Graphics Processing Unit-Accelerated Nonrigid Registration of MR Images to CT Images During CT-Guided Percutaneous Liver Tumor Ablations.

RATIONALE AND OBJECTIVES: Accuracy and speed are essential for the intraprocedural nonrigid magnetic resonance (MR) to computed tomography (CT) image registration in the assessment of tumor margins during CT-guided liver tumor ablations. Although both accuracy and speed can be improved by limiting the registration to a region of interest (ROI), manual contouring of the ROI prolongs the registration process substantially. To achieve accurate and fast registration without the use of an ROI, we combined a nonrigid registration technique on the basis of volume subdivision with hardware acceleration using a graphics processing unit (GPU). We compared the registration accuracy and processing time of GPU-accelerated volume subdivision-based nonrigid registration technique to the conventional nonrigid B-spline registration technique. MATERIALS AND METHODS: Fourteen image data sets of preprocedural MR and intraprocedural CT images for percutaneous CT-guided liver tumor ablations were obtained. Each set of images was registered using the GPU-accelerated volume subdivision technique and the B-spline technique. Manual contouring of ROI was used only for the B-spline technique. Registration accuracies (Dice similarity coefficient [DSC] and 95% Hausdorff distance [HD]) and total processing time including contouring of ROIs and computation were compared using a paired Student t test. RESULTS: Accuracies of the GPU-accelerated registrations and B-spline registrations, respectively, were 88.3 ± 3.7% versus 89.3 ± 4.9% (P = .41) for DSC and 13.1 ± 5.2 versus 11.4 ± 6.3 mm (P = .15) for HD. Total processing time of the GPU-accelerated registration and B-spline registration techniques was 88 ± 14 versus 557 ± 116 seconds (P < .000000002), respectively; there was no significant difference in computation time despite the difference in the complexity of the algorithms (P = .71). CONCLUSIONS: The GPU-accelerated volume subdivision technique was as accurate as the B-spline technique and required significantly less processing time. The GPU-accelerated volume subdivision technique may enable the implementation of nonrigid registration into routine clinical practice.

A Wavelet-packet-based approach for breast cancer classification.

In this paper, a new approach for non-invasive diagnosis of breast diseases is tested on the region of the breast without undue influence from the background and medically unnecessary parts of the images. We applied Wavelet packet analysis on the two-dimensional histogram matrices of a large number of breast images to generate the filter banks, namely sub-images. Each of 1250 resulting sub-images are used for computation of 32 two-dimensional histogram matrices. Then informative statistical features (e.g. skewness and kurtosis) are extracted from each matrix. The independent features, using 5-fold cross-validation protocol, are considered as the input sets of supervised classification. We observed that the proposed method improves the detection accuracy of Architectural Distortion disease compared to previous works and also is very effective for diagnosis of Spiculated Mass and MISC diseases.

Parallel nonlinear analysis of weighted brain's gray and white matter images for Alzheimer's dementia diagnosis.

In this study, we are proposing a novel nonlinear classification approach to discriminate between Alzheimer's Disease (AD) and a control group using T1-weighted and T2-weighted Magnetic Resonance Images (MRI's) of brain. Since T1-weighted images and T2-weighted images have inherent physical differences, obviously each of them has its own particular medical data and hence, we extracted some specific features from each. Then the variations of the relevant eigenvalues of the extracted features were tracked to pick up the most informative ones. The final features were assigned to two parallel systems to be nonlinearly categorized. Considering the fact that AD defects the white and gray regions of brain more than its black and marginal regions, and also since T1-weighted has more medical data of white and gray regions than T2-weighted images, we put optimal weights for the two outputs. Combination of these two results made the final decision of AD diagnosis system. The dataset includes 60 T1-weighted images and 60 T2-weighted images of normal and abnormal cases. The dataset which includes different cross-sections of the brain, after an accurate registration, was split to two groups of test set (40 percent of the dataset) and training set (60 percent of the dataset). The results demonstrate more than two thirds of accuracy in detection of normal and abnormal images.

Soft-tissue modeling and image-guided control of steerable needles.

In this paper, we exploit a fuzzy controller on a flexible bevel-tip needle to manipulate the needle's base in order to steer its tip in a preset obstacle-free and target-tracking path. Although the needle tends to follow a curvature path, spinning the needle with an extremely high rotational velocity makes it symmetric with respect to the tissue to follow a straight path. The fuzzy controller determines an appropriate spinning to generate the planned trajectory and, the closed-loop system tries to match the needle body with that trajectory. The swine's brain tissue model, extracted from an in-vitro experimental setup, is a non-homogenous, uncertain and fast-updatable network to model real tissues, needle and their interactions providing the essential visual feedback for the control system. The simulation results illustrate a precise path tracking of the bevel-tip needle based on the fuzzy controller's commands with two degrees of freedom.