SimpleElastix: A User-Friendly, Multi-lingual Library for Medical Image Registration

Marstal, Kasper; Berendsen, Floris F.; Staring, Marius; Klein, Stefan

doi:10.1109/cvprw.2016.78

Cited by 240 publications

(184 citation statements)

References 18 publications

Supporting

Mentioning

183

Contrasting

Order By: Relevance

“…b, which includes preprocessing steps applied to precontrast (0 mmol/kg), low‐dose postcontrast (0.01 mmol/kg), and true full‐dose postcontrast (0.1 mmol/kg) IR‐FSPGR sequences for each subject. To remove the systematic differences between signal intensity levels in nonenhancing regions (such as scalp fat), efficient rigid coregistration using SimpleElastic software, and signal normalization based on average voxel value within a mask was conducted. This step is required since the transmit and receive gains used for the sequences were determined from separate prescans, and thus were not guaranteed to be the same.…”

Section: Methodsmentioning

confidence: 99%

Deep learning enables reduced gadolinium dose for contrast‐enhanced brain MRI

Gong

Pauly

Wintermark

et al. 2018

Magnetic Resonance Imaging

240

186

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Deep learning enables reduced gadolinium dose for contrast‐enhanced brain MRI

Gong

Pauly

Wintermark

et al. 2018

Magnetic Resonance Imaging

240

186

View full text Add to dashboard Cite

show abstract

“…The proposed AC-RegNet model was compared with two initial baselines: SimpleElastix [30] and the baseline RegNet described in Section 3.1, which do not consider segmentation-aware loss functions during training. SimpleElastix is a classic medical image registration toolbox, considered state-of-the-art and listed as one of the most popular software packages implementing iterative image registration during the last 20 years (see [43]).…”

Section: Model Comparisonmentioning

confidence: 99%

Learning deformable registration of medical images with anatomical constraints

2020

View full text Add to dashboard Cite

Deformable image registration is a fundamental problem in the field of medical image analysis. During the last years, we have witnessed the advent of deep learning-based image registration methods which achieve state-of-the-art performance, and drastically reduce the required computational time. However, little work has been done regarding how can we encourage our models to produce not only accurate, but also anatomically plausible results, which is still an open question in the field. In this work, we argue that incorporating anatomical priors in the form of global constraints into the learning process of these models, will further improve their performance and boost the realism of the warped images after registration. We learn global non-linear representations of image anatomy using segmentation masks, and employ them to constraint the registration process. The proposed AC-RegNet architecture is evaluated in the context of chest X-ray image registration using three different datasets, where the high anatomical variability makes the task extremely challenging. Our experiments show that the proposed anatomically constrained registration model produces more realistic and accurate results than state-of-the-art methods, demonstrating the potential of this approach.

show abstract

“…20 In this latter case, μXANES spectra were extracted from a stack of images recorded at each energy step of the spectrum, with a step size of 0.5 μm (horizontal) × 0.5 μm (vertical). The 139 XRF images recorded using a region of interest selective for Ti Kα emission lines, corrected for the detector deadtime and normalized by I 0 , were aligned using Elastix 21 and saved to an hdf5 file containing the intensities and energy values for each map. μXANES spectra were then extracted from the FXAS maps using PyMCA.…”

Section: μXrf and μXanes Analysesmentioning

confidence: 99%