Image Enhancement With PDEs and Nonconservative Advection Flow Fields

Jaouen, Vincent; Bert, Julien; Boussion, Nicolas; Fayad, Hadi; Hatt, Mathieu; Visvikis, Dimitris

doi:10.1109/tip.2018.2881838

Cited by 18 publications

(9 citation statements)

References 72 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1c-f). They can also show some contour completion abilities in case of missing edges [32], [33]. These properties are not only desirable for image segmentation with active contours, but also for image registration purposes and may help overcoming some of the limitations of previously proposed gradient-based alignment methods, such as NGF.…”

Section: A Vector Field Similaritymentioning

confidence: 97%

Regularized directional representations for medical image registration

Jaouen¹,

Conze²,

Dardenne³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In image registration, many efforts have been devoted to the development of alternatives to the popular normalized mutual information criterion. Concurrently to these efforts, an increasing number of works have demonstrated that substantial gains in registration accuracy can also be achieved by aligning structural representations of images rather than images themselves. Following this research path, we propose a new method for mono-and multimodal image registration based on the alignment of regularized vector fields derived from structural information such as gradient vector flow fields, a technique we call vector field similarity. Our approach can be combined in a straightforward fashion with any existing registration framework by substituting vector field similarity to intensity-based registration. In our experiments, we show that the proposed approach compares favourably with conventional image alignment on several public image datasets using a diversity of imaging modalities and anatomical locations.

show abstract

Section: A Vector Field Similaritymentioning

confidence: 97%

Regularized directional representations for medical image registration

Jaouen¹,

Conze²,

Dardenne³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…(2) Through the image obtained in wavelet decomposition processing step (1), four frequency domains are obtained, which are LL 1 , LH 1 , HL 1 , and HH 1 . Continue wavelet decomposition of LL 1 in low-frequency domain and obtain four frequency domains again (18,19), in order: LL 2 , LL 2 , HL 2 , and HH 2 . Perform wavelet decomposition repeatedly until the maximum number of layers is decomposed J.…”

Section: Steps Of Medical Image Denoisingmentioning

confidence: 99%

Medical Image Segmentation Algorithm for Three-Dimensional Multimodal Using Deep Reinforcement Learning and Big Data Analytics

Gao

Wang

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

To avoid the problems of relative overlap and low signal-to-noise ratio (SNR) of segmented three-dimensional (3D) multimodal medical images, which limit the effect of medical image diagnosis, a 3D multimodal medical image segmentation algorithm using reinforcement learning and big data analytics is proposed. Bayesian maximum a posteriori estimation method and improved wavelet threshold function are used to design wavelet shrinkage algorithm to remove high-frequency signal component noise in wavelet domain. The low-frequency signal component is processed by bilateral filtering and the inverse wavelet transform is used to denoise the 3D multimodal medical image. An end-to-end DRD U-Net model based on deep reinforcement learning is constructed. The feature extraction capacity of denoised image segmentation is increased by changing the convolution layer in the traditional reinforcement learning model to the residual module and introducing the multiscale context feature extraction module. The 3D multimodal medical image segmentation is done using the reward and punishment mechanism in the deep learning reinforcement algorithm. In order to verify the effectiveness of 3D multimodal medical image segmentation algorithm, the LIDC-IDRI data set, the SCR data set, and the DeepLesion data set are selected as the experimental data set of this article. The results demonstrate that the algorithm's segmentation effect is effective. When the number of iterations is increased to 250, the structural similarity reaches 98%, the SNR is always maintained between 55 and 60 dB, the training loss is modest, relative overlap and accuracy all exceed 95%, and the overall segmentation performance is superior. Readers will understand how deep reinforcement learning and big data analytics test the effectiveness of 3D multimodal medical image segmentation algorithm.

show abstract

“…The multiscale construction tensor is a matrix derived from the gradient of a function. It summarizes the main directions of the gradient in the specified domain of points with powers that are coherent with these directions [23]. The diffusion process with the steering of the structure tensor instead of the regularized gradient steering allows us to adapt it to more refined goals, such as the enhancement of coherent flow-like structural elements.…”

Section: Research On Image Texture Analysis Andmentioning

confidence: 99%

Image Texture Analysis and Edge Detection Algorithm Based on Anisotropic Diffusion Equation

Li¹

2021

Advances in Mathematical Physics

View full text Add to dashboard Cite

This paper uses partial differential equation image processing techniques to establish image texture analysis models based on nonlinear anisotropic diffusion equations for image denoising, image segmentation, and image decomposition. This paper proposes a class of denoising models based on the hybrid anisotropic diffusion equation from the characteristics of different noise types. The model exhibits anisotropic diffusion near the image boundary, which can protect the boundary well, and isotropic diffusion inside the image; so, it can remove the noise effectively. We use the immovable point theory to prove the uniqueness of the model solution and further discuss other properties such as asymptotics of the solution. We propose a class of image texture analysis algorithms based on anisotropic diffusion equations and discrete gray level sets. First, a class of nonconvex generalized functions is proposed to remove the noise from the original image to obtain a smooth image while sharpening the edges. Then, an energy generalization function based on the gray level set is proposed, and the existence of the global minimum of this energy generalization function is discussed. Finally, an equivalent form of this energy generalization is given in the discrete case, and an image texture analysis algorithm is designed based on the equivalent form. The algorithm is improved by initial position optimization, dynamic adjustment of parameters, and adaptive selection of thresholds so that the ants can search along the real edges. Experiments show that the improved algorithm for image edge detection can obtain more complete edges and better detection results. The energy generalization function is calculated directly on the discrete gray level set instead of solving the corresponding partial differential equation, which can avoid the selection of the initial level set and the reinitialization of the level set, thus greatly improving the segmentation efficiency. The new algorithm has a high improvement in segmentation efficiency and can efficiently handle large size complex images.

show abstract

Image Enhancement With PDEs and Nonconservative Advection Flow Fields

Cited by 18 publications

References 72 publications

Regularized directional representations for medical image registration

Regularized directional representations for medical image registration

Medical Image Segmentation Algorithm for Three-Dimensional Multimodal Using Deep Reinforcement Learning and Big Data Analytics

Image Texture Analysis and Edge Detection Algorithm Based on Anisotropic Diffusion Equation

Contact Info

Product

Resources

About