A diffeomorphic unsupervised method for deformable soft tissue image registration

Zhang, Shuo; Liu, Peter; Zheng, Minhua; Shi, Wen Zhong

doi:10.1016/j.compbiomed.2020.103708

Cited by 12 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have also validated the method quantitatively. We have compared our method with various other diffeomorphic and non-diffeomorphic methods such as [65], [32], [39], [40], [38], and [31], using some popular measures such as mean square error (MSE), normalized cross-correlation (NCC), structural similarity (SS), mutual information (MI), feature similarity index (FSIM), and mean absolute error (MSE) [52]. The results of CT/CT, 3DRA/3DRA, MR/MR, and CT/MR are provided in Table 1, 2, 3, and 4, respectively.…”

Section: Resultsmentioning

confidence: 99%

Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration

Mohanty

Dakua

2022

IEEE Access

View full text Add to dashboard Cite

This paper describes a new non-rigid approach to register images from same-and crossimaging modalities such as magnetic resonance imaging, computed tomography, and 3D rotational angiography. The deformation is a key challenge in medical image registration. We have proposed a diffeomorphism-based method to tackle this problem using an optimized framework. A non stationary velocity field is used to minimize the effect of forces that are derived from the image gradients. Furthermore, we propose a similarity energy function, based on the gray scale distribution, to limit the fluctuations while approaching the local minima. The proposed method is evaluated on both private and public datasets; the results show that the values of mean square error (MSE), normalized cross-correlation (NCC), structural similarity (SS), mutual information (MI), feature similarity index (FSIM), and mean absolute error (MAE) are 1.3136, 0.9962, 0.9897, 0.883, 0.9922, and 1.52 ± 2.09, respectively. Both qualitative and quantitative evaluation show promising registration accuracy reflecting the potential of the proposed method.

show abstract

Section: Resultsmentioning

confidence: 99%

Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration

Mohanty

Dakua

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…det(Dφ −1 ) < 0 indicates the locations where folding has occurred. The proportion of folding voxels ρ = ∑ δ(det(Dφ −1 )<0) V is computed to evaluate the topology-preserving performance [14]. We conducted experiments on the OASIS-3 dataset to evaluate the performance of the proposed fusion method and to compare it with three state-of-the state methods: AAW, MIScnn [15] and patchify [16].…”

Section: Methodsmentioning

confidence: 99%

Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration

Liu

2021

Sensors

View full text Add to dashboard Cite

Patch-based medical image registration has been well explored in recent decades. However, the patch fusion process can generate grid-like artifacts along the edge of patches for the following two reasons: firstly, in order to ensure the same size of input and output, zero-padding is used, which causes uncertainty in the edges of the output feature map during the feature extraction process; secondly, the sliding window extraction patch with different strides will result in different degrees of grid-like artifacts. In this paper, we propose an exponential-distance-weighted (EDW) method to remove grid-like artifacts. To consider the uncertainty of predictions near patch edges, we used an exponential function to convert the distance from the point in the overlapping regions to the center point of the patch into a weighting coefficient. This gave lower weights to areas near the patch edges, to decrease the uncertainty predictions. Finally, the dense displacement field was obtained by this EDW weighting method. We used the OASIS-3 dataset to evaluate the performance of our method. The experimental results show that the proposed EDW patch fusion method removed grid-like artifacts and improved the dice similarity coefficient superior to those of several state-of-the-art methods. The proposed fusion method can be used together with any patch-based registration model.

show abstract

“…The network was trained with a combination of four losses, one focusing on the intensity similarity using normalised cross-correlation (L sim ), one focusing on anatomical structures using dice loss (L seg ) and two losses for regularisation of the displacements. The first one was the Jacobian loss which is exploited on different works such as [17,16,26] (L jac ) and the second one enforcing smooth gradients similar to [8] (L smooth ). As such our final loss is: L = (L sim + L seg + αL smooth + βL jac ) M →F + (L sim + L seg + αL smooth + βL jac ) F →M with α and β being the weights of the regularisation losses.…”

Section: Deep Learning-based Registration Schemementioning

confidence: 99%

Exploring Deep Registration Latent Spaces

Estienne

Vakalopoulou

Christodoulidis

et al. 2021

Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

A diffeomorphic unsupervised method for deformable soft tissue image registration

Cited by 12 publications

References 17 publications

Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration

Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration

Exponential-Distance Weights for Reducing Grid-like Artifacts in Patch-Based Medical Image Registration

Exploring Deep Registration Latent Spaces

Contact Info

Product

Resources

About