Foveated Nonlocal Self-Similarity

Foi, Alessandro; Boracchi, Giacomo

doi:10.1007/s11263-016-0898-1

Cited by 31 publications

(18 citation statements)

References 111 publications

(137 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, when we watch a point in an image, this point will have the highest sensitivity and the sensitivity will drop with the increasing distance to the point. Inspired by the characteristics of the HVS, Alessandro Foi et al [31] have proposed calculating the patch similarity based on the Euclidean distance d FOV between the the foveated patches, defined as:d FOV(I, x1, x2) = ‖Ix1 FOV−Ix2 FOV‖22 where Ix1 FOV and Ix2 FOV denote the foveated patches that were obtained by foveating the image I at the two fixation points x1 and x2. By applying the foveation operator F to the image I , the foveated patch Ix FOV is produced as:Ix …”

Section: Methodsmentioning

confidence: 99%

Non-Rigid Multi-Modal 3D Medical Image Registration Based on Foveated Modality Independent Neighborhood Descriptor

Yang

Ding

Zhang

2019

Sensors

View full text Add to dashboard Cite

The non-rigid multi-modal three-dimensional (3D) medical image registration is highly challenging due to the difficulty in the construction of similarity measure and the solution of non-rigid transformation parameters. A novel structural representation based registration method is proposed to address these problems. Firstly, an improved modality independent neighborhood descriptor (MIND) that is based on the foveated nonlocal self-similarity is designed for the effective structural representations of 3D medical images to transform multi-modal image registration into mono-modal one. The sum of absolute differences between structural representations is computed as the similarity measure. Subsequently, the foveated MIND based spatial constraint is introduced into the Markov random field (MRF) optimization to reduce the number of transformation parameters and restrict the calculation of the energy function in the image region involving non-rigid deformation. Finally, the accurate and efficient 3D medical image registration is realized by minimizing the similarity measure based MRF energy function. Extensive experiments on 3D positron emission tomography (PET), computed tomography (CT), T1, T2, and (proton density) PD weighted magnetic resonance (MR) images with synthetic deformation demonstrate that the proposed method has higher computational efficiency and registration accuracy in terms of target registration error (TRE) than the registration methods that are based on the hybrid L-BFGS-B and cat swarm optimization (HLCSO), the sum of squared differences on entropy images, the MIND, and the self-similarity context (SSC) descriptor, except that it provides slightly bigger TRE than the HLCSO for CT-PET image registration. Experiments on real MR and ultrasound images with unknown deformation have also be done to demonstrate the practicality and superiority of the proposed method.

show abstract

Section: Methodsmentioning

confidence: 99%

Non-Rigid Multi-Modal 3D Medical Image Registration Based on Foveated Modality Independent Neighborhood Descriptor

Yang

Ding

Zhang

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…The effect of BM3D 5 and FNLM 6 denoising on the ability of descriptors to discriminate distinct local structure/texture was investigated using two pairs of OCT images, each acquired from the same patient. The ability of descriptors d i and d j in images I i and I j was quantified using mutual descriptiveness, MD(bold-italicdi,bold-italicdj,x,scriptNq)=Ui(bold-italicdi,bold-italicdj,x,scriptNq)+Uj(bold-italicdj,bold-italicdi,x,scriptNq)2+2H(bold-italicdi(x),bold-italicdj(x))∈[0,1] combining the Huber dissimilarity measure H and the uniqueness U i determined by the similarity of a descriptor to its neighboring descriptors defined in a neighborhood scriptNq in I i and I j as Ui(bold-italicdi,bold-italicdj,x,scriptNq)=12|scriptNq|∑q∈scriptNq…”

Section: Methodsmentioning

confidence: 99%

“…The registration method and D-MINDs are described in Section 2. Since OCT exhibits poor signal-to-noise ratio, 4 the effects of denoising methods [i.e., block-matching and 3D (BM3D) filtering 5 and foveated nonlocal means (FNLM) filtering 6 ] on the ability of descriptors to encode local structure and/or texture in images are presented in Sections 3 and 4. The sections additionally demonstrate the performance of the D-MIND Demons method in cross-scanner intra- and inter-subject registration using clinical OCT data compared to its variants––i.e., integrating D-MINDs with other descriptors including average image gradients (AG), compact histograms of image orientation (CHO), co-occurrence (COC) texture features, 7 and run length (RL) texture features 8 .…”

Section: Introductionmentioning

confidence: 99%

Inter-scanner variation independent descriptors for constrained diffeomorphic demons registration of retina OCT

Reaungamornrat

Carass

et al. 2018

Medical Imaging 2018: Image Processing

View full text Add to dashboard Cite

Purpose OCT offers high in-plane micrometer resolution, enabling studies of neurodegenerative and ocular-disease mechanisms via imaging of the retina at low cost. An important component to such studies is inter-scanner deformable image registration. Image quality of OCT, however, is suboptimal with poor signal-to-noise ratio and through-plane resolution. Geometry of OCT is additionally improperly defined. We developed a diffeomorphic deformable registration method incorporating constraints accommodating the improper geometry and a decentralized-modality-insensitive-neighborhood-descriptors (D-MIND) robust against degradation of OCT image quality and inter-scanner variability. Method The method, called D-MIND Demons, estimates diffeomorphisms using D-MINDs under constraints on the direction of velocity fields in a MIND-Demons framework. Descriptiveness of D-MINDs with/without denoising was ranked against four other shape/texture-based descriptors. Performance of D-MIND Demons and its variants incorporating other descriptors was compared for cross-scanner, intra- and inter-subject deformable registration using clinical retina OCT data. Result D-MINDs outperformed other descriptors with the difference in mutual descriptiveness between high-contrast and homogenous regions > 0.2. Among Demons variants, D-MIND-Demons was computationally efficient, demonstrating robustness against OCT image degradation (noise, speckle, intensity-non-uniformity, and poor through-plane resolution) and consistent registration accuracy [(4±4 μm) and (4±6 μm) in cross-scanner intra- and inter-subject registration] regardless of denoising. Conclusions A promising method for cross-scanner, intra- and inter-subject OCT image registration has been developed for ophthalmological and neurological studies of retinal structures. The approach could assist image segmentation, evaluation of longitudinal disease progression, and patient population analysis, which in turn, facilitate diagnosis and patient-specific treatment.

show abstract

“…Clearly, more complex anisotropic patch shapes could have been used [30]. We decided to consider this anisotropy as a good trade off between accuracy and complexity.…”

Section: E Introduction Of the Anisotropymentioning

confidence: 99%

Anisotropic Weighted KS-NLM Filter for Noise Reduction in MRI

et al. 2020

View full text Add to dashboard Cite

The topic of denoising magnetic resonance (MR) images is considered in this paper. More in detail, an enhanced Non-Local Means (NLM) filter using the Kolmogorov-Smirnov (KS) distance is proposed. The KS-NLM approach estimates the similarity between image patches by computing the KS distance. To overcome that NLM filters assign the same role to all pixels in patches, that is, not privileging the central one, we propose a new filter, namely the Anisotropic Weighted KS-NLM (Aw KS-NLM), which better deals with central pixels within the patches by, on one hand, including a suitable weighted strategy and, on the other, by performing a local anisotropy analysis. The Aw KS-NLM has been compared to other existing non-local Means (NLM) methodologies in both MRI simulated and real datasets. The results provide excellent noise reduction and image-detail preservation.

show abstract

Foveated Nonlocal Self-Similarity

Cited by 31 publications

References 111 publications

Non-Rigid Multi-Modal 3D Medical Image Registration Based on Foveated Modality Independent Neighborhood Descriptor

Non-Rigid Multi-Modal 3D Medical Image Registration Based on Foveated Modality Independent Neighborhood Descriptor

Inter-scanner variation independent descriptors for constrained diffeomorphic demons registration of retina OCT

Anisotropic Weighted KS-NLM Filter for Noise Reduction in MRI

Contact Info

Product

Resources

About