公开(公告)号：US20240078669A1

公开(公告)日：2024-03-07

申请号：US18497912

申请日：2023-10-30

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Máté Fejes ,  Gopal Avinash ,  Ravi Soni ,  Bipul Das ,  Rakesh Mullick ,  Pál Tegzes ,  Lehel Ferenczi ,  Vikram Melapudi ,  Krishna Seetharam Shriram

IPC: G06T7/00 ,  G06N3/08 ,  G06T15/08

CPC classification number: G06T7/0012 ,  G06N3/08 ,  G06T15/08 ,  G06T2207/10088 ,  G06T2207/10104

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

公开(公告)号：US11727086B2

公开(公告)日：2023-08-15

申请号：US17093960

申请日：2020-11-10

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Gopal B. Avinash ,  Máté Fejes ,  Ravi Soni ,  Dániel Attila Szabó ,  Rakesh Mullick ,  Vikram Melapudi ,  Krishna Seetharam Shriram ,  Sohan Rashmi Ranjan ,  Bipul Das ,  Utkarsh Agrawal ,  László Ruskó ,  Zita Herczeg ,  Barbara Darázs

IPC: G06F18/214 ,  G06T7/30 ,  G06N5/04 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50 ,  A61B6/03 ,  A61B6/00 ,  A61B5/055 ,  A61B5/00 ,  G06T5/50 ,  G06F18/22 ,  G06F18/28 ,  G06F18/21

CPC classification number: G06F18/214 ,  A61B5/055 ,  A61B5/7267 ,  A61B6/032 ,  A61B6/5223 ,  G06F18/2178 ,  G06F18/22 ,  G06F18/28 ,  G06N5/04 ,  G06T5/50 ,  G06T7/30 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/50 ,  G06T2200/04 ,  G06T2207/10081 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20212 ,  G06T2207/30004 ,  G06V2201/03

Abstract: Techniques are described for generating mono-modality training image data from multi-modality image data and using the mono-modality training image data to train and develop mono-modality image inferencing models. A method embodiment comprises generating, by a system comprising a processor, a synthetic 2D image from a 3D image of a first capture modality, wherein the synthetic 2D image corresponds to a 2D version of the 3D image in a second capture modality, and wherein the 3D image and the synthetic 2D image depict a same anatomical region of a same patient. The method further comprises transferring, by the system, ground truth data for the 3D image to the synthetic 2D image. In some embodiments, the method further comprises employing the synthetic 2D image to facilitate transfer of the ground truth data to a native 2D image captured of the same anatomical region of the same patient using the second capture modality.

公开(公告)号：US20230177706A1

公开(公告)日：2023-06-08

申请号：US17543283

申请日：2021-12-06

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Balázs Péter Cziria ,  Pál Tegzes ,  Gopal Biligeri Avinash ,  German Guillermo Vera Gonzalez ,  Lehel Mihály Ferenczi ,  Zita Herczeg ,  Ravi Soni ,  Dibyajyoti Pati

IPC: G06T7/30 ,  G06K9/62

CPC classification number: G06T7/30 ,  G06K9/6256 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems/techniques that facilitate multi-layer image registration are provided. In various embodiments, a system can access a first image and a second image. In various aspects, the system can generate, via execution of a machine learning model on the first image and the second image, a plurality of registration fields and a plurality of weight matrices that respectively correspond to the plurality of registration fields. In various instances, the system can register the first image with the second image based on the plurality of registration fields and the plurality of weight matrices.

公开(公告)号：US20230169666A1

公开(公告)日：2023-06-01

申请号：US17457179

申请日：2021-12-01

Applicant: GE Precision Healthcare LLC

Inventor： Dibyajyoti Pati ,  Junpyo Hong ,  Venkata Ratnam Saripalli ,  German Guillermo Vera Gonzalez ,  Dejun Wang ,  Aizhen Zhou ,  Gopal B. Avinash ,  Ravi Soni ,  Tao Tan ,  Fuqiang Chen ,  Yaan Ge

IPC: G06T7/30 ,  A61B6/00 ,  G06N3/08

CPC classification number: G06T7/30 ,  A61B6/5241 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/10116 ,  G06T2207/20212

Abstract: Various methods and systems are provided for automatically registering and stitching images. In one example, a method includes entering a first image of a subject and a second image of the subject to a model trained to output a transformation matrix based on the first image and the second image, where the model is trained with a plurality of training data sets, each training data set including a pair of images, a mask indicating a region of interest (ROI), and associated ground truth, automatically stitching together the first image and the second image based on the transformation matrix to form a stitched image, and outputting the stitched image for display on a display device and/or storing the stitched image in memory.

公开(公告)号：US20220284570A1

公开(公告)日：2022-09-08

申请号：US17192804

申请日：2021-03-04

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Máté Fejes ,  Gopal Avinash ,  Ravi Soni ,  Bipul Das ,  Rakesh Mullick ,  Pál Tegzes ,  Lehel Ferenczi ,  Vikram Melapudi ,  Krishna Seetharam Shriram

IPC: G06T7/00 ,  G06N3/08 ,  G06T15/08

Abstract: Methods and systems are provided for inferring thickness and volume of one or more object classes of interest in two-dimensional (2D) medical images, using deep neural networks. In an exemplary embodiment, a thickness of an object class of interest may be inferred by acquiring a 2D medical image, extracting features from the 2D medical image, mapping the features to a segmentation mask for an object class of interest using a first convolutional neural network (CNN), mapping the features to a thickness mask for the object class of interest using a second CNN, wherein the thickness mask indicates a thickness of the object class of interest at each pixel of a plurality of pixels of the 2D medical image; and determining a volume of the object class of interest based on the thickness mask and the segmentation mask.

公开(公告)号：US20220058437A1

公开(公告)日：2022-02-24

申请号：US16999665

申请日：2020-08-21

Applicant: GE Precision Healthcare LLC

Inventor： Ravi Soni ,  Tao Tan ,  Gopal B. Avinash ,  Dibyaiyoti Pati ,  Hans Krupakar ,  Venkata Ratnam Saripalli

IPC: G06K9/62 ,  G06N20/00

Abstract: Systems and techniques that facilitate synthetic training data generation for improved machine learning generalizability are provided. In various embodiments, an element augmentation component can generate a set of preliminary annotated training images based on an annotated source image. In various aspects, a preliminary annotated training image can be formed by inserting at least one element of interest or at least one background element into the annotated source image. In various instances, a modality augmentation component can generate a set of intermediate annotated training images based on the set of preliminary annotated training images. In various cases, an intermediate annotated training image can be formed by varying at least one modality-based characteristic of a preliminary annotated training image. In various aspects, a geometry augmentation component can generate a set of deployable annotated training images based on the set of intermediate annotated training images. In various instances, a deployable annotated training image can be formed by varying at least one geometric characteristic of an intermediate annotated training image. In various embodiments, a training component can train a machine learning model on the set of deployable annotated training images.

公开(公告)号：US12249067B2

公开(公告)日：2025-03-11

申请号：US17664702

申请日：2022-05-24

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Hongxiang Yi ,  Rakesh Mullick ,  Lehel Mihály Ferenczi ,  Gopal Biligeri Avinash ,  Borbála Deák-Karancsi ,  Balázs Péter Cziria ,  Laszlo Rusko

IPC: G06T7/00 ,  A61B8/08 ,  G06T7/149 ,  G06T7/174

Abstract: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object. The system further combines the different image segmentations based on the ranking scores to generate the fused image segmentation.

公开(公告)号：US11983798B2

公开(公告)日：2024-05-14

申请号：US17392431

申请日：2021-08-03

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Buer Qi ,  Dejun Wang ,  Gopal B. Avinash ,  Gireesha Chinthamani Rao ,  German Guillermo Vera Gonzalez ,  Lehel Ferenczi

IPC: G06T11/00 ,  G06N20/00

CPC classification number: G06T11/005 ,  G06N20/00 ,  G06T11/006 ,  G06T2210/41 ,  G06T2211/40

Abstract: Systems/techniques that facilitate AI-based region-of-interest masks for improved data reconstructions are provided. In various embodiments, a system can access a set of two-dimensional medical scan projections. In various aspects, the system can generate a set of two-dimensional region-of-interest masks respectively corresponding to the set of two-dimensional medical scan projections. In various instances, the system can generate a region-of-interest visualization based on the set of two-dimensional region-of-interest masks and the set of two-dimensional medical scan projections. In various cases, the system can generate the set of two-dimensional region-of-interest masks by executing a machine learning segmentation model on the set of two-dimensional medical scan projections.

公开(公告)号：US20240127047A1

公开(公告)日：2024-04-18

申请号：US18046347

申请日：2022-10-13

Applicant: GE Precision Healthcare LLC

Inventor： Tao Tan ,  Hongxu Yang ,  Gopal Biligeri Avinash ,  Balázs Péter Cziria ,  Pál Tegzes ,  Xiaomeng Dong ,  Ravi Soni ,  Lehel Mihály Ferenczi ,  Laszlo Rusko

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454

Abstract: Systems/techniques that facilitate deep learning image analysis with increased modularity and reduced footprint are provided. In various embodiments, a system can access medical imaging data. In various aspects, the system can perform, via execution of a deep learning neural network, a plurality of inferencing tasks on the medical imaging data. In various instances, the deep learning neural network can comprise a common backbone in parallel with a plurality of task-specific backbones. In various cases, the plurality of task-specific backbones can respectively correspond to the plurality of inferencing tasks.

公开(公告)号：US20240122566A1

公开(公告)日：2024-04-18

申请号：US17965228

申请日：2022-10-13

Applicant: GE Precision Healthcare LLC

Inventor： Balázs P. Cziria ,  German Guillermo Vera Gonzalez ,  Tao Tan ,  Pal Tegzes ,  Justin M. Wanek ,  Gopal B. Avinash ,  Zita Herczeg ,  Ravi Soni ,  Gireesha Chinthamani Rao

IPC: A61B6/00 ,  G01N23/04 ,  G06T5/00 ,  G06T5/50 ,  G16H30/40

CPC classification number: A61B6/5264 ,  A61B6/463 ,  A61B6/467 ,  A61B6/482 ,  G01N23/04 ,  G06T5/003 ,  G06T5/50 ,  G16H30/40 ,  G01N2223/401 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/20201 ,  G06T2207/20224 ,  G06T2207/30004

Abstract: A dual energy x-ray imaging system and method of operation includes an artificial intelligence-based motion correction system to minimize the effects of motion artifacts in images produced by the imaging system. The motion correction system is trained to apply simulated motion to various objects of interest within the LE and HE projections in the training dataset to improve registration of the LE and HE projections. The motion correction system is also trained to enhance the correction of small motion artifacts using noise attenuation and subtraction image-based edge detection on the training dataset images reduce noise from the LE projection, consequently improving small motion artifact correction. The motion correction system additionally employs separate motion corrections for soft and bone tissue in forming subtraction soft tissue and bone tissue images, and includes a motion alarm to indicate when motion between LE and HE projections requires a retake of the projections.