A fully parallel algorithm for multimodal image registration using normalized gradient fields

Rühaak, Jan; König, Lars; Hallmann, Marc; Papenberg, Nils; Heldmann, Stefan; Schumacher, Hanno; Fischer, Bernd

doi:10.1109/isbi.2013.6556539

Cited by 22 publications

(23 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conducted analyses suggest that, when using normalised gradient fields, the registration of MR images is more difficult than the alignment of scans from other imaging modalities as in Refs. [21,22,23]. We observe that in the particular case of MR brain images, the discrimination between noise and structure related gradients is very challenging, especially in cortical areas.…”

Section: Mr Images With Intensity Inhomogeneitiesmentioning

confidence: 94%

“…In this work 3 and t require only a single parameter, as opposed to the user specified regularisation values chosen in Ref. [23]. Explicitly, 3 and t are computed following an automatic choice based on total variation…”

Section: Numerical Stabilitymentioning

confidence: 99%

“…This seemingly small difference, the squaring of the cosine, causes outliers to bias the similarity measure and thus affects the robustness. Despite these properties of the squared cosine measure, it has been successfully utilised in the literature [21,22,23] for registering images that do not contain outliers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A robust similarity measure for volumetric image registration with outliers

Snape

Pszczółkowski

Zafeiriou

et al. 2016

Image and Vision Computing

View full text Add to dashboard Cite

Section: Mr Images With Intensity Inhomogeneitiesmentioning

confidence: 94%

Section: Numerical Stabilitymentioning

confidence: 99%

See 1 more Smart Citation

A robust similarity measure for volumetric image registration with outliers

Snape

Pszczółkowski

Zafeiriou

et al. 2016

Image and Vision Computing

View full text Add to dashboard Cite

“…In simulated results, matching using HOG descriptors performed well, but tests on real images lead to coarse and inaccurate depth maps. Using normalized gradients to compute global registration for medical images was proposed by Haber and Modersitzki [57] and extended Rühaak et al [58] and by Hodneland et al [59] among others. These works are intended to align medical images (e.g.…”

Section: Related Workmentioning

confidence: 99%

Generalized Assorted Camera Arrays: Robust Cross-Channel Registration and Applications

Holloway

Mitra

Koppal

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-One popular technique for multi-modal imaging is Generalized Assorted Pixels (GAP), where an assorted pixel array on the image sensor allows for multi-modal capture. Unfortunately GAP is limited in its applicability because of the need for multi-modal filters that are amenable with semiconductor fabrication processes and results in a fixed multi-modal imaging configuration. In this paper, we advocate for Generalized Assorted Camera (GAC) arrays for multi-modal imaging-i.e., a camera array with filters of different characteristics placed in front of each camera aperture. GAC provides us with three distinct advantages over GAP: ease of implementation, flexible application dependent imaging since filters are external and can be changed and depth information that can be used for enabling novel applications (e.g. post-capture refocusing). The primary challenge in GAC arrays is that since the different modalities are obtained from different viewpoints, there is a need for accurate and efficient cross-channel registration. Traditional approaches such as SSD, SAD, and mutual information all result in multimodal registration errors. Here, we propose a robust crosschannel matching cost function, based on aligning normalized gradients, that allows us to compute cross-channel sub-pixel correspondences for scenes exhibiting non-trivial geometry. We highlight the promise of GAC arrays with our cross-channel normalized gradient cost for several applications such as low light imaging, post-capture refocusing, skin perfusion imaging using RGB+NIR and hyperspectral imaging.

show abstract

“…After this initial work, the first similarity based solely on normalised gradients was proposed by Haber et al [10]. Since its introduction, this measure has been successfully utilised [11,12,13]. However, as we show in this paper, this cost functional is less robust to image inhomogeneities and is affected when gross outliers, such as lesions or tumours, are present in the images.…”

Section: Introductionmentioning

confidence: 99%

A robust similarity measure for nonrigid image registration with outliers

Pszczółkowski

Zafeiriou

Ledig

et al. 2014

2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

Nonrigid image registration is a widely used technique in medical imaging. While most methods work very well on images without pathologies or artefacts, there is a high need for improved robustness on images from pathological subjects and acquisitions with artefacts such as intensity inhomogeneity. In this paper, we propose a novel similarity measure based on normalised gradients for nonrigid registration, which is robust on images with intensity inhomogeneities or pathologies. We provide both theoretical and experimental proof of the robustness and evaluate the approach on manually segmented and simulated pathological images. Compared to normalised mutual information and to an alternative similarity also based on normalised gradients, we obtain significant overlap improvements for images with intensity inhomogeneities. We further confirm improved robustness on images with simulated tumours.

show abstract

A fully parallel algorithm for multimodal image registration using normalized gradient fields

Cited by 22 publications

References 10 publications

A robust similarity measure for volumetric image registration with outliers

A robust similarity measure for volumetric image registration with outliers

Generalized Assorted Camera Arrays: Robust Cross-Channel Registration and Applications

A robust similarity measure for nonrigid image registration with outliers

Contact Info

Product

Resources

About