-
公开(公告)号：US11195310B2
公开(公告)日：2021-12-07
申请号：US16056111
申请日：2018-08-06
发明人： Lin Fu , Sathish Ramani , Jie Tang , Bruno Kristiaan Bernard De Man , Jed Douglas Pack , Jiang Hsieh , Ge Wang
摘要： The present disclosure relates to image reconstruction with favorable properties in terms of noise reduction, spatial resolution, detail preservation and computational complexity. The disclosed techniques may include some or all of: a first-pass reconstruction, a simplified datafit term, and/or a deep learning denoiser. In various implementations, the disclosed technique is portable to different CT platforms, such as by incorporating a first-pass reconstruction step.
-
公开(公告)号：US10949951B2
公开(公告)日：2021-03-16
申请号：US16110764
申请日：2018-08-23
发明人： Jie Tang , Eric Gros , Jiang Hsieh , Roy Nilsen
摘要： Systems and methods for improved image denoising using a deep learning network model are disclosed. An example system includes an input data processor to process a first patient image of a first patient to add a first noise to the first patient image to form a noisy image input. The example system includes an image data denoiser to process the noisy image input using a first deep learning network to identify the first noise. The image data denoiser is to train the first deep learning network using the noisy image input. When the first deep learning network is trained to identify the first noise, the image data denoiser is to deploy the first deep learning network as a second deep learning network model to be applied to a second patient image of the first patient to identify a second noise in the second patient image.
-
公开(公告)号：US20200065940A1
公开(公告)日：2020-02-27
申请号：US16110764
申请日：2018-08-23
发明人： Jie Tang , Eric Gros , Jiang Hsieh , Roy Nilsen
摘要： Systems and methods for improved image denoising using a deep learning network model are disclosed. An example system includes an input data processor to process a first patient image of a first patient to add a first noise to the first patient image to form a noisy image input. The example system includes an image data denoiser to process the noisy image input using a first deep learning network to identify the first noise. The image data denoiser is to train the first deep learning network using the noisy image input. When the first deep learning network is trained to identify the first noise, the image data denoiser is to deploy the first deep learning network as a second deep learning network model to be applied to a second patient image of the first patient to identify a second noise in the second patient image.
-
公开(公告)号：US10383589B2
公开(公告)日：2019-08-20
申请号：US15829554
申请日：2017-12-01
发明人： Jiang Hsieh , Zhoubo Li , Brian Edward Nett , Meghan Lynn Yue , Roy A. Nilsen
摘要： Methods and systems are provided for direct monochromatic image generation for spectral computed tomography. In one embodiment, a method comprises acquiring projection data during a scan of a subject, reconstructing a low energy image and a high energy image from the projection data, and generating a monochromatic image from the low energy image and the high energy image. In this way, a monochromatic image may be generated directly from low and high energy images with a substantial reduction in image noise, especially when compared to a monochromatic image generated indirectly from material density images.
-
公开(公告)号：US20190220975A1
公开(公告)日：2019-07-18
申请号：US16359647
申请日：2019-03-20
发明人： Jiang Hsieh , Gopal Avinash , Saad Sirohey
CPC分类号： G06T7/0012 , G06N3/04 , G06N3/08 , G06T2207/10004 , G06T2207/20081 , G06T2207/20084 , G16H30/40 , G16H40/40
摘要： Methods and apparatus for monitoring and improving imaging system operation are provided. An example apparatus includes a first deployed deep learning network (DLN) which operates with an acquisition engine to generate an imaging device configuration. The example apparatus includes a second deployed DLN which operates with a reconstruction engine based on acquired image data. The example apparatus includes a first assessment engine with a third deployed DLN. The assessment engine receives output from at least one of the acquisition engine or the reconstruction engine to assess operation of the respective at least one of the acquisition engine or the reconstruction engine and to provide feedback to the respective at least one of the acquisition engine or the reconstruction engine. The first deployed DLN and the second deployed DLN are generated and deployed from first and second training DLNS, respectively.
-
公开(公告)号：US20190167218A1
公开(公告)日：2019-06-06
申请号：US15829554
申请日：2017-12-01
发明人： Jiang Hsieh , Zhoubo Li , Brian Edward Nett , Meghan Lynn Yue , Roy A. Nilsen
CPC分类号： A61B6/482 , A61B6/032 , A61B6/4014 , A61B6/405 , A61B6/4241 , A61B6/5205 , A61B6/5241 , G06T11/008
摘要： Methods and systems are provided for direct monochromatic image generation for spectral computed tomography. In one embodiment, a method comprises acquiring projection data during a scan of a subject, reconstructing a low energy image and a high energy image from the projection data, and generating a monochromatic image from the low energy image and the high energy image. In this way, a monochromatic image may be generated directly from low and high energy images with a substantial reduction in image noise, especially when compared to a monochromatic image generated indirectly from material density images.
-
公开(公告)号：US10242443B2
公开(公告)日：2019-03-26
申请号：US15360410
申请日：2016-11-23
发明人： Jiang Hsieh , Gopal Avinash , Saad Sirohey
摘要： Methods and apparatus for monitoring and improving imaging system operation are provided. An example apparatus includes a first deployed deep learning network (DLN) which operates with an acquisition engine to generate an imaging device configuration. The example apparatus includes a second deployed DLN which operates with a reconstruction engine based on acquired image data. The example apparatus includes a first assessment engine with a third deployed DLN. The assessment engine receives output from at least one of the acquisition engine or the reconstruction engine to assess operation of the respective at least one of the acquisition engine or the reconstruction engine and to provide feedback to the respective at least one of the acquisition engine or the reconstruction engine. The first deployed DLN and the second deployed DLN are generated and deployed from first and second training DLNS, respectively.
-
公开(公告)号：US10127659B2
公开(公告)日：2018-11-13
申请号：US15360626
申请日：2016-11-23
发明人： Jiang Hsieh , Gopal Avinash , Saad Sirohey
摘要： Methods and apparatus for improved deep learning for image acquisition are provided. An imaging system configuration apparatus includes a training learning device including a first processor to implement a first deep learning network (DLN) to learn a first set of imaging system configuration parameters based on a first set of inputs from a plurality of prior image acquisitions to configure at least one imaging system for image acquisition, the training learning device to receive and process feedback including operational data from the plurality of image acquisitions by the at least one imaging system. The example apparatus includes a deployed learning device including a second processor to implement a second DLN, the second DLN generated from the first DLN of the training learning device, the deployed learning device configured to provide a second imaging system configuration parameter to the imaging system in response to receiving a second input for image acquisition.
-
公开(公告)号：US20170249759A1
公开(公告)日：2017-08-31
申请号：US15056657
申请日：2016-02-29
发明人： Jiang Hsieh , GuangHong Chen
CPC分类号： G06T11/008 , A61B6/032 , A61B6/5205 , A61B6/5258 , G06K9/3233 , G06K9/6255 , G06T5/50 , G06T7/0012 , G06T7/0081 , G06T7/11 , G06T2207/10081 , G06T2207/20021 , G06T2207/20224 , G06T2211/421 , G06T2211/432
摘要： An imaging system includes a computed tomography (CT) acquisition unit and at least one processor. The CT acquisition unit includes an X-ray source and a CT detector configured to collect CT imaging data of an object. The at least one processor is operably coupled to the CT acquisition unit, and configured to reconstruct an initial image using the CT imaging information, the initial image including at least one object representation portion and at least one artifact portion; identify at least one region of the initial image containing at least one artifact and isolate the at least one artifact by analyzing the initial image using an artifact dictionary and a non-artifact dictionary, the artifact dictionary including entries describing corresponding artifact image portions, the non-artifact dictionary including entries defining corresponding non-artifact image portions; and remove the at least one artifact from the initial image to provide a corrected image.
-
公开(公告)号：US20160371860A1
公开(公告)日：2016-12-22
申请号：US15185338
申请日：2016-06-17
发明人： Ping Liu , Jie Wu , Jiang Hsieh
CPC分类号： G06T11/003 , A61B6/025 , A61B6/03 , A61B6/032 , A61B6/505 , A61B6/5223 , G06T7/0012 , G06T7/11 , G06T11/008 , G06T15/08 , G06T2207/10012 , G06T2207/10081 , G06T2207/30196
摘要： The present invention provides a system and method for generating a CT slice image. The system comprises an MIP image generation module, a region of interest determination module, an angle setting module, a curve determination module, a match module and a slice generation module. The MIP image generation module generates MIP images of a reconstructed image; the region of interest determination module determines an image range in an original slice, and determines the parts of the MIP images within the image range as regions of interest; the angle setting module rotates the regions of interest to a plurality of specific angles for a plurality of times; the curve determination module generates a plurality of two-dimensional projected curves of the regions of interest for the plurality of specific angles; the match module selects a two-dimensional projected curve matching with a part to be diagnosed based on features of the plurality of two-dimensional projected curves; the slice generation module determines a slice position range and a slice angle based on the features of the matched curve and the corresponding specific angle.
摘要翻译： 本发明提供了一种用于生成CT切片图像的系统和方法。 该系统包括MIP图像生成模块，感兴趣区域确定模块，角度设置模块，曲线确定模块，匹配模块和切片生成模块。 MIP图像生成模块生成重建图像的MIP图像; 感兴趣区域确定模块确定原始片段中的图像范围，并且将图像范围内的MIP图像的部分确定为感兴趣区域; 角度设定模块将感兴趣区域旋转多个特定角度多次; 曲线确定模块生成多个特定角度的感兴趣区域的多个二维投影曲线; 匹配模块基于多个二维投影曲线的特征来选择与待诊断部分匹配的二维投影曲线; 切片生成模块基于匹配曲线的特征和对应的特定角度来确定切片位置范围和切片角度。
-
-
-
-
-
-
-
-
-
搜索结果
73 条记录 (耗时 0.036 秒)
