Canon Medical Systems Corporation

Toshiba Medical Systems Corporation

University of Central Florida Research Foundation Inc

Qiulin Tang

Zhou Yu

Jian Zhou

Satoru Nakanishi

Liang Cai

Wenli Wang

Alexander Katsevich

Gengsheng Lawrence Zeng

Marco Razeto

Yujie Lu

James Matthews

Thomas Labno

Ruoqiao Zhang

Chih-chieh Liu

A method, system, and computer readable medium to compensate for consecutive missing views in Computed Tomography (CT) reconstruction. By utilizing at least one complementary ray from a previous or subsequent view, the missing view(s) can be filled in. When plural complementary rays exist, a linear or non-linear combination of rays can be used to fill in the missing views, and the weights used in the combination may be smoothed to prevent over-emphasis of the replacement views.

Method and system to compensate for consecutive missing views in computed tomography (CT) reconstruction

An information processing method controls a CT scanner such that the method includes, but is not limited to, determining an X-ray irradiation period from an electrocardiogram acquired from an electrocardiography device attached to a living object to be imaged, by processing the electrocardiogram at multiple different cardiac phases; performing, by controlling a CT gantry including and rotatably supporting an X-ray source and an X-ray detector, a diagnostic CT scan in the determined X-ray irradiation period, of at least a part of the heart region, to obtain a CT image; and causing a display unit to display the obtained CT image. The method can be performed at least by an information processing apparatus including processing circuitry and/or computer instructions stored in a non-transitory computer readable storage medium for performing the method.

Information processing method, medical image diagnostic apparatus, and information processing system for detecting a quiescent cardiac phase

Data acquired from a scan of an object can be decomposed into frequency components. The frequency components can be input into a trained model to obtain processed frequency components. These processed frequency components can be composed and used to generate a final image. The trained model can be trained, independently or dependently, using frequency components covering the same frequencies as the to-be-processed frequency components. In addition, organ specific processing can be enabled by training the trained model using image and/or projection datasets of the specific organ.

Projection based deep learning with frequency splitting for computed tomography

An apparatus, method, and computer-readable medium for improving image quality of a medical volume. In an embodiment, the apparatus includes processing circuitry configured to receive a reconstructed input image volume from X-ray projection data corresponding to a three-dimensional region of an object to be examined, apply a pseudo-three-dimensional neural network (P3DNN) to the reconstructed input image volume, the application of the pseudo-three-dimensional neural network including generating, for the reconstructed input image volume, a plurality of three-dimensional image datasets representing a different anatomical plane of the reconstructed input image volume, applying at least one convolutional filter to each of a sagittal plane dataset, a transverse plane dataset, and a coronal plane dataset, and concatenating results of the applied at least one convolutional filter to generate an intermediate output image volume, and generate, based on the application of the P3DNN, an output image volume corresponding to the three-dimensional region of the object.

Apparatus, method, and non-transitory computer-readable storage medium for improving image quality of a medical image volume

Devices, systems, and methods obtain scan data that were generated by scanning a scanned region, wherein the scan data include groups of scan data that were captured at respective angles; generate partial reconstructions of at least a part of the scanned region, wherein each partial reconstruction of the partial reconstructions is generated based on a respective one or more groups of the groups of scan data, and wherein a collective scanning range of the respective one or more groups is less than the angular scanning range; input the partial reconstructions into a machine-learning model, which generates one or more motion-compensated reconstructions of the at least part of the scanned region based on the partial reconstructions; calculate a respective edge entropy of each of the one or more motion-compensated reconstructions of the at least part of the scanned region; and adjust the machine-learning model based on the respective edge entropies.

Devices, systems, and methods for medical imaging

Devices, systems, and methods receive scan data that were generated by scanning a region of a subject with a computed tomography apparatus; generate multiple partial angle reconstruction (PAR) images based on the scan data; obtain corresponding characteristics of the multiple PAR images; perform correspondence mapping on the multiple PAR images based on the obtained corresponding characteristics and on the multiple PAR images, wherein the correspondence mapping generates correspondence-mapping data; and generate a motion-corrected reconstruction image based on the correspondence-mapping data and on one or both of the scan data and the PAR images.

Devices, systems, and methods for motion-corrected medical imaging

A method and apparatuses are provided that use a neural network to correct artifacts in computed tomography (CT) images, especially cone-beam CT (CBCT) artifacts. The neural network is trained using a training dataset of artifact-minimized images paired with respective artifact-exhibiting images. In some embodiments, the artifact-minimized images are acquired using a small cone angle for the X-ray beam, and the artifact-exhibiting images are acquired either by forwarding projecting the artifact-minimized images using a large-cone-angle CBCT configuration or by performing a CBCT scan. In some embodiments, the network is a 2D convolutional neural network, and an artifact-exhibiting image is applied to the neural network as 2D slices taken for the coronal and/or sagittal views. Then the 2D image results from the neural network are reassembled as a 3D imaging having reduced imaging artifacts.

Apparatuses and a method for artifact reduction in medical images using a neural network

An apparatus and method are provided for computed tomography (CT) imaging to reduce truncation artifacts due to a part of an imaged object being outside the scanner field of view (FOV) for at least some views of a CT scan. After initial determining extrapolation widths to extend the projection data to fill a truncation region, the extrapolation widths are combined into a padding map and smoothed to improve uniformity and remove jagged edges. Then a hybrid material model fits the measured projection data nearest the truncation region to extrapolate projection data filling the truncation region. Smoothing the padding map is improved by the insight that in general smaller extrapolation widths are more accurate and trustworthy. Further, practical applications often include multiple inhomogeneous materials. Thus, the hybrid material model provides a better approximation than single material models, and more accurate fitting is achieved.

Method and apparatus for projection domain truncation correction in computed-tomography (CT)

An apparatus and method of denoising a dynamic image is provided. The dynamic image can represent a time-series of snapshot images. The dynamic image is transformed, using a sparsifying transformation, into an aggregate image and a series of transform-domain images. The transform-domain images represent kinetic information of the dynamic images (i.e., differences between the snapshots), and the aggregate image represents static information (i.e., features and structure common among the snapshots). The transform-domain images, which can be approximated using a sparse approximation method, are denoised. The denoised transform-domain images are recombined with the aggregate image using an inverse sparsifying transformation to generate a denoised dynamic image. The transform-domain images can be denoised using at least one of a principal component analysis method and a K-SVD method.

Dynamic image denoising using a sparse representation

A method and apparatus is provided to reconstruct a computed tomography image from projection data using windowed filtered back-projection (FBP) and using regularization constraints that can be quadratic or non-quadratic. The method emulates multiple Landweber iterations using a single windowed FBP operation and then iterates between imposing regularization constraints and a single windowed FBP operation. This windowed FBP operation is only performed once. The regularization constraints can be imposed using edge-preserving denoising methods, including, e.g., a Huber filter, a median filter, a bilateral filter, a guided filter, a non-local means filter, a total-variation minimization regularizer, other known regularizer, or an anisotropic diffusion filter. The entire procedure contains no forward projection and contains only one back-projection.

Fast iterative reconstruction with one backprojection and no forward projection

A method and apparatus is provided to determine a reconstructed image from computed tomography projection data using iterative reconstruction with an objective function that includes modified weights. The modified weights can include, among other weight values, redundancy weights and statistical weights, which are modified to compress low-frequency components. Additionally, high-frequency components of the statistical weights can be compressed, amplified, or maintained at their current magnitude. The high-frequency components can be subject to a threshold-and-invert step, substituting an inverted value for each high-frequency component above a predefined threshold. Using the modified weights, the reconstructed image can be determined using penalized weighted least squares to minimize the objective function.

Data fidelity weight design for iterative reconstruction

An apparatus and method of processing cone-beam X-ray projection data using a short-scan method (e.g., filtered back projection and weighting the projection data using the Parker weights for projection angles spanning 180&#xb0; plus the fan angle) to reconstruct an image. Imaging artifacts in the short-scan image are corrected by combining the short scan image with a correction image. The correction image is obtained by applying an asymmetric filter to the difference between the short-scan image and a full-scan image, the full scan image being obtained using image reconstruction of the full-scan projection data. In one implementation, the asymmetric filter is a low-pass filter that, in the spatial domain, is foreshortened along a center-view axis corresponding to the short scan.

Method and apparatus for computed tomography using asymetric filter for volume half reconstruction

An apparatus and method for computed tomography (CT) imaging to obtain an image from gated projection data, such as electrocardiographic gated projection data used in cardiac CT. The image reconstruction is performed using an iterative reconstruction method to minimize a cost function including a data-fidelity term (e.g., a system-matrix term) and a regularization term. The system-matrix term includes a weighted inner-product of the system-matrix equation, wherein the weighting matrix includes weighting values to correct the unequal data redundancy of the gated projection data.

Method and apparatus for iteratively reconstructing tomographic images from electrocardiographic-gated projection data

A medical image processing apparatus for receiving a target phase data set and a reference phase data set at different times, obtaining a segmentation of an elongated structure in the target phase data and the reference phase data set, determining a target phase line along the segmentation of the elongated structure in the target phase data set and a reference phase line along the segmentation of the elongated structure in the reference phase data set, and determining a synthesized target phase line by combining the target phase line and reference phase line.

Growing community of inventors

Buffalo Grove, IL, United States of America

Qiulin Tang