Enhancement of Cilia Sub-structures by Multiple Instance Registration and Super-Resolution Reconstruction

Suveer, Amit; Sladoje, Nataša; Lindblad, Joakim; Dragomir, Anca; Sintorn, Ida‐Maria

doi:10.1007/978-3-319-59129-2_31

Cited by 1 publication

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By differentiating the distance measure we are able to use efficient gradientbased optimization. The proposed method outperforms the commonly used similarity measures in both synthetic and real scenarios of medical and biomedical registration tasks, which we confirm by (i) landmark-based evaluation on transmission electron microscopy (TEM) images of cilia [12], with the aim of improving multi-image super-resolution reconstruction, as well as (ii) evaluation on the task of atlas-based segmentation of magnetic resonance (MR) images of brain, on the LPBA40dataset [13].…”

Section: Introductionsupporting

confidence: 54%

“…we confirm by (i) landmark-based evaluation on transmission electron microscopy (TEM) images of cilia [12], with the aim of improving multi-image super-resolution reconstruction, as well as (ii) evaluation on the task of atlas-based segmentation of magnetic resonance (MR) images of brain, on the LPBA40dataset [13].…”

Section: Introductionmentioning

confidence: 58%

“…1) TEM Images of Cilia (2D): The dataset of 20 images of cilia [12] is acquired with the MiniTEM 4 imaging system. Each image is isotropic of size 129 × 129 pixels, with a pixelsize of a few nm.…”

Section: A Datasetsmentioning

confidence: 99%

“…For the central pair, the error is simply AME CP = AME, whereas for the outer rings we utilize the knowledge that an odd (even) landmark should be matched with an odd (even) landmark of the other image. The error function for the outer rings, [12], is therefore defined as:…”

Section: ) Average Error Measure (Ae)mentioning

confidence: 99%

“…We compare the performance of the proposed method with reported results of a previous study [12] which uses intensitybased registration with PCC as similarity measure. We follow the general protocol described in [12] and perform, as a first step, a multi-start rigid registration (parameterized by angle θ in radians, and translation t = (t x , t y )), followed, in a second step, by affine registration initiated by the best (lowest final distance) registration of the 9 rigid ones.…”

Section: F Evaluation On Real Applicationsmentioning

confidence: 99%

See 4 more Smart Citations

Fast and Robust Symmetric Image Registration Based on Distances Combining Intensity and Spatial Information

Öfverstedt

Lindblad

Sladoje

2019

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Intensity-based image registration approaches rely on similarity measures to guide the search for geometric correspondences with high affinity between images. The properties of the used measure are vital for the robustness and accuracy of the registration. In this study a symmetric, intensity interpolationfree, affine registration framework based on a combination of intensity and spatial information is proposed. The excellent performance of the framework is demonstrated on a combination of synthetic tests, recovering known transformations in the presence of noise, and real applications in biomedical and medical image registration, for both 2D and 3D images. The method exhibits greater robustness and higher accuracy than similarity measures in common use, when inserted into a standard gradientbased registration framework available as part of the open source Insight Segmentation and Registration Toolkit (ITK). The method is also empirically shown to have a low computational cost, making it practical for real applications. Source code is available.

show abstract

Section: Introductionsupporting

confidence: 54%

Section: Introductionmentioning

confidence: 58%

Section: A Datasetsmentioning

confidence: 99%

Section: ) Average Error Measure (Ae)mentioning

confidence: 99%

Section: F Evaluation On Real Applicationsmentioning

confidence: 99%

See 3 more Smart Citations