-
[show abstract]
[hide abstract]
ABSTRACT: Accurate registration of 18F-FDG PET (positron emission tomography) and CT (computed tomography) images has important clinical significance in radiation oncology. PET and CT images are acquired from 18F-FDG PET/CT scanner, but the two acquisition processes are separate and take a long time. As a result, there are position errors in global and deformable errors in local caused by respiratory movement or organ peristalsis. The purpose of this work was to implement and validate a deformable CT to PET image registration method in esophageal cancer to eventually facilitate accurate positioning the tumor target on CT, and improve the accuracy of radiation therapy. Global registration was firstly utilized to preprocess position errors between PET and CT images, achieving the purpose of aligning these two images on the whole. Demons algorithm, based on optical flow field, has the features of fast process speed and high accuracy, and the gradient of mutual information-based demons (GMI demons) algorithm adds an additional external force based on the gradient of mutual information (GMI) between two images, which is suitable for multimodality images registration. In this paper, GMI demons algorithm was used to achieve local deformable registration of PET and CT images, which can effectively reduce errors between internal organs. In addition, to speed up the registration process, maintain its robustness, and avoid the local extremum, multiresolution image pyramid structure was used before deformable registration. By quantitatively and qualitatively analyzing cases with esophageal cancer, the registration scheme proposed in this paper can improve registration accuracy and speed, which is helpful for precisely positioning tumor target and developing the radiation treatment planning in clinical radiation therapy application.
Journal of Applied Clinical Medical Physics 01/2013; 14(1):3931. · 1.29 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Mutual information (MI) is a well-accepted similarity measure for image registration in medical systems. However, MI-based registration faces the challenges of high computational complexity and a high likelihood of being trapped into local optima due to an absence of spatial information. In order to solve these problems, multi-scale frameworks can be used to accelerate registration and improve robustness. Traditional Gaussian pyramid representation is one such technique but it suffers from contour diffusion at coarse levels which may lead to unsatisfactory registration results. In this work, a new multi-scale registration framework called edge preserving multiscale registration (EPMR) was proposed based upon an edge preserving total variation L1 norm (TV-L1) scale space representation. TV-L1 scale space is constructed by selecting edges and contours of images according to their size rather than the intensity values of the image features. This ensures more meaningful spatial information with an EPMR framework for MI-based registration. Furthermore, we design an optimal estimation of the TV-L1 parameter in the EPMR framework by training and minimizing the transformation offset between the registered pairs for automated registration in medical systems. We validated our EPMR method on both simulated mono- and multi-modal medical datasets with ground truth and clinical studies from a combined positron emission tomography/computed tomography (PET/CT) scanner. We compared our registration framework with other traditional registration approaches. Our experimental results demonstrated that our method outperformed other methods in terms of the accuracy and robustness for medical images. EPMR can always achieve a small offset value, which is closer to the ground truth both for mono-modality and multi-modality, and the speed can be increased 5-8% for mono-modality and 10-14% for multi-modality registration under the same condition. Furthermore, clinical application by adaptive gross tumor volume re-contouring for clinical PET/CT image-guided radiation therapy throughout the course of radiotherapy is also studied, and the overlap between the automatically generated contours for the CT image and the contours delineated by the oncologist used for the planning system are on average 90%.
Physics in Medicine and Biology 07/2012; 57(16):5187-204. · 2.83 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Purpose: In order to register 4DCT efficiently, we propose an improved deformable registration algorithm based on improved multi-resolution demons strategy to improve the efficiency of the algorithm. Methods: 4DCT images of lung cancer patients are collected from a General Electric Discovery ST CT scanner from our cancer hospital. All of the images are sorted into groups and reconstructed according to their phases, and eachrespiratory cycle is divided into 10 phases with the time interval of 10%. Firstly, in our improved demons algorithm we use gradients of both reference and floating images as deformation forces and also redistribute the forces according to the proportion of the two forces. Furthermore, we introduce intermediate variable to cost function for decreasing the noise in registration process. At the same time, Gaussian multi-resolution strategy and BFGS method for optimization are used to improve speed and accuracy of the registration. To validate the performance of the algorithm, we register the previous 10 phase-images. We compared the difference of floating and reference images before and after registered where two landmarks are decided by experienced clinician. We registered 10 phase-images of 4D-CT which is lung cancer patient from cancer hospital and choose images in exhalationas the reference images, and all other images were registered into the reference images. Results: This method has a good accuracy demonstrated by a higher similarity measure for registration of 4D-CT and it can register a large deformation precisely. Finally, we obtain the tumor target achieved by the deformation fields using proposed method, which is more accurately than the internal margin (IM) expanded by the Gross Tumor Volume (GTV). Furthermore, we achieve tumor and normal tissue tracking and dose accumulation using 4DCT data. Conclusions: An efficient deformable registration algorithm was proposed by using multi-resolution demons algorithm for 4DCT.
Medical Physics 06/2012; 39(6):3672-3673. · 2.83 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The use of the functional PET information from PET-CT scans to improve liver segmentation from low-contrast CT data is yet to be fully explored. In this paper, we fully utilize PET information to tackle challenging liver segmentation issues including (1) the separation and removal of the surrounding muscles from liver region of interest (ROI), (2) better localization and mapping of the probabilistic atlas onto the low-contrast CT for a more accurate tissue classification, and (3) an improved initial estimation of the liver ROI to speed up the convergence of the expectation-maximization (EM) algorithm for the Gaussian distribution mixture model under the guidance of a probabilistic atlas. The primary liver extraction from the PET volume provides a simple mechanism to avoid the complicated pre-processing of feature extraction as used in the existing liver CT segmentation methods. It is able to guide the probabilistic atlas to better conform to the CT liver region and hence helps to overcome the challenge posed by liver shape variability. Our proposed method was evaluated against manual segmentation by experienced radiologists. Experimental results on 35 clinical PET-CT studies demonstrated that our method is accurate and robust in automated normal liver segmentation.
Computer methods and programs in biomedicine 08/2011; 107(2):164-74. · 1.14 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we propose an automated liver segmentation method to overcome the challenging issues of high degree of variations in liver shape / size and similar density distribution shared by the liver and its surrounding structures. To improve the performance of conventional statistical shape model for liver segmentation, in our method, the signed distance function is utilized so that the landmarks correspondence is not required when performing the principle component analysis. We improve the Chan-Vese model to bind the shape energy and local intensity feature to evolve the surface both globally and locally toward the closest shape driven by the PCA. In our experiments, 20 clinical CT studies were used for training and 25 clinical CT studies were used for validation. Our experimental results demonstrate that our method can achieve accurate and robust liver segmentation from both of low-contrast and high-contrast CT images.
Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:3415-8.
-
IEEE Transactions on Information Technology in Biomedicine. 01/2011; 15:691-702.
-
[show abstract]
[hide abstract]
ABSTRACT: Incorporating of daily cone-beam computer tomography (CBCT) image into online radiation therapy process can achieve adaptive image-guided radiation therapy (AIGRT). Registration of planning CT (PCT) and daily CBCT are the key issues in this process. In our work, a new multiscale deformable registration method is proposed by combining edge-preserving scale space with the multilevel free-form deformation (FFD) grids for CBCT-based AIGRT system. The edge-preserving scale space, which is able to select edges and contours of images according to their geometric size, is derived from the total variation model with the L1 norm (TV-L1). At each scale, despite the noise and contrast resolution differences between the PCT and CBCT, the selected edges and contours are sufficiently strong to drive the deformation using the FFD grid, and the edge-preserving property ensures more meaningful spatial information for mutual information (MI)-based registration. At last, the deformation fields are gained by a coarse to fine manner. Furthermore, in consideration of clinical application we designed an optimal estimation of the TV-L1 parameters by minimizing the defined offset function for automated registration. Six types of patients are studied in our work, including rectum, prostate, lung, H&N (head and neck), breast, and chest cancer patients. The experiment results demonstrate the significance of the proposed method both quantitatively with ground truth known and qualitatively with ground truth unknown. The applications for AIGRT, including adaptive deformable recontouring and redosing, and DVH (dose volume histogram) analysis in the course of radiation therapy are also studied.
Journal of Applied Clinical Medical Physics 01/2011; 12(4):3527. · 1.29 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: Registration of planning images with daily images is an important component for adaptive radiation therapy (ART). In this paper, a multiscale deformable registration framework is proposed by combining edge preserving scale space with the free form deformation (FFD) for registration of planning computed tomography (CT) images with daily cone beam CT (CBCT) images. The edge preserving scale space which is able to select edges and contours of an image according to their geometric size is derived from the total variation model with the L1 norm (TV-L1). At each scale, the selected edges and contours are sufficiently strong to drive the deformation using the FFD grid, then the deformation fields are gained by a coarse to fine manner. Furthermore, for automated registration we design an optimal estimation of the TV-L1 parameter by minimizing the defined offset. The experiments on CT and CBCT images show accuracy and robustness when compared to traditional methods.
Image Processing (ICIP), 2010 17th IEEE International Conference on; 10/2010
-
[show abstract]
[hide abstract]
ABSTRACT: Mutual information (MI) is a well accepted similarity measure for image registration. However, MI based registration faces the challenges of high computational complexity, low registration efficiency and high likelihood of being trapped into local optima due to an absence of spatial information. In this paper, we propose a new multiscale registration framework based upon an edge preserving total variation L1 norm (TV-L1) scale space representation. Our scale space is constructed by selecting edges and contours of an image according to the geometric size rather than the intensity values of the image features. This ensures more meaningful spatial information for MI based registration. Furthermore, we design an optimal estimation of the TV-L1 parameter in our framework by training and minimizing the transformation offset between the images for automated registration. We validated our method on both simulated mono- and multi-modal medical datasets with ground truth and temporal clinical studies from a combined PET/CT scanner.
Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on; 08/2010
-
Proceedings of the International Conference on Image Processing, ICIP 2010, September 26-29, Hong Kong, China; 01/2010
