Fractional flow reserve (FFR) is the reference standard to identify flow-limiting coronary stenosis that requires revascularization. Accurate computation of FFR from coronary intravascular images is based on the precise reconstruction of the side branches. In this paper, a novel approach for segmentation of side branches in intravascular images is presented. The framework consists of an image-to-image translation module and two side branch region segmentation modules. By using the image-to-image translation module, information from intravascular optical coherence tomography (IVOCT) and intravascular ultrasound (IVUS) images is combined to improve the segmentation performance. The framework is trained on a total of 62475 IVOCT and 186110 IVUS images, and evaluated on an independent dataset which contains 9344 IVOCT images with 91 side branches and 39450 IVUS images with 128 side branches. The Dice coefficients of IVOCT and IVUS side branches segmentation are 0.935±0.039 and 0.856±0.038, respectively. The validation results of side branches detection are: Precision = 0.934, Recall = 0.923, F1Score = 0.929 in IVOCT, and 0.925, 0.868, 0.895 in IVUS, accordingly. Ablation studies demonstrate excellent efficiency in incorporating multi-modal information with our proposed image-to-image translation module.
High-Intensity Focused Ultrasound treatment combined with magnetic resonance technology (MRI-guided HIFU,
MRgHIFU) can protect the thermal ablation without harming the surrounding tissue by using MRI for target positioning,
where image registration plays an important role in the implementation of precise treatment. In this paper, we apply
three-dimension free-form deformation non-rigid registration on treatment plan amendments and tracking of breast
cancer. Free-form deformation based and demons based non-rigid registration are respectively employed on breast
cancer MR imaging required at different times before and after for comparison. The results of the experiments show that
the registration performed on the breast tumor image data with slight and larger deformation is effective, and the mutual
information of the ROI increased from 1.49 before registration to 1.53.
Various computerized features extracted from breast ultrasound images are useful in assessing the malignancy of breast tumors. However, the underlying relationship between the computerized features and tumor malignancy may not be linear in nature. We use the decision tree ensemble trained by the cost-sensitive boosting algorithm to approximate the target function for malignancy assessment and to reflect this relationship qualitatively. Partial dependence plots are employed to explore and visualize the effect of features on the output of the decision tree ensemble. In the experiments, 31 image features are extracted to quantify the sonographic characteristics of breast tumors. Patient age is used as an external feature because of its high clinical importance. The area under the receiver-operating characteristic curve of the tree ensembles can reach 0.95 with sensitivity of 0.95 (61/64) at the associated specificity 0.74 (77/104). The partial dependence plots of the four most important features are demonstrated to show the influence of the features on malignancy, and they are in accord with the empirical observations. The results can provide visual and qualitative references on the computerized image features for physicians, and can be useful for enhancing the interpretability of computer-aided diagnosis systems for breast ultrasound.
To accommodate the inter- and intra-fractional motion of internal organs in prostate cancer treatment, a large
margin (5mm-25mm) has often to be considered during radiation therapy planning. Normally, the inter-fractional
motion is more substantial than the intra-fractional counterpart. Therefore, the study of inter-fractional motion
pattern is of special interest for adaptive radiation therapy. Existing methods on organ motion analysis mainly
focus on the deviation of an organ's shape from its mean shape. The deviation information is helpful in choosing a
statistically proper margin, but is of limited use for plan adaptation. In this paper, we propose a new deformation
analysis method that can be directly used for plan adaptation. First, deformation estimation is accomplished by
a fast deformable registration method, which utilizes a contour based multi-grid strategy to register treatment
cone-beam CT (CBCT) images with planning CT images. Second, dominant deformation modes are extracted
by a novel deformation analysis approach. To be specific, a cooperative principal component analysis (PCA)
method is developed to analyze the deformation field in a coarse-to-fine strategy. The deformation modes are
initialized by applying PCA on the organs as a whole and refined by analyzing the individual organs subsequently.
The experimental results show that the organ motion can be well characterized by a few dominant deformation
modes. Based on the dominant modes, a corresponding set of dominant modal plans could be generated for
further optimization. Ultimately, an adaptive plan for each treatment can be obtained on-line while the margin
can be effectively reduced to minimize the unnecessary radiation dosage.
The shapes of malignant breast tumors are more complex than the benign lesions due to their nature of infiltration into
surrounding tissues. We investigated the efficacy of shape features and presented a method using polygon shape
complexity to improve the discrimination of benign and malignant breast lesions on ultrasound. First, 63 lesions (32
benign and 31 malignant) were segmented by K-way normalized cut with the priori rules on the ultrasound images.
Then, the shape measures were computed from the automatically extracted lesion contours. A polygon shape complexity
measure (SCM) was introduced to characterize the complexity of breast lesion contour, which was calculated from the
polygonal model of lesion contour. Three new statistical parameters were derived from the local integral invariant
signatures to quantify the local property of the lesion contour. Receiver operating characteristic (ROC) analysis was
carried on to evaluate the performance of each individual shape feature. SCM outperformed the other shape measures,
the area under ROC curve (AUC) of SCM was 0.91, and the sensitivity of SCM could reach 0.97 with the specificity
0.66. The measures of shape feature and margin feature were combined in a linear discriminant classifier. The
resubstitution and leave-one-out AUC of the linear discriminant classifier were 0.94 and 0.92, respectively. The
distinguishing ability of SCM showed that it could be a useful index for the clinical diagnosis and computer-aided
diagnosis to reduce the number of unnecessary biopsies.
In this paper, a structured light system based on synchronous scanning technology is developed for meeting the need of body surface acquisition. The proposed system is composed of a
fixed CCD camera, a fixed structured light projector and a mirror scanner. While the mirror is reflecting light stripes and scene images, the camera acquires a series of body section images from the scanner. After extracting the trace of laser stripes and calculating the relative 3-D coordinate of the illuminated pixels on the series of CCD images, the system can acquire the spatial profile of the
inspected body surface. Moreover, a prototype is developed according to the results from geometrical analysis mentioned above. The experiment data obtained from the scanning system are shown. This synchronized scanning system can be widely applied in the custom design, surgery navigation and the other optical measurement field in the future.
This paper presents a novel method for speckle reduction in ultrasonic images. Firstly, a particular filtering kernel is defined by decomposing the local rectangular neighborhood into asymmetric sticks pointing outside with variable orientation from the investigated pixel. Then the local mean and variance along each stick are calculated using a template based convolution algorithm. Finally, a pseudo-diffusion model is derived to diffuse the intensity averages of sticks into the central pixel, and a variance sensitive conductance functions is designed to adaptively control the diffusion strength in varying directions. The proposed method is in essence an integration of the linear boundary detection operator, i.e. stick technique, and the nonlinear diffusion model. In homogeneous regions, our method will act as a Gaussian like low pass filter, since the sticks are partially overlapped near the center, which implicitly assigns distance dependent weights to neighboring pixels. In heterogeneous regions, the information is expressed as many structures, which often occur as line boundaries or tube shapes in ultrasonic images, then our approach can encourage smoothing along the sticks falling inside the structures, and penalize blurring along the sticks across edges. The performance of our method is verified in experiments of both synthetic and clinical ultrasonic images. The results show that our method outperforms the existed filtering techniques in term of smoothing homogeneous regions, preserving resolvable features, enhancing weak edges and linear structures.
A 3D plenoptic function in the form of a mosaic image is presented in this paper. A sequence of plane images and relative cylinder panoramas are sampled original ly by a camera constrained on a line. Then, these original images are arranged in to a mosaic image by abstracting appropriate circles from the images and pasting them together. Pixels in the mosaic image are indexed in three parameters: camera location along the track line and two angles q and f. When rendering a novel view from a certain camera location, pixels in the view are mapped into view-rays of parameters q and f. Then, the values of view-rays are indexed from the mosaic image. Experimental results show that the proposed method is effective in rendering scene.
This paper discussed the approaches of wavelets for multiresulition in image matching. Using the hierarchical structure of wavelet transform, the match process is from the coarsest level to the finest one, refining and condensing the field of matching. Two types of special wavelet transform are explored and compared respectively. For vector-valued wavelets, an improved model of multiresolution matching is constituted to match the successive images in the case of exiting only rotation and translation between images. For complex-valued wavelets, a modified algorithm is presented to match image which has project transform between adjacent frames. Experiments for two groups of image sequences show that vector-valued wavelets and complex-valued wavelets used for image matching are available.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.