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

Wu, Jiaze; Gogna, Apoorva; Tan, Bien Soo; Ooi, London Lucien Peng Jin; Tian, Qi; Liu, Feng; Liu, Jimin

doi:10.1016/j.compmedimag.2014.11.013

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This observation would not affect the quantitative analysis of CEUS images. Further exploration and mapping the high‐dimensional respiratory motion image sequence into the low‐dimensional space using a manifold learning method and extracting the respiratory motion information would thus be worthwhile . The peak time of the contrast intensity in the reference image extraction was obtained by subjective estimation, which can be easily performed by ultrasonographers, and Rognin et al performed a quantitative analysis of CEUS image sequences using this method .…”

Section: Discussionmentioning

confidence: 99%

Respiratory motion correction for liver contrast‐enhanced ultrasound by automatic selection of a reference image

Zhang

Chen

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Purpose: Respiratory motion correction is necessary for the quantitative analysis of liver contrastenhanced ultrasound (CEUS) image sequences. Most respiratory motion correction methods are based on the dual mode of CEUS image sequences, including contrast and grayscale image sequences. Due to free-breathing motion, the acquired two-dimensional (2D) ultrasound cine might show the in-plane and out-of-plane motion of tumors. The registration of an entire 2D ultrasound contrast image sequence based on out-of-plane images is ineffective. For the respiratory motion correction of CEUS sequences, the reference image is usually considered the standard for the deletion of any out-of-plane images. Most methods used for the selection of the reference image are subjective in nature. Here, a quantitative selection method for an optimal reference image from CEUS image sequences in the B mode and contrast mode was explored. Methods: The original high-dimensional ultrasound grayscale image data were mapped into a twodimensional space using Laplacian Eigenmaps (LE), and K-means clustering was adopted. The center image of the larger cluster with a near-peak contrast intensity was considered the optimal ultrasound reference image. In the ultrasound grayscale image sequence, the images with the maximum correlations to the reference image in the same time interval were selected as the corrected image sequence. The effectiveness of this proposed method was then validated on 18 CEUS cases of VX2 tumors in rabbit livers. Results: Correction smoothed the time-intensity curves (TICs) extracted from the region of interest of the CEUS image sequences. Before correction, the average of the total mean structural similarity (TMSSIM) and the average of the mean correlation coefficient (MCC) from the image sequences were 0.45 AE 0.11 and 0.67 AE 0.16, respectively, and after correction, the average TMSSIM and MCC increased (P < 0.001) by 31% to 0.59 AE 0.11 and by 21% to 0.81 AE 0.11, respectively. The average deviation value (DV) index of the TICs from the image sequences prior to correction was 92.16 AE 18.12, and correction reduced the average to 31.71 AE 7.31. The average TMSSIM and MCC values after correction using the mean frame of the reference image (MBMFRI) were clearly lower than those after correction using the proposed method (P < 0.001). Moreover, the average DV after correction using the MBMFRI was obviously higher than that after correction using the proposed method (P < 0.001). Conclusions: The breathing frequency of rabbits is notably faster than that of human beings, but the proposed correction method could reduce the effect of the respiratory motion in the CEUS image sequences. The reference image was selected quantitatively, which could improve the accuracy of the quantitative analysis of rabbit liver CEUS sequences using the reference image method based on the current standard of manual selection and the MBMFRI. This easy-to-operate method can potentially be used in both animal studies and clinical applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Respiratory motion correction for liver contrast‐enhanced ultrasound by automatic selection of a reference image

Zhang

Chen

et al. 2019

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Therefore, a better solution is to track internal motion directly from intraprocedural ultrasound (US) images since internal anatomical structures usually have better correlation with the respiratory pattern than external markers. The methods extract the breathing signal using different motion estimation techniques, such as block similarity (BS), 3 manifold learning (ML), 4,5 and template matching (TM). 6,7 BS provides real-time signal tracking capability but is usually sensitive to image noises and artifacts and not directly relevant to breathing.…”

Section: Introductionmentioning

confidence: 99%

Technical Note: Automatic real‐time ultrasound tracking of respiratory signal using selective filtering and dynamic template matching

Cheng

Gogna

et al. 2015

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

Subject-specific and respiration-corrected 4D liver model from real-time ultrasound image sequences

Cheng

Gogna

et al. 2016

Computer Methods in Biomechanics and Biomedical Engineering: Im

View full text Add to dashboard Cite

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

Cited by 6 publications

References 22 publications

Respiratory motion correction for liver contrast‐enhanced ultrasound by automatic selection of a reference image

Respiratory motion correction for liver contrast‐enhanced ultrasound by automatic selection of a reference image

Technical Note: Automatic real‐time ultrasound tracking of respiratory signal using selective filtering and dynamic template matching

Subject-specific and respiration-corrected 4D liver model from real-time ultrasound image sequences

Contact Info

Product

Resources

About