionally regularization terms need to be manually adjusted for each application to obtain accurate results. However, recent studies show that the regularization prior can be modeled by neural networks, independent of learning, for deformable image registration [14,25] to remove the need for manual adjustment of parameters.…”

Section: Introductionmentioning

confidence: 99%

A training-free recursive multiresolution framework for diffeomorphic deformable image registration

Sheikhjafari,

Noga,

Punithakumar

et al. 2022

Preprint

View full text Add to dashboard Cite

Diffeomorphic deformable image registration is one of the crucial tasks in medical image analysis, which aims to find a unique transformation while preserving the topology and invertibility of the transformation. Deep convolutional neural networks (CNNs) have yielded wellsuited approaches for image registration by learning the transformation priors from a large dataset. The improvement in the performance of these methods is related to their ability to learn information from several sample medical images that are difficult to obtain and bias the framework to the specific domain of data. In this paper, we propose a novel diffeomorphic training-free approach; this is built upon the principle of an ordinary differential equation.Our formulation yields an Euler integration type recursive scheme to estimate the changes of spatial transformations between the fixed and the moving image pyramids at different resolutions. The proposed architecture is simple in design. The moving image is warped successively at each resolution and finally aligned to the fixed image; this procedure is recursive in a way that at each resolution, a fully convolutional network (FCN) models a progressive change of deformation for the current warped image. The entire system is end-to-end and optimized for each pair of images from scratch. In comparison to learning-based methods, the proposed method neither requires a dedicated training set nor suffers from any training bias. We evaluate our method on three cardiac image datasets. The evaluation results demonstrate that the proposed method achieves state-of-the-art registration accuracy while maintaining desirable diffeomorphic properties.

show abstract

Deformable Medical Image Registration Using a Randomly-Initialized CNN as Regularization Prior

Cited by 2 publications

References 9 publications

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

Posterior temperature optimized Bayesian models for inverse problems in medical imaging

A training-free recursive multiresolution framework for diffeomorphic deformable image registration

Contact Info

Product

Resources

About