Patents by Inventor Jiaofeng Xu
Jiaofeng Xu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11501438Abstract: Techniques for generating an enhanced cone-beam computed tomography (CBCT) image using a trained model are provided. A CBCT image of a subject is received. a synthetic computed tomography (sCT) image corresponding to the CBCT image is generated, using a generative model. The generative model is trained in a generative adversarial network (GAN). The generative model is further trained to process the CBCT image as an input and provide the sCT image as an output. The sCT image is presented for medical analysis of the subject.Type: GrantFiled: July 24, 2018Date of Patent: November 15, 2022Assignee: Elekta, Inc.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20220318956Abstract: Techniques for generating a synthetic computed tomography (sCT) image from a cone-beam computed tomography (CBCT) image are provided. The techniques include receiving a CBCT image of a subject; generating, using a generative model, a sCT image corresponding to the CBCT image, the generative model trained based on one or more deformable offset layers in a generative adversarial network (GAN) to process the CBCT image as an input and provide the sCT image as an output; and generating a display of the sCT image for medical analysis of the subject.Type: ApplicationFiled: June 27, 2019Publication date: October 6, 2022Inventor: Jiaofeng Xu
-
Patent number: 11080901Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.Type: GrantFiled: January 10, 2020Date of Patent: August 3, 2021Assignee: Elekta, Inc.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20200151922Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.Type: ApplicationFiled: January 10, 2020Publication date: May 14, 2020Inventors: Jiaofeng Xu, Xiao Han
-
Patent number: 10573032Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.Type: GrantFiled: April 27, 2018Date of Patent: February 25, 2020Assignee: Elekta, Inc.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20190333219Abstract: Techniques for generating an enhanced cone-beam computed tomography (CBCT) image using a trained model are provided. A CBCT image of a subject is received, a synthetic computed tomography (sCT) image corresponding to the CBCT image is generated, using a generative model. The generative model is trained in a generative adversarial network (GAN). The generative model is further trained to process the CBCT image as an input and provide the sCT image as an output. The sCT image is presented for medical analysis of the subject.Type: ApplicationFiled: July 24, 2018Publication date: October 31, 2019Inventors: Jiaofeng Xu, Xiao Han
-
Patent number: 10346986Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: GrantFiled: October 16, 2018Date of Patent: July 9, 2019Assignee: Elekta, Inc.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20190050992Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: ApplicationFiled: October 16, 2018Publication date: February 14, 2019Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20180374245Abstract: Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.Type: ApplicationFiled: April 27, 2018Publication date: December 27, 2018Inventors: Jiaofeng Xu, Xiao Han
-
Patent number: 10134141Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: GrantFiled: March 26, 2018Date of Patent: November 20, 2018Assignee: Elekta, Inc.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20180218503Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: ApplicationFiled: March 26, 2018Publication date: August 2, 2018Inventors: Jiaofeng Xu, Xiao Han
-
Patent number: 9965863Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: GrantFiled: August 26, 2016Date of Patent: May 8, 2018Assignee: ELEKTA, INC.Inventors: Jiaofeng Xu, Xiao Han
-
Patent number: 9947102Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving a three-dimensional image acquired by an imaging device, and selecting a plurality of stacks of adjacent two-dimensional images from the three-dimensional image. The method may further include segmenting, by a processor, each stack of adjacent two-dimensional images using a neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the plurality of stacks.Type: GrantFiled: August 26, 2016Date of Patent: April 17, 2018Assignee: ELEKTA, INC.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20180061059Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving the three-dimensional image acquired by an imaging device, and creating a first stack of two-dimensional images from a first plane of the three-dimensional image and a second stack of two-dimensional images from a second plane of the three-dimensional image. The method may further include segmenting, by a processor, the first stack and the second stack of two-dimensional images using at least one neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the first stack and second stack.Type: ApplicationFiled: August 26, 2016Publication date: March 1, 2018Applicant: ELEKTA, INC.Inventors: Jiaofeng Xu, Xiao Han
-
Publication number: 20180061058Abstract: The present disclosure relates to systems, methods, devices, and non-transitory computer-readable storage medium for segmenting three-dimensional images. In one implementation, a computer-implemented method for segmenting a three-dimensional image is provided. The method may include receiving a three-dimensional image acquired by an imaging device, and selecting a plurality of stacks of adjacent two-dimensional images from the three-dimensional image. The method may further include segmenting, by a processor, each stack of adjacent two-dimensional images using a neural network model. The method may also include determining, by the processor, a label map for the three-dimensional image by aggregating the segmentation results from the plurality of stacks.Type: ApplicationFiled: August 26, 2016Publication date: March 1, 2018Applicant: ELEKTA, INC.Inventors: Jiaofeng Xu, Xiao Han