专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08358880B2 Hybrid coupling structure of the short range plasmon polariton and conventional dielectric waveguide, a coupling structure of the long range plasmon polariton and conventional dielectric waveguide, and applications thereof 有权
标题翻译：短距离等离子体激元和常规电介质波导的混合耦合结构，远距离等离子体激元和常规电介质波导的耦合结构及其应用
公开(公告)号：US08358880B2
公开(公告)日：2013-01-22
申请号：US12639549
申请日：2009-12-16
申请人： Fang Liu , Rui-Yuan Wan , Yi-Dong Huang , Xue Feng , Wei Zhang , Jiang De Peng , Yoshikatsu Miura , Daisuke Niwa , Dai Ohnishi
发明人： Fang Liu , Rui-Yuan Wan , Yi-Dong Huang , Xue Feng , Wei Zhang , Jiang De Peng , Yoshikatsu Miura , Daisuke Niwa , Dai Ohnishi
IPC分类号： G02F1/035
CPC分类号： G01N21/553 , B82Y20/00 , G01N21/43 , G01N21/7703 , G02B6/1226 , G02F1/035 , G02F2001/0144 , G02F2203/10
摘要： The present invention provides a hybrid coupling structure of a short range surface plasmon polariton and a conventional dielectric waveguide, including a dielectric substrate layer, a dielectric waveguide layer positioned on the said dielectric substrate layer, a coupling matching layer positioned on the said dielectric waveguide layer and a short range surface plasmon waveguide portion, formed on the said coupling matching layer, for conducting the short range surface plasmon polariton. The present invention also provides a coupling structure of a long range surface plasmon polariton and a dielectric waveguide, including a dielectric substrate layer, a dielectric waveguide layer, a coupling matching layer and a long range surface plasmon waveguide portion upward from below respectively.
摘要翻译：本发明提供了一种短距离表面等离子体激元和传统电介质波导的混合耦合结构，包括电介质基底层，位于所述电介质基底层上的电介质波导层，位于所述电介质波导层上的耦合匹配层以及形成在所述耦合匹配层上的用于传导短距离表面等离子体激元的短距离表面等离子体波导部分。本发明还提供了一种远距离表面等离子体激元和介质波导的耦合结构，其中包括电介质基底层，电介质波导层，耦合匹配层和远距离表面等离子体激元波导部分。

2. 发明申请

US20100310205A1 Hybrid Coupling Structure of the short Range Plasmon Polariton and Conventional Dielectric Waveguide, A Coupling Structure of the Long Range Plasmon Polariton and Conventional Dielectric Waveguide, and Applications Thereof 有权
标题翻译：短距离等离子体极化和常规介质波导的混合耦合结构，长距离等离子体极化和常规介质波导的耦合结构及其应用
公开(公告)号：US20100310205A1
公开(公告)日：2010-12-09
申请号：US12639549
申请日：2009-12-16
申请人： Fan Liu , Rui-Yuan Wan , Yi-Dong Huang , Xue Feng , Wei Zhang , Jiang De Peng , Yoshikatsu Miura , Daisuke Niwa , Dai Ohnishi
发明人： Fan Liu , Rui-Yuan Wan , Yi-Dong Huang , Xue Feng , Wei Zhang , Jiang De Peng , Yoshikatsu Miura , Daisuke Niwa , Dai Ohnishi
IPC分类号： G02B6/26 , G02F1/01
CPC分类号： G01N21/553 , B82Y20/00 , G01N21/43 , G01N21/7703 , G02B6/1226 , G02F1/035 , G02F2001/0144 , G02F2203/10
摘要： The present invention provides a hybrid coupling structure of a short range surface plasmon polariton and a conventional dielectric waveguide, including a dielectric substrate layer, a dielectric waveguide layer positioned on the said dielectric substrate layer, a coupling matching layer positioned on the said dielectric waveguide layer and a short range surface plasmon waveguide portion, formed on the said coupling matching layer, for conducting the short range surface plasmon polariton. The present invention also provides a coupling structure of a long range surface plasmon polariton and a dielectric waveguide, including a dielectric substrate layer, a dielectric waveguide layer, a coupling matching layer and a long range surface plasmon waveguide portion upward from below respectively.
摘要翻译：本发明提供了一种短距离表面等离子体激元和传统电介质波导的混合耦合结构，包括电介质基底层，位于所述电介质基底层上的电介质波导层，位于所述电介质波导层上的耦合匹配层以及形成在所述耦合匹配层上的用于传导短距离表面等离子体激元的短距离表面等离子体波导部分。本发明还提供了一种远距离表面等离子体激元和介质波导的耦合结构，其中包括电介质基底层，电介质波导层，耦合匹配层和远距离表面等离子体激元波导部分。

3. 发明授权

US12033740B2 Systems and methods for robust and automatic face de-identification for CT and MRI 有权
公开(公告)号：US12033740B2
公开(公告)日：2024-07-09
申请号：US17542409
申请日：2021-12-04
申请人： Vasileios K. Papaioannou , Quan Chen , Xue Feng
发明人： Vasileios K. Papaioannou , Quan Chen , Xue Feng
IPC分类号： G16H30/20 , G16H30/40
CPC分类号： G16H30/20 , G16H30/40
摘要： The present disclosure relates to a method and apparatus for robust and automatic face de-identification from CT and MRI. The method includes: receiving DICOM files of patient bodies obtained by a CT or MRI system; normalizing the images; extracting the heads from bodies; creating face masks; and writing DICOM files back with de-identified faces.

4. 发明授权

US12026934B2 Systems and methods for training a convolutional neural network that is robust to missing input information 有权
公开(公告)号：US12026934B2
公开(公告)日：2024-07-02
申请号：US17531720
申请日：2021-11-20
申请人： Xue Feng , Quan Chen , Kanchan Ghimire
发明人： Xue Feng , Quan Chen , Kanchan Ghimire
IPC分类号： G06V10/774 , G06N3/04 , G06V10/25 , G06V10/80 , G06V10/94
CPC分类号： G06V10/774 , G06N3/04 , G06V10/25 , G06V10/80 , G06V10/95
摘要： The present disclosure relates to a method and apparatus for training a convolutional neural network (CNN) that is robust to missing input information. The method includes: receive a plurality of three-dimensional (3D) images per case obtained from a CT, an MRI, or a PET system or the combination thereof; receive accompanying metadata for each received 3D images, comprising pixel spacing, slice thickness, and matrix size; processing the received 3D images per case utilizing the received metadata of each 3D images to generate 4D images containing complimentary information from received imaging modalities, wherein the generated 4D images may miss a plurality of imaging modalities; further process the generated 4D images if the generated 4D images miss a plurality of imaging modalities, wherein the step comprises: fill the generated 4D images with a fixed value for all pixels of missed imaging modalities; build an adaptable deep learning framework using CNNs for image segmentation that utilizes the generated 4D images as input; train the CNNs with the generated 4D images to obtain segmentation labels for each region-of-interest (ROI) by emulating missing modality, wherein the step of emulating missing modality in training comprises: randomly decide whether or not to emulate; if decide to emulate, randomly select a plurality of input modalities to emulate as missing and fill the images with a fixed value for all pixels of the selected input modalities; and deploy the trained CNNs on 4D images generated from 3D images for each new testing case employing the steps of receiving and processing 3D images described above to obtain segmentation labels for each ROI, wherein the step of deployment comprises: accommodate missing modalities in generated 4D images by filling the images with the same fixed value used in training for missed modalities.

5. 发明公开

US20230178218A1 SYSTEMS AND METHODS FOR ROBUST AND AUTOMATIC FACE DE-IDENTIFICATION FOR CT AND MRI 审中-公开
公开(公告)号：US20230178218A1
公开(公告)日：2023-06-08
申请号：US17542409
申请日：2021-12-04
申请人： Vasileios K. Papaioannou , Quan Chen , Xue Feng
发明人： Vasileios K. Papaioannou , Quan Chen , Xue Feng
IPC分类号： G16H30/20 , G16H30/40
CPC分类号： G16H30/20 , G16H30/40
摘要： The present disclosure relates to a method and apparatus for robust and automatic face de-identification from CT and MRI. The method includes: receiving DICOM files of patient bodies obtained by a CT or MM system; normalizing the images; extracting the heads from bodies; creating face masks; and writing DICOM files back with de-identified faces.

6. 发明申请

US20140152304A1 SYSTEMS AND METHODS FOR REDUCED OFF-RESONANCE BLURRING IN SPIRAL IMAGING 有权
标题翻译：用于减少螺旋成像中的非共振辐射的系统和方法
公开(公告)号：US20140152304A1
公开(公告)日：2014-06-05
申请号：US13868095
申请日：2013-04-22
申请人： Samuel W. Fielden , Craig H. Meyer , Xue Feng
发明人： Samuel W. Fielden , Craig H. Meyer , Xue Feng
IPC分类号： G01R33/565
CPC分类号： G01R33/565 , G01R33/4824
摘要： Systems, methods of reducing off-resonance blurring in acquired magnetic resonance imaging data. The method includes acquiring a first set of spiral interleaf data for each of one or more spiral-in/out interleaves by performing a first sampling each of one or more locations in k-space along a first redundant spiral-in/out trajectory, and acquiring a second set of spiral interleaf data for each of the one or more spiral-in/out interleaves by performing a second sampling of each of the one or more locations in the k-space along a second redundant spiral-in/out trajectory, wherein the second redundant spiral-in/out trajectory corresponds to a time-reversed trajectory of the first redundant spiral-in/out trajectory. The method may yet further include combining the first set of spiral interleaf data and the second set of spiral interleaf data with an averaging operation such as to reduce artifacts.
摘要翻译：系统，减少获取的磁共振成像数据中的非共振模糊的方法。该方法包括：通过沿着第一冗余螺旋进/出轨迹对k空间中的一个或多个位置执行第一采样，获取一个或多个螺旋输入/输出交错中的每一个的第一组螺旋插入数据，以及通过沿着第二冗余螺旋进/出轨迹执行所述k空间中的所述一个或多个位置中的每个位置的第二采样来获取所述一个或多个螺旋输入/输出交错中的每一个的第二组螺旋插入数据，其中所述第二冗余螺旋进/出轨迹对应于所述第一冗余螺旋进/出轨迹的时间反转轨迹。该方法还可以包括将第一组螺旋插入数据和第二组螺旋插值数据与平均化操作组合，以减少伪影。

7. 发明公开

US20230316796A1 SYSTEMS AND METHODS FOR AUTOMATIC DETECTION OF ANATOMICAL SITES FROM TOMOGRAPHIC IMAGES 审中-公开
公开(公告)号：US20230316796A1
公开(公告)日：2023-10-05
申请号：US17693272
申请日：2022-03-11
申请人： Kanchan Ghimire , Quan Chen , Xue Feng
发明人： Kanchan Ghimire , Quan Chen , Xue Feng
IPC分类号： G06V40/10 , G06V10/26 , G06V10/44 , G06V10/28 , G06V10/34 , G16H30/20 , G16H30/40
CPC分类号： G06V40/10 , G06V10/267 , G06V10/273 , G06V10/28 , G06V10/34 , G06V10/457 , G16H30/20 , G16H30/40 , G06V2201/031
摘要： The present disclosure relates to a method and apparatus for automatic detection of anatomical sites from tomographic images. The method includes: receiving 3D images obtained by a CT or an MRI system, transforming the images to the DICOM standard patient-based coordinate system, pre-processing the images to have normalized intensity values based on their modality, performing body segmentation, cropping the images to remove excess areas outside the body, and detecting different anatomical sites including head and neck, thorax, abdomen, male pelvis and female pelvis, wherein the step of detecting different anatomical sites comprises: performing slice-level analyses on 2D axial slices to detect the head and neck region using dimensional measurement thresholds based on human anatomy, calculating lung ratios on axial slices to find if lungs are present, determining whether 3D images with lungs present span over the thoracic region, abdomen region, or both, conducting 2D connectivity analyses on axial slices to detect the pelvis region if two separate leg regions are found and differentiating detected pelvis regions as either male pelvis or female pelvis regions based on human anatomy.

8. 发明公开

US20230154586A1 SYSTEM AND METHOD FOR FAST MONTE CARLO DOSE CALCULATION USING A VIRTUAL SOURCE MODEL 审中-公开
公开(公告)号：US20230154586A1
公开(公告)日：2023-05-18
申请号：US17528590
申请日：2021-11-17
申请人： James Castle , Quan Chen , Xue Feng
发明人： James Castle , Quan Chen , Xue Feng
IPC分类号： G16H20/10 , G16H50/50 , G16H30/40 , G16H15/00 , G06T7/00
CPC分类号： G16H20/10 , G16H50/50 , G16H30/40 , G16H15/00 , G06T7/0012 , G06T2207/10081
摘要： The present disclosure relates to a method and apparatus for fast Monte Carlo (MC) dose calculation using a virtual source model (VSM). The method includes: receiving three-dimensional (3D) images obtained by a computed tomography (CT) system; receiving 3D planned dose images, 3D organ segmentation contour images, and radiotherapy plans generated by a treatment planning system (TPS); processing all 3D images to have the same spatial resolution and matrix size; processing 3D CT images to convert image intensity to density; processing the radiotherapy plans to generate instructions on how to simulate plan delivery; building VSM using inverse cumulative density function (CDF) tables for the simulation of radiotherapy plans, wherein the step of building VSM comprises: receiving output data files containing phase-space information for the radiation output of a specific medical linear accelerator treatment head; calculating the probability of particles' inplane and crossplane positions reverse transported from the phase-space surface back to the treatment head; calculating the Gaussian means and standard deviations of particles' positions at the treatment head and determining the criteria for particle source; calculating the probabilities for each particle source; calculating the probabilities for the medical linear accelerator treatment head to produce different particle species; binning the inplane position probability information of particles into a single histogram for each source and particle species; binning the crossplane position probability information of particles into histograms for each bin of the inplane position histogram for each source and particle species; binning the inplane direction cosine probability information of particles into histograms for each bin of the inplane position histogram for each source and particle species; binning the crossplane direction cosine probability information of particles into histograms for each bin of the crossplane position histogram for each source and particle species; binning the kinetic energy probability information of particles into radially binned histograms for each source and particle species; converting probability densities for inplane and crossplane positions, inplane and crossplane direction cosines, and kinetic energies histograms into cumulative probability densities for each source and particle species; and inverting cumulative probability densities and converting into probability binned inverse CDF tables; simulating and transporting external beams using VSM through virtual treatment machines to the 3D CT densities according to radiotherapy plans to produce 3D images of simulated patient dose; and post-processing 3D planned dose, organ segmentation contour, and simulated patient dose images to obtain a final report comparing planned versus simulated dose.

9. 发明授权

US11455733B2 System and method to improve model-based organ segmentation with image post-processing 有权
公开(公告)号：US11455733B2
公开(公告)日：2022-09-27
申请号：US16903299
申请日：2020-06-16
申请人： Xue Feng , Quan Chen
发明人： Xue Feng , Quan Chen
IPC分类号： G06T7/174 , G06T7/11 , G06T5/00
摘要： The present disclosure relates to a method and apparatus to improve model-based organ segmentation with image post-processing using one or more processors. The method includes: receiving three-dimensional (3D) CT or MR images and the corresponding voxel-by-voxel segmentation results from the output of an automatic DCNN segmentation model, analyzing the segmentation results on a 3D basis according to organ anatomical information, processing the results to identify regions with anatomically incorrect segmentations, fixing the incorrect segmentations, analyzing the remaining segmentation results on a two-dimensional (2D) and slice-by-slice basis according to predefined organ segmentation criteria, identifying the start and end slices, processing the results to remove segmentations beyond the identified slices to obtain the final results.

10. 发明公开

US20230154009A1 SYSTEMS AND METHODS FOR AUTOMATIC SEGMENTATION OF ORGANS FROM HEAD AND NECK TOMOGRAPHIC IMAGES 审中-公开
公开(公告)号：US20230154009A1
公开(公告)日：2023-05-18
申请号：US17529188
申请日：2021-11-17
申请人： Xue Feng , Quan Chen , Kanchan Ghimire
发明人： Xue Feng , Quan Chen , Kanchan Ghimire
IPC分类号： G06T7/168
CPC分类号： G06T7/168 , G06T2207/10081 , G06T2207/10088 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004 , G06T2207/20216
摘要： The present disclosure relates to a method and apparatus for automatic head and neck organ segmentation. The method includes: receiving 3D images obtained by a CT system or an MRI system; processing the 3D images to transform to patient coordinate system and have the same spatial resolution and matrix size; building a deep learning framework using CNN models for organ segmentation; doubling the size of training dataset by emulating uncollected training data with mirrored images and their corresponding labels; improving the performance by predicting on original and mirrored images and averaging the output probabilities; and post-processing the output from the deep learning framework to obtain final organ segmentation.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式