Bayesian Deep Learning for Deformable Medical Image Registration

Deshpande, Vijay S.; Bhatt, Jignesh S.

doi:10.1007/978-3-030-34872-4_5

Cited by 12 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later research has been carried out on finding ideal hyperparameters for optimizing its structure, developing various versions of architectures and understanding its mathematical framework. Many significant statistical methods are introduced into CNNs like probability distributions in place of finite, fixed valued weights, and incorporating naive Bayes into deep learning [20] to improve their performance [4]. Residual Network architecture (ResNet) [21] uses residual blocks to decrease the training error.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards glass-box CNNs

Manaswini¹,

Bhatt²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Convolution neural networks (CNNs) are brain-inspired architectures popular for their ability to train and relearn visually complex tasks. It is incremental and scalable; however, CNN is mostly treated as black-box and involves multiple trial & error runs. We observe that CNN constructs powerful internal representations that help achieve state-of-the-art performance. Here we propose three layer glass-box (analytical) CNN for two-class image classification problems. First is a representation layer that encompasses both the class information (group invariant) and symmetric transformations (group equivariant) of input images. It is then passed through dimension reduction layer (PCA). Finally the compact yet complete representation is provided to a classifier. Analytical machine learning classifiers and multilayer perceptrons are used to assess sensitivity. Proposed glass-box CNN is compared with equivariance of AlexNet (CNN) internal representation for better understanding and dissemination of results. In future, we would like to construct glass-box CNN for multiclass visually complex tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Machine learning approaches are large scale function estimation algorithms that can learn on their own and adapt to new data based on their past and future experiences [3]. It has wide applications in medical diagnosis [4][5][6], autonomous cars [7], facial recognition [8], remote sensing [9], and in many other fields.…”

Section: Introductionmentioning

confidence: 99%

Towards glass-box CNNs

Manaswini¹,

Bhatt²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Denoising is the fundamental step in the medical diagnosis [11], [12], since doctors and medical practitioners most often rely on these processed images. In particular, magnetic resonance imaging (MRI) and computed tomography (CT) including low-dose CT (LDCT) scans are used to observe the internal structure as well as any defects like tumors or injuries present inside the body.…”

Section: Introductionmentioning

confidence: 99%

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

2021

Self Cite

View full text Add to dashboard Cite

Deep learning attempts medical image denoising either by directly learning the noise present or via first learning the image content. We observe that residual learning (RL) often suffers from signal leakage while dictionary learning (DL) is prone to Gibbs (ringing) artifacts. In this paper, we propose an unsupervised noise learning framework that enhances denoising by augmenting the limitation of RL with the strength of DL and vice versa. To this end, we propose a ten-layer deep residue network (DRN) augmented with patch-based dictionaries. The input images are presented to patch-based DL to indirectly learn the noise via sparse representation while given to the DRN to directly learn the noise. An optimum noise characterization is captured by iterating DL/DRN network against proposed loss. The denoised images are obtained by subtracting the learned noise from available data. We show that augmented DRN effectively handles high-frequency regions to avoid Gibbs artifacts due to DL while augmented DL helps to reduce the overfitting due to RL. Comparative experiments with many state-of-the-arts on MRI and CT datasets (2D/3D) including low-dose CT (LDCT) are conducted on a GPU-based supercomputer. The ablation studies are carried out that demonstrate enhanced denoising performance with minimal signal leakage and least artifacts by proposed augmented approach.

show abstract

“…Deshpande et al employed a Bayesian deep learning approach for deformable medical image registration. They reported that this approach has a better performance than existing state-of-the-art approaches [ 45 ]. Khawaled et al developed a fully Bayesian framework for unsupervised deep learning-based deformable image registration.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Fully Convolutional Networks for Brain Image Registration

Cui

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The purpose of medical image registration is to find geometric transformations that align two medical images so that the corresponding voxels on two images are spatially consistent. Nonrigid medical image registration is a key step in medical image processing, such as image comparison, data fusion, target recognition, and pathological change analysis. Existing registration methods only consider registration accuracy but largely neglect the uncertainty of registration results. In this work, a method based on the Bayesian fully convolutional neural network is proposed for nonrigid medical image registration. The proposed method can generate a geometric uncertainty map to calculate the uncertainty of registration results. This uncertainty can be interpreted as a confidence interval, which is essential for judging whether the source data are abnormal. Moreover, the proposed method introduces group normalization, which is conducive to the network convergence of the Bayesian neural network. Some representative learning-based image registration methods are compared with the proposed method on different image datasets. Experimental results show that the registration accuracy of the proposed method is better than that of the methods, and its antifolding performance is comparable to that of fast image registration and VoxelMorph. Furthermore, the proposed method can evaluate the uncertainty of registration results.

show abstract

Bayesian Deep Learning for Deformable Medical Image Registration

Cited by 12 publications

References 13 publications

Towards glass-box CNNs

Towards glass-box CNNs

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

Bayesian Fully Convolutional Networks for Brain Image Registration

Contact Info

Product

Resources

About