Manifold learning for image-based breathing gating in ultrasound and MRI

Wachinger, Christian; Yiğitsoy, Mehmet; Rijkhorst, Erik-Jan; Navab, Nassir

doi:10.1016/j.media.2011.11.008

Cited by 81 publications

(67 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to be used for breathing gating from liver US images, manifold learning techniques have recently been applied for other gating situations, such as breathing-gated 4D CT imaging for the lung [31,32], breathing-gated fluoroscopic imaging for lung cancer radiotherapy [33], breathing-gated MR [22,34,35] and heartbeating-gated intravascular ultrasound (IVUS) [36]. Therefore, it is rationally expected that the proposed LTSA-based method in this paper is also able to find more value in other clinical fields.…”

Section: Discussionmentioning

confidence: 99%

“…purely image-based respiratory signal tracking [6,[17][18][19][20][21][22], which extract the respiratory signal directly from time-varying US liver images during pre-operative image acquisition or intra-operative imageguided procedures. These methods detect the respiration-related information by utilizing some specific image processing techniques to process an image region or the whole image.…”

Section: Introductionmentioning

confidence: 99%

“…This method uses the cumulated phase shift in the spectral domain of successive image frames as a measure of the respiratory motion. Wachinger et al [21,22] pointed and experimentally demonstrated that this method cannot well recover the respiratory information from US images and further proposed a manifold learning (ML) based respiratory signal tracking for 4D US imaging. The ML-based tracking method makes use of a classic nonlinear dimensionality reduction technique, Laplacian Eigenmaps (LEM) [23], to infer intrinsic low-dimensional structures (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A manifold learning method to detect respiratory signal from liver ultrasound images

Wu¹,

Gogna²,

Tan³

et al. 2015

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A manifold learning method to detect respiratory signal from liver ultrasound images

Wu¹,

Gogna²,

Tan³

et al. 2015

Computerized Medical Imaging and Graphics

View full text Add to dashboard Cite

“…Wachinger et al [7] proposed an automatic, image-based respiratory gating method for acquiring 4D breathing data with a wobbler US probe using Laplacian eigenmaps (LE). They later developed a technique for extraction of respiratory gating navigators from US images [8]. The method was demonstrated by performing the analysis on various datasets showing different organs and sections, for both 2D and three-dimensional (3D) US data over time.…”

Section: Introductionmentioning

confidence: 99%

Image-Based Real-Time Motion Gating of 3D Cardiac Ultrasound Images

Panayiotou

Peressutti

King

et al. 2017

Statistical Atlases and Computational Models of the Heart. Imaging and Modelling Challenges

View full text Add to dashboard Cite

Abstract. Cardiac phase determination of 3D ultrasound (US) imaging has numerous applications including intra-and inter-modality registration of US volumes, and gating of live images. We have developed a novel and potentially clinically useful real-time three-dimensional (3D) cardiac motion gating technique that facilitates and supports 3D USguided procedures. 0ur proposed real-time 3D-Masked-PCA technique uses the Principal Component Analysis (PCA) statistical method in combination with other image processing operations. Unlike many previously proposed gating techniques that are either retrospective and hence cannot be applied on live data, or can only gate respiratory motion, the technique is able to extract the phase of live 3D cardiac US data. It is also robust to varying image-content; thus it does not require specific structures to be visible in the US image. We demonstrate the application of the technique for the purposes of real-time 3D cardiac gating of trans-oesophageal US used in electrophysiology (EP) and trans-catheter aortic valve implantation (TAVI) procedures. The algorithm was validated using 2 EP and 8 TAVI clinical sequences (623 frames in total), from patients who underwent left atrial ablation and aortic valve replacement, respectively. The technique successfully located all of the 69 end-systolic and end-diastolic gating points in these sequences.

show abstract

“…However, this method is limited to moving objects that exhibit only translations. Manifold learning is also used to retrospectively sample ICUS sequences [16] or ultrasound and MR images [17].…”

Section: Introductionmentioning

confidence: 99%

Automated detection of cardiac phase from intracoronary ultrasound image sequences

Sun

Dong

2015

BME

View full text Add to dashboard Cite

Abstract. Intracoronary ultrasound (ICUS) is a widely used interventional imaging modality in clinical diagnosis and treatment of cardiac vessel diseases. Due to cyclic cardiac motion and pulsatile blood flow within the lumen, there exist changes of coronary arterial dimensions and relative motion between the imaging catheter and the lumen during continuous pullback of the catheter. The action subsequently causes cyclic changes to the image intensity of the acquired image sequence. Information on cardiac phases is implied in a non-gated ICUS image sequence. A 1-D phase signal reflecting cardiac cycles was extracted according to cyclical changes in local gray-levels in ICUS images. The local extrema of the signal were then detected to retrieve cardiac phases and to retrospectively gate the image sequence. Results of clinically acquired in vivo image data showed that the average inter-frame dissimilarity of lower than 0.1 was achievable with our technique. In terms of computational efficiency and complexity, the proposed method was shown to be competitive when compared with the current methods. The average frame processing time was lower than 30 ms. We effectively reduced the effect of image noises, useless textures, and non-vessel region on the phase signal detection by discarding signal components caused by non-cardiac factors.

show abstract

Manifold learning for image-based breathing gating in ultrasound and MRI

Cited by 81 publications

References 35 publications

A manifold learning method to detect respiratory signal from liver ultrasound images

A manifold learning method to detect respiratory signal from liver ultrasound images

Image-Based Real-Time Motion Gating of 3D Cardiac Ultrasound Images

Automated detection of cardiac phase from intracoronary ultrasound image sequences

Contact Info

Product

Resources

About