Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (8 results)

  • Thesis
  • Peer Reviewed
UCLA Electronic Theses and Dissertations (2016)

Medical images are being increasingly used and facilitate various applications such as computer aided diagnosis, quantitative functional analysis, treatment planning and image-guided interventions. In those applications, multiple images are usually acquired from multiple/single subjects at different time points or in real-time for comparison, progression monitoring or guidance and management during interventions. Such acquisition offers a unique opportunity to study patient anatomy in the context of multiple realizations, and permits both the construction of patient (or sub-population cohort) specific context and motion analysis. To fully benefit from those applications, shape and motion analysis are needed. The former can be considered in the general research area of shape estimation and segmentation from an image processing perspective; the latter addresses motion estimation and prediction, two problems of ultimate clinical importance. These are challenging questions, especially when images are acquired with different modalities, subject to low SNR and/or intensity and contrast variations as a consequence of contrast dynamics. It is also a well-admitted challenge to predict anatomical motion due to the complexity of motion pattern combined with the curse of dimensionality from high-dimensional anatomy representations. To this end, this thesis aims to address those challenges. One key and fundamental component of our development is the extraction of robust shape features from images, based on the observation that boundaries/shapes are usually better preserved and more consistent even under changing or challenging imaging conditions. The main contribution of this thesis is by developing variational frameworks to extract shape features automatically and reliably and building proper low-dimensional embeddings, based on which motion estimation and prediction methods are developed.

The first part of this thesis focuses on solving motion estimation/tracking based on extracting and registering shape features. We have developed and validated a robust motion estimation method, by registering shape features extracted from a variational segmentation method. Extracted with length and temporal shape regularizations, the shape features are robust to intensity and contrast variations and low SNR. The continuous representation of the shape features further eliminates the needs and risks of large errors of building and registering explicit correspondences among features. To evaluate its clinical value, we have applied the proposed method to compensate respiratory motion in MR urography, and quantitatively evaluated its performance on estimating functional renal parameters. To further complement the shape extraction step in the proposed method, while also serving as a fundamental methodology development, we have further developed a unified segmentation framework by incorporating a novel sparse composite shape prior, which is especially advantageous for shape extraction when images are subject to high noise and/or with signal voids. We have evaluated and shown clinical values of this framework in solving various challenging segmentation problems including corpus callosum segmentation in 2D MR, liver segmentation in 3D CT and left ventricle segmentation in Cine MRI.

We then address the shape extraction problem when point clouds are acquired using photogrammetry systems in image-guided radiotherapy. We represent and reconstruct continuous shapes/surfaces from acquired point clouds by minimizing a regularized variational functional, such that the resulting surfaces are robust to noise and missing measurements. To further speed-up the reconstruction, we have developed a real-time surface reconstruction method based upon the overcomplete nature of the respiratory motion, by representing each point cloud as a sparse combination of training set and propagate such linear relation to the continuous surface space.

Finally, we investigate how to efficiently model temporal dynamics of high-dimensional motion by learning their low-dimensional embeddings. We have developed a unified prediction framework on high-dimensional states by applying manifold learning to construct a low-dimensional feature sub-manifold, where efficient prediction can be performed. A pre-image estimation method is also explored to map the predicted value in the sub-manifold to its original high-dimensional space.

Our developed methodologies for shape and motion analysis are general and their clinical values are beyond the DCE-MRI and image-guided radiotherapy as demonstrated in this thesis. We also expect the development of robust shape descriptors to have substantial impact in the general field of computer vision when motion estimation and prediction are needed, especially when images captured are under non-ideal conditions.

    Cover page: Shape and motion analysis in medical imaging
    • Article
    • Peer Reviewed
    UCLA Previously Published Works (2015)
    Image segmentation plays an essential role in many medical applications. Low SNR conditions and various artifacts makes its automation challenging. To achieve robust and accurate segmentation results, a good approach is to introduce proper shape priors. In this study, we present a unified variational segmentation framework that regularizes the target shape with a level-set based sparse composite prior. When the variational problem is solved with a block minimization/decent scheme, the regularizing impact of the sparse composite prior can be observed to adjust to the most recent shape estimate, and may be interpreted as a 'dynamic' shape prior, yet without compromising convergence thanks to the unified energy framework. The proposed method was applied to segment corpus callosum from 2D MR images and liver from 3D CT volumes. Its performance was evaluated using Dice Similarity Coefficient and Hausdorff distance, and compared with two benchmark level-set based segmentation methods. The proposed method has achieved statistically significant higher accuracy in both experiments and avoided faulty inclusion/exclusion of surrounding structures with similar intensities, as opposed to the benchmark methods.
      Cover page: A unified variational segmentation framework with a level-set based sparse composite shape prior
      • Article
      • Peer Reviewed
      UCLA Previously Published Works (2013)

      Purpose

      To develop a nonrigid motion estimation method that is robust to heterogeneous intensity inconsistencies amongst the image pairs or image sequence.

      Methods

      Intensity and contrast variations, as in dynamic contrast enhanced magnetic resonance imaging, present a considerable challenge to registration methods based on general discrepancy metrics. In this study, the authors propose and validate a novel method that is robust to such variations by utilizing shape features. The geometry of interest (GOI) is represented with a flexible zero level set, segmented via well-behaved regularized optimization. The optimization energy drives the zero level set to high image gradient regions, and regularizes it with area and curvature priors. The resulting shape exhibits high consistency even in the presence of intensity or contrast variations. Subsequently, a multiscale nonrigid registration is performed to seek a regular deformation field that minimizes shape discrepancy in the vicinity of GOIs.

      Results

      To establish the working principle, realistic 2D and 3D images were subject to simulated nonrigid motion and synthetic intensity variations, so as to enable quantitative evaluation of registration performance. The proposed method was benchmarked against three alternative registration approaches, specifically, optical flow, B-spline based mutual information, and multimodality demons. When intensity consistency was satisfied, all methods had comparable registration accuracy for the GOIs. When intensities among registration pairs were inconsistent, however, the proposed method yielded pronounced improvement in registration accuracy, with an approximate fivefold reduction in mean absolute error (MAE = 2.25 mm, SD = 0.98 mm), compared to optical flow (MAE = 9.23 mm, SD = 5.36 mm), B-spline based mutual information (MAE = 9.57 mm, SD = 8.74 mm) and mutimodality demons (MAE = 10.07 mm, SD = 4.03 mm). Applying the proposed method on a real MR image sequence also provided qualitatively appealing results, demonstrating good feasibility and applicability of the proposed method.

      Conclusions

      The authors have developed a novel method to estimate the nonrigid motion of GOIs in the presence of spatial intensity and contrast variations, taking advantage of robust shape features. Quantitative analysis and qualitative evaluation demonstrated good promise of the proposed method. Further clinical assessment and validation is being performed.
        Cover page: Estimating nonrigid motion from inconsistent intensity with robust shape features
        • Article
        • Peer Reviewed
        UCLA Previously Published Works (2014)

        Purpose

        To incorporate a newly developed shape-based motion estimation scheme into magnetic resonance urography (MRU) and verify its efficacy in facilitating quantitative functional analysis.

        Methods

        The authors propose a motion compensation scheme in MRU that consists of three sequential modules: MRU image acquisition, motion compensation, and quantitative functional analysis. They designed two sets of complementary experiments to evaluate the performance of the proposed method. In the first experiment, dynamic contrast enhanced (DCE) MR images were acquired from three sedated subjects, from which clinically valid estimates were derived and served as the "ground truth." Physiologically sound motion was then simulated to synthesize image sequences influenced by respiratory motion. Quantitative assessment and comparison were performed on functional estimates of Patlak number, glomerular filtration rate, and Patlak differential renal function without and with motion compensation against the ground truth. In the second experiment, the authors acquired a temporal series of noncontrast MR images under free breathing from a healthy adult subject. The performance of the proposed method on compensating real motion was evaluated by comparing the standard deviation of the obtained temporal intensity curves before and after motion compensation.

        Results

        On DCE-MR images with simulated motion, the generated relative enhancement curves exhibited large perturbations and the Patlak numbers of the left and right kidney were significantly underestimated up to 35% and 34%, respectively, compared with the ground truth. After motion compensation, the relative enhancement curves exhibited much less perturbations and Patlak estimation errors reduced within 3% and 4% for the left and right kidneys, respectively. On clinical free-breathing MR images, the temporal intensity curves exhibited significantly reduced variations after motion compensation, with standard deviation decreased from 30.3 and 38.2 to 8.3 and 11.7 within two manually selected regions of interest, respectively.

        Conclusions

        The developed motion compensation method has demonstrated its ability to facilitate quantitative MRU functional analysis, with improved accuracy of pharmacokinetic modeling and quantitative parameter estimations. Future work will consider performing more intensive clinical verifications with sophisticated pharmacokinetic models and generalizing the proposed method to other quantitative DCE analysis, such as on liver or prostate function.
          Cover page: Shape‐based motion correction in dynamic contrast‐enhanced MRI for quantitative assessment of renal function
          • Article
          • Peer Reviewed
          UCLA Previously Published Works (2016)
          The development of high-dimensional imaging systems in image-guided radiotherapy provides important pathways to the ultimate goal of real-time full volumetric motion monitoring. Effective motion management during radiation treatment usually requires prediction to account for system latency and extra signal/image processing time. It is challenging to predict high-dimensional respiratory motion due to the complexity of the motion pattern combined with the curse of dimensionality. Linear dimension reduction methods such as PCA have been used to construct a linear subspace from the high-dimensional data, followed by efficient predictions on the lower-dimensional subspace. In this study, we extend such rationale to a more general manifold and propose a framework for high-dimensional motion prediction with manifold learning, which allows one to learn more descriptive features compared to linear methods with comparable dimensions. Specifically, a kernel PCA is used to construct a proper low-dimensional feature manifold, where accurate and efficient prediction can be performed. A fixed-point iterative pre-image estimation method is used to recover the predicted value in the original state space. We evaluated and compared the proposed method with a PCA-based approach on level-set surfaces reconstructed from point clouds captured by a 3D photogrammetry system. The prediction accuracy was evaluated in terms of root-mean-squared-error. Our proposed method achieved consistent higher prediction accuracy (sub-millimeter) for both 200 ms and 600 ms lookahead lengths compared to the PCA-based approach, and the performance gain was statistically significant.
            Cover page: Prediction of high-dimensional states subject to respiratory motion: a manifold learning approach
            • Article
            • Peer Reviewed
            UCLA Previously Published Works (2016)

            Purpose

            To develop a robust and real-time surface reconstruction method on point clouds captured from a 3D surface photogrammetry system.

            Methods

            The authors have developed a robust and fast surface reconstruction method on point clouds acquired by the photogrammetry system, without explicitly solving the partial differential equation required by a typical variational approach. Taking advantage of the overcomplete nature of the acquired point clouds, their method solves and propagates a sparse linear relationship from the point cloud manifold to the surface manifold, assuming both manifolds share similar local geometry. With relatively consistent point cloud acquisitions, the authors propose a sparse regression (SR) model to directly approximate the target point cloud as a sparse linear combination from the training set, assuming that the point correspondences built by the iterative closest point (ICP) is reasonably accurate and have residual errors following a Gaussian distribution. To accommodate changing noise levels and/or presence of inconsistent occlusions during the acquisition, the authors further propose a modified sparse regression (MSR) model to model the potentially large and sparse error built by ICP with a Laplacian prior. The authors evaluated the proposed method on both clinical point clouds acquired under consistent acquisition conditions and on point clouds with inconsistent occlusions. The authors quantitatively evaluated the reconstruction performance with respect to root-mean-squared-error, by comparing its reconstruction results against that from the variational method.

            Results

            On clinical point clouds, both the SR and MSR models have achieved sub-millimeter reconstruction accuracy and reduced the reconstruction time by two orders of magnitude to a subsecond reconstruction time. On point clouds with inconsistent occlusions, the MSR model has demonstrated its advantage in achieving consistent and robust performance despite the introduced occlusions.

            Conclusions

            The authors have developed a fast and robust surface reconstruction method on point clouds captured from a 3D surface photogrammetry system, with demonstrated sub-millimeter reconstruction accuracy and subsecond reconstruction time. It is suitable for real-time motion tracking in radiotherapy, with clear surface structures for better quantifications.
              Cover page: A robust real‐time surface reconstruction method on point clouds captured from a 3D surface photogrammetry system
              • Article
              • Peer Reviewed
              UCLA Previously Published Works (2015)

              Purpose

              To accurately and efficiently reconstruct a continuous surface from noisy point clouds captured by a surface photogrammetry system (VisionRT).

              Methods

              The authors have developed a level-set based surface reconstruction method on point clouds captured by a surface photogrammetry system (VisionRT). The proposed method reconstructs an implicit and continuous representation of the underlying patient surface by optimizing a regularized fitting energy, offering extra robustness to noise and missing measurements. By contrast to explicit/discrete meshing-type schemes, their continuous representation is particularly advantageous for subsequent surface registration and motion tracking by eliminating the need for maintaining explicit point correspondences as in discrete models. The authors solve the proposed method with an efficient narrowband evolving scheme. The authors evaluated the proposed method on both phantom and human subject data with two sets of complementary experiments. In the first set of experiment, the authors generated a series of surfaces each with different black patches placed on one chest phantom. The resulting VisionRT measurements from the patched area had different degree of noise and missing levels, since VisionRT has difficulties in detecting dark surfaces. The authors applied the proposed method to point clouds acquired under these different configurations, and quantitatively evaluated reconstructed surfaces by comparing against a high-quality reference surface with respect to root mean squared error (RMSE). In the second set of experiment, the authors applied their method to 100 clinical point clouds acquired from one human subject. In the absence of ground-truth, the authors qualitatively validated reconstructed surfaces by comparing the local geometry, specifically mean curvature distributions, against that of the surface extracted from a high-quality CT obtained from the same patient.

              Results

              On phantom point clouds, their method achieved submillimeter reconstruction RMSE under different configurations, demonstrating quantitatively the faith of the proposed method in preserving local structural properties of the underlying surface in the presence of noise and missing measurements, and its robustness toward variations of such characteristics. On point clouds from the human subject, the proposed method successfully reconstructed all patient surfaces, filling regions where raw point coordinate readings were missing. Within two comparable regions of interest in the chest area, similar mean curvature distributions were acquired from both their reconstructed surface and CT surface, with mean and standard deviation of (μrecon=-2.7×10(-3) mm(-1), σrecon=7.0×10(-3) mm(-1)) and (μCT=-2.5×10(-3) mm(-1), σCT=5.3×10(-3) mm(-1)), respectively. The agreement of local geometry properties between the reconstructed surfaces and the CT surface demonstrated the ability of the proposed method in faithfully representing the underlying patient surface.

              Conclusions

              The authors have integrated and developed an accurate level-set based continuous surface reconstruction method on point clouds acquired by a 3D surface photogrammetry system. The proposed method has generated a continuous representation of the underlying phantom and patient surfaces with good robustness against noise and missing measurements. It serves as an important first step for further development of motion tracking methods during radiotherapy.
                Cover page: A continuous surface reconstruction method on point cloud captured from a 3D surface photogrammetry system
                • Article
                • Peer Reviewed
                UCLA Previously Published Works (2017)

                Purpose

                Respiratory motion prediction using an artificial neural network (ANN) was integrated with pseudocontinuous arterial spin labeling (pCASL) MRI to allow free-breathing perfusion measurements in the kidney. In this study, we evaluated the performance of the ANN to accurately predict the location of the kidneys during image acquisition.

                Methods

                A pencil-beam navigator was integrated with a pCASL sequence to measure lung/diaphragm motion during ANN training and the pCASL transit delay. The ANN algorithm ran concurrently in the background to predict organ location during the 0.7-s 15-slice acquisition based on the navigator data. The predictions were supplied to the pulse sequence to prospectively adjust the axial slice acquisition to match the predicted organ location. Additional navigators were acquired immediately after the multislice acquisition to assess the performance and accuracy of the ANN. The technique was tested in eight healthy volunteers.

                Results

                The root-mean-square error (RMSE) and mean absolute error (MAE) for the eight volunteers were 1.91 ± 0.17 mm and 1.43 ± 0.17 mm, respectively, for the ANN. The RMSE increased with transit delay. The MAE typically increased from the first to last prediction in the image acquisition. The overshoot was 23.58% ± 3.05% using the target prediction accuracy of ± 1 mm.

                Conclusion

                Respiratory motion prediction with prospective motion correction was successfully demonstrated for free-breathing perfusion MRI of the kidney. The method serves as an alternative to multiple breathholds and requires minimal effort from the patient.
                  Cover page: Respiratory motion prediction and prospective correction for free‐breathing arterial spin‐labeled perfusion MRI of the kidneys
                  Top