Unifying Registration and Segmentation for Multi-sensor Images

Flach, Boris; Kask, Eeri; Schlesinger, Dmitrij; Skulish, Andriy

doi:10.1007/3-540-45783-6_24

Cited by 12 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of MR Imaging, physicians use 15 the terms "multi-parametric", "multi-modal" or "multi-spectral". In this field, there is an increasing interest in adapting image analysis techniques to multi-sensor schemes [1,2,3,4]. Many authors have worked on fusion and segmentation of multi-sensor images, and this technique proved to be efficient in many application fields, especially medical images analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Many authors have worked on fusion and segmentation of multi-sensor images, and this technique proved to be efficient in many application fields, especially medical images analysis. Flach 20 et al [4] focused on registration and segmentation of multi-modal images (MRI, CT scans, Ultrasound, etc. ), and proposed a generic method based on Gibbs probability distribution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Introducing spatial neighbourhood in Evidential C-Means for segmentation of multi-source images: Application to prostate multi-parametric MRI

2014

View full text Add to dashboard Cite

In this paper we introduce an evidential multi-source segmentation scheme for the extraction of prostate zonal anatomy using multi-parametric MRI. The Evidential C-Means (ECM) classifier was adapted to a segmentation scheme by introducing spatial neighbourhood-based relaxation step in its optimisation process. In order to do so, basic belief assignments on voxels membership were relaxed using distance-weighted combination of belief from spatial neighbours. For the application on prostate tissues, geometric a priori was modelled and used as an additional data source. Our method was first experimented on simulated images to prove the improvement brought to the ECM. A validation study of the segmentation method was then conducted on 31 patients MRI data. Each MRI was manually segmented by three independent expert radiologists, and an estimated truth was computed using STAPLE algorithm, for inter-observer variability was taken into account. This validation proved that segmentation obtained with our method is accurate and comparable to expert segmentation. We also show that our segmentation scheme enables to detect and highlight outliers, which could be interpreted by physicians as irregular tissues. The use of belief functions also provides additional information on borders between structures. We do believe these are sources of evidence that could help physicians/algorithms in characterising tissues and structures. 6 Courtesy of P. Puech and A. Iancu expert radiologists from University Hospital of Lille for contributing in this study.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Introducing spatial neighbourhood in Evidential C-Means for segmentation of multi-source images: Application to prostate multi-parametric MRI

2014

View full text Add to dashboard Cite

show abstract

“…Many authors have worked on fusion and segmentation of multisource images. Flach et al 20 focused on the registration and segmentation of multimodal images and proposed a generic method based on Gibbs probability distribution. Chun and Greenshields 21 also used Gibbs and Markov random fields (GRF and MRF) for a Bayesian classification of multi-echo MRI.…”

Section: Introductionmentioning

confidence: 99%

Zonal segmentation of prostate using multispectral magnetic resonance images

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Active contour approaches [6,29,18,30], markov random fields [10,28] and a Bayesian framework based on a maximum aposteriori probability (MAP) estimation [21] were proposed to formulate a joint segmentation and registration for different applications. However, all these approaches are restricted to lower dimensional parametric transformations.…”

Section: Introductionmentioning

confidence: 99%

A Variational Approach for Combined Segmentation and Estimation of Respiratory Motion in Temporal Image Sequences

Ehrhardt

Schmidt-Richberg²,

Handels

2007

2007 IEEE 11th International Conference on Computer Vision

View full text Add to dashboard Cite

In this paper a variational approach for the combined segmentation and registration of temporal image sequences is presented. The purpose of the proposed method is to estimate respiratory-induced organ motion in temporal CT image sequences and to segment a structure of interest simultaneously. In this model the segmentation of all images in the sequences is obtained by finding a non-linear registration to an initial segmentation in a reference image. A dense non-linear displacement field is estimated using image intensities and segmentation information in the images. Both problems (registration and segmentation) are formulated in a joint variational approach and solved simultaneously.A validation of the combined registration and segmentation approach is presented and demonstrates that the simultaneous solution of both problems improves the segmentation performance over a sequential application of the registration and segmentation steps.

show abstract

Unifying Registration and Segmentation for Multi-sensor Images

Cited by 12 publications

References 3 publications

Introducing spatial neighbourhood in Evidential C-Means for segmentation of multi-source images: Application to prostate multi-parametric MRI

Introducing spatial neighbourhood in Evidential C-Means for segmentation of multi-source images: Application to prostate multi-parametric MRI

Zonal segmentation of prostate using multispectral magnetic resonance images

A Variational Approach for Combined Segmentation and Estimation of Respiratory Motion in Temporal Image Sequences

Contact Info

Product

Resources

About