Yaoqin Xie

Intrafractional Motion of the Prostate During Hypofractionated Radiotherapy

PURPOSE To report the characteristics of prostate motion as tracked by the stereoscopic X-ray images of the implanted fiducials during hypofractionated radiotherapy with CyberKnife. METHODS AND MATERIALS Twenty-one patients with prostate cancer who were treated with CyberKnife between January 2005 and September 2007 were selected for this retrospective study. The CyberKnife uses a stereoscopic X-ray system to obtain the position of the prostate target through the monitoring of implanted gold fiducial markers. If there is a significant deviation, the treatment is paused while the patient is repositioned by moving the couch. The deviations calculated from X-ray images acquired within the time interval between two consecutive couch motions constitute a data set. RESULTS Included in the analysis were 427 data sets and 4,439 time stamps of X-ray images. The mean duration for each data set was 697 sec. At 30 sec, a motion >2 mm exists in about 5% of data sets. The percentage is increased to 8%, 11%, and 14% at 60 sec, 90 sec, and 120 sec, respectively. A similar trend exists for other values of prostate motion. CONCLUSIONS With proper monitoring and intervention during treatment, the prostate shifts observed among patients can be kept within the tracking range of the CyberKnife. On average, a sampling rate of approximately 40 sec between consecutive X-rays is acceptable to ensure submillimeter tracking. However, there is significant movement variation among patients, and a higher sampling rate may be necessary in some patients.

Objective assessment of deformable image registration in radiotherapy: A multi-institution study

The looming potential of deformable alignment tools to play an integral role in adaptive radiotherapy suggests a need for objective assessment of these complex algorithms. Previous studies in this area are based on the ability of alignment to reproduce analytically generated deformations applied to sample image data, or use of contours or bifurcations as ground truth for evaluation of alignment accuracy. In this study, a deformable phantom was embedded with 48 small plastic markers, placed in regions varying from high contrast to roughly uniform regional intensity, and small to large regional discontinuities in movement. CT volumes of this phantom were acquired at different deformation states. After manual localization of marker coordinates, images were edited to remove the markers. The resulting image volumes were sent to five collaborating institutions, each of which has developed previously published deformable alignment tools routinely in use. Alignments were done, and applied to the list of reference coordinates at the inhale state. The transformed coordinates were compared to the actual marker locations at exhale. A total of eight alignment techniques were tested from the six institutions. All algorithms performed generally well, as compared to previous publications. Average errors in predicted location ranged from 1.5 to 3.9 mm, depending on technique. No algorithm was uniformly accurate across all regions of the phantom, with maximum errors ranging from 5.1 to 15.4 mm. Larger errors were seen in regions near significant shape changes, as well as areas with uniform contrast but large local motion discontinuity. Although reasonable accuracy was achieved overall, the variation of error in different regions suggests caution in globally accepting the results from deformable alignment.

Scatter correction for cone-beam CT in radiation therapy

Cone-beam CT (CBCT) is being increasingly used in modern radiation therapy for patient setup and adaptive replanning. However, due to the large volume of x-ray illumination, scatter becomes a rather serious problem and is considered as one of the fundamental limitations of CBCT image quality. Many scatter correction algorithms have been proposed in literature, while a standard practical solution still remains elusive. In radiation therapy, the same patient is scanned repetitively during a course of treatment, a natural question to ask is whether one can obtain the scatter distribution on the first day of treatment and then use the data for scatter correction in the subsequent scans on different days. To realize this scatter removal scheme, two technical pieces must be in place: (i) A strategy to obtain the scatter distribution in on-board CBCT imaging and (ii) a method to spatially match a prior scatter distribution with the on-treatment CBCT projection data for scatter subtraction. In this work, simple solutions to the two problems are provided. A partially blocked CBCT is used to extract the scatter distribution. The x-ray beam blocker has a strip pattern, such that partial volume can still be accurately reconstructed and the whole-field scatter distribution can be estimated from the detected signals in the shadow regions using interpolation∕extrapolation. In the subsequent scans, the patient transformation is determined using a rigid registration of the conventional CBCT and the prior partial CBCT. From the derived patient transformation, the measured scatter is then modified to adapt the new on-treatment patient geometry for scatter correction. The proposed method is evaluated using physical experiments on a clinical CBCT system. On the Catphan©600 phantom, the errors in Hounsfield unit (HU) in the selected regions of interest are reduced from about 350 to below 50 HU; on an anthropomorphic phantom, the error is reduced from 15.7% to 5.4%. The proposed method is attractive in applications where a high CBCT image quality is critical, for example, dose calculation in adaptive radiation therapy.

Auto-propagation of contours for adaptive prostate radiation therapy

The purpose of this work is to develop an effective technique to automatically propagate contours from planning CT to cone beam CT (CBCT) to facilitate CBCT-guided prostate adaptive radiation therapy. Different from other disease sites, such as the lungs, the contour mapping here is complicated by two factors: (i) the physical one-to-one correspondence may not exist due to the insertion or removal of some image contents within the region of interest (ROI); and (ii) reduced contrast to noise ratio of the CBCT images due to increased scatter. To overcome these issues, we investigate a strategy of excluding the regions with variable contents by a careful design of a narrow shell signifying the contour of an ROI. For rectum, for example, a narrow shell with the delineated contours as its interior surface was constructed to avoid the adverse influence of the day-to-day content change inside the rectum on the contour mapping. The corresponding contours in the CBCT were found by warping the narrow shell through the use of BSpline deformable model. Both digital phantom experiments and clinical case testing were carried out to validate the proposed ROI mapping method. It was found that the approach was able to reliably warp the constructed narrow band with an accuracy better than 1.3 mm. For all five clinical cases enrolled in this study, the method yielded satisfactory results even when there were significant rectal content changes between the planning CT and CBCT scans. The overlapped area of the auto-mapped contours over 90% to the manually drawn contours is readily achievable. The proposed approach permits us to take advantage of the regional calculation algorithm yet avoiding the nuisance of rectum/bladder filling and provide a useful tool for adaptive radiotherapy of prostate in the future.

Feature-based rectal contour propagation from planning CT to cone beam CT.

The purpose of this work is to develop a novel feature-based registration strategy to automatically map the rectal contours from planning computed tomography (CT) (pCT) to cone beam CT (CBCT). The rectal contours were manually outlined on the pCT. A narrow band with the outlined contour as its interior surface was then constructed, so that we can exclude the volume inside the rectum in the registration process. The corresponding contour in the CBCT was found by using a feature-based registration algorithm, which consists of two steps: (1) automatically searching for control points in the pCT and CBCT based on the features of the surrounding tissue and matching the homologous control points using the scale invariance feature transformation; and (2) using the control points for a thin plate spline transformation to warp the narrow band and mapping the corresponding contours from pCT to CBCT. The proposed contour propagation technique is applied to digital phantoms and clinical cases and, in all cases, the contour mapping results are found to be clinically acceptable. For clinical cases, the method yielded satisfactory results even when there were significant rectal content changes between the pCT and CBCT scans. As a consequence, the accordance between the rectal volumes after deformable registration and the manually segmented rectum was found to be more than 90%. The proposed technique provides a powerful tool for adaptive radiotherapy of prostate, rectal, and gynecological cancers in the future.

Learning based alpha matting using support vector regression

Alpha matting refers to the problem of estimating the opacity mask of the foreground in an image. Many recent algorithms solve it with color samples or some local assumptions, causing artifacts when they fail to collect appropriate samples or the assumptions do not hold. In this paper, we treat alpha matting as a supervised learning problem and propose a new matting approach. Given the input image and a trimap (labeling some foreground/background pixels), we segment the unlabeled region into pieces and learn the relations between pixel features and alpha values for these pieces. We use support vector regression (SVR) in the learning process. To obtain better learning results, we design a training samples selection method and use adaptive parameters for SVR. Qualitative and quantitative evaluations on a matting benchmark show that our approach outperforms many recent algorithms in terms of accuracy.

A Novel Recursive Bayesian Learning-Based Method for the Efficient and Accurate Segmentation of Video With Dynamic Background

Segmentation of video with dynamic background is an important research topic in image analysis and computer vision domains. In this paper, we present a novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. In the algorithm, each frame pixel is represented as the layered normal distributions which correspond to different background contents in the scene. The layers are associated with a confident term and only the layers satisfy the given confidence which will be updated via the recursive Bayesian estimation. This makes learning of background motion trajectories more accurate and efficient. To improve the segmentation quality, the coarse foreground is obtained via simple background subtraction first. Then, a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions. Extensive experiments on a variety of public video datasets and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both segmentation accuracy and efficiency.

Evaluation of various speckle reduction filters on medical ultrasound images

At present, ultrasound is one of the essential tools for noninvasive medical diagnosis. However, speckle noise is inherent in medical ultrasound images and it is the cause for decreased resolution and contrast-to-noise ratio. Low image quality is an obstacle for effective feature extraction, recognition, analysis, and edge detection; it also affects image interpretation by doctor and the accuracy of computer-assisted diagnostic techniques. Thus, speckle reduction is significant and critical step in pre-processing of ultrasound images. Many speckle reduction techniques have been studied by researchers, but to date there is no comprehensive method that takes all the constraints into consideration. In this paper we discuss seven filters, namely Lee, Frost, Median, Speckle Reduction Anisotropic Diffusion (SRAD), Perona-Maliks Anisotropic Diffusion (PMAD) filter, Speckle Reduction Bilateral Filter (SRBF) and Speckle Reduction filter based on soft thresholding in the Wavelet transform. A comparative study of these filters has been made in terms of preserving the features and edges as well as effectiveness of de-noising.We computed five established evaluation metrics in order to determine which despeckling algorithm is most effective and optimal for real-time implementation. In addition, the experimental results have been demonstrated by filtered images and statistical data table.

An accurate and effective FMM-based approach for freehand 3D ultrasound reconstruction

Abstract Freehand three-dimensional ultrasound imaging is a highly attractive research area because it is capable of volumetric visualization and analysis of tissues and organs. The reconstruction algorithm plays a key role to the construction of three-dimensional ultrasound volume data with higher image quality and faster reconstruction speed. However, a systematic approach to such problem is still missing. A new fast marching method (FMM) for three-dimensional ultrasound volume reconstruction using the tracked and hand-held probe is proposed in this paper. Our reconstruction approach consists of two stages: bin-filling stage and hole-filling stage. Each pixel in the B-scan images is traversed and its intensity value is assigned to its nearest voxel in the bin-filling stage. For the efficient and accurate reconstruction, we present a new hole-filling algorithm based on the fast marching method. Our algorithm advances the interpolation boundary along its normal direction and fills the area closest to known voxel points in first, which ensure that the structural details of image can be preserved. Experimental results on both ultrasonic abdominal phantom and in vivo urinary bladder of human subject and comparisons with some popular algorithms are used to demonstrate its improvement in both reconstruction accuracy and efficiency.

Nonrigid Registration of Lung CT Images Based on Tissue Features

Nonrigid image registration is a prerequisite for various medical image process and analysis applications. Much effort has been devoted to thoracic image registration due to breathing motion. Recently, scale-invariant feature transform (SIFT) has been used in medical image registration and obtained promising results. However, SIFT is apt to detect blob features. Blobs key points are generally detected in smooth areas which may contain few diagnostic points. In general, diagnostic points used in medical image are often vessel crossing points, vascular endpoints, and tissue boundary points, which provide abundant information about vessels and can reflect the motion of lungs accurately. These points generally have high gradients as opposed to blob key points and can be detected by Harris. In this work, we proposed a hybrid feature detection method which can detect tissue features of lungs effectively based on Harris and SIFT. In addition, a novel method which can remove mismatched landmarks is also proposed. A series of thoracic CT images are tested by using the proposed algorithm, and the quantitative and qualitative evaluations show that our method is statistically significantly better than conventional SIFT method especially in the case of large deformation of lungs during respiration.