公开(公告)号：US20240005507A1

公开(公告)日：2024-01-04

申请号：US18046385

申请日：2022-10-13

Applicant: Alibaba (China) Co., Ltd.

Inventor： Jiawen YAO ,  Yingda XIA ,  Ke YAN ,  Dakai JIN ,  Xiansheng HUA ,  Le LU ,  Ling ZHANG

IPC: G06T7/10 ,  G06T7/73 ,  G06V20/70

CPC classification number: G06T7/10 ,  G06T7/73 ,  G06V2201/031 ,  G06T2207/20084 ,  G06T2207/10081 ,  G06V20/70

Abstract: An image processing method is provided. The method includes obtaining a to-be-processed image comprising a target object, and inputting the to-be-processed image to a convolutional layer of an image processing model, to obtain an initial feature map of the to-be-processed image, wherein the image processing model comprises an encoder and a decoder; inputting the initial feature map to a self-attention mechanism layer of the encoder, and obtaining a target feature map corresponding to the initial feature map according to position information of each feature in the initial feature map and a position relationship between the each feature and other features; and inputting the target feature map to the decoder for processing, to obtain an object segmentation map and an object label of the target object in the to-be-processed image

公开(公告)号：US20240005498A1

公开(公告)日：2024-01-04

申请号：US18357991

申请日：2023-07-24

Applicant: FUJIFILM Corporation

Inventor： Akira KUDO

IPC: G06T7/00 ,  G16H30/40 ,  G06V10/82

CPC classification number: G06T7/0012 ,  G16H30/40 ,  G06V10/82 ,  G06T2207/20048 ,  G06T2207/10072 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06V2201/031

Abstract: By using a learning model having a structure of a generative adversarial network including a first generator configured using a first convolutional neural network that receives an input of a medical image of a first domain and that outputs a first generated image of a second domain, and a first discriminator configured using a second convolutional neural network that receives an input of data including first image data, which is the first generated image or a medical image of the second domain included in a training dataset and coordinate information of a human body coordinate system corresponding to each position of a plurality of unit elements configuring the first image data, and that discriminates authenticity of the input image, a computer acquires a plurality of pieces of training data including the medical image of the first domain and the medical image of the second domain; and performs training processing.

公开(公告)号：US20240000432A1

公开(公告)日：2024-01-04

申请号：US18468744

申请日：2023-09-18

Applicant: FUJIFILM Corporation

Inventor： Toshihiro USUDA

IPC: A61B8/00 ,  G06T11/60 ,  G06V10/25 ,  G06V10/764 ,  G06V20/50 ,  G06T7/70 ,  A61B8/12

CPC classification number: A61B8/469 ,  G06T11/60 ,  G06V10/25 ,  G06V10/764 ,  G06V20/50 ,  G06T7/70 ,  G06T2207/10132 ,  A61B8/463 ,  A61B8/54 ,  G06V2201/031 ,  G06T2207/30092 ,  G06T2207/10068 ,  A61B8/12

Abstract: A medical image processing apparatus includes a processor configured to execute an image acquisition process for sequentially acquiring time-series medical images; a region-of-interest recognition process for recognizing a position and a type of a region of interest from the medical images; and a display control process for causing a display device to display position information indicating the position of the region of interest and type information indicating the type of the region of interest such that the position information and the type information are superimposed on the medical images. In the display control process, the processor changes a position at which the position information is to be displayed according to a change in the position of the region of interest over time, and maintains a position at which the type information is to be displayed regardless of a change in the position of the region of interest over time.

公开(公告)号：US11854190B2

公开(公告)日：2023-12-26

申请号：US17167058

申请日：2021-02-03

Applicant: FUJIFILM Corporation

Inventor： Shoji Kanada

IPC: G06T7/00 ,  G06T7/11 ,  G06V10/25 ,  G06V10/75 ,  G06F18/22 ,  G06V10/74 ,  G06V20/64

CPC classification number: G06T7/0012 ,  G06F18/22 ,  G06T7/11 ,  G06V10/25 ,  G06V10/751 ,  G06V10/761 ,  G06V20/653 ,  G06T2207/30061 ,  G06V2201/031

Abstract: A region division unit divides a target region of a first medical image into a plurality of regions. A finding classification unit classifies each pixel of the first medical image into at least one finding. A feature amount calculation unit calculates a first feature amount for each finding. A region similarity derivation unit derives a region similarity between the first medical image and a second medical image for each of the divided regions. A similarity derivation unit performs a weighting operation for a plurality of region similarities with a weighting coefficient corresponding to at least one of a size of each of the divided regions or a size of a specific finding included in each of the divided regions to derive a similarity between the first medical image and the second medical image.

公开(公告)号：US11801039B2

公开(公告)日：2023-10-31

申请号：US17223260

申请日：2021-04-06

Applicant: FUJIFILM Corporation

Inventor： Takuya Tsutaoka

IPC: G06T5/00 ,  G06F18/2431 ,  G06V10/764 ,  G06V10/44 ,  A61B8/08 ,  G06T7/00 ,  G06V10/20 ,  A61B8/00

CPC classification number: A61B8/5223 ,  A61B8/08 ,  A61B8/5238 ,  A61B8/5269 ,  G06F18/2431 ,  G06T5/007 ,  G06T7/0014 ,  G06V10/255 ,  G06V10/44 ,  G06V10/764 ,  A61B8/463 ,  G06T2207/10132 ,  G06T2207/30084 ,  G06T2207/30168 ,  G06V2201/031

Abstract: An ultrasound diagnostic apparatus 1 includes a bladder pattern storage unit 22, a reference pattern setting unit 21, a bladder extraction unit 18 that extracts a bladder region from an ultrasound image, a bladder extraction success/failure determination unit 19 that determines whether the bladder region represents a bladder having the reference pattern, and an image quality adjustment unit 20 that adjusts the image quality of the ultrasound image in a case where determination is made that the bladder region does not represent the bladder having the reference pattern, in which in a case where the determination is made that the bladder region does not represent the bladder having the reference pattern even in an ultrasound image of which the image quality is adjusted, the bladder extraction success/failure determination unit 19 determines whether the bladder region represents the bladder having the abnormal bladder pattern.

公开(公告)号：US20230334656A1

公开(公告)日：2023-10-19

申请号：US17922809

申请日：2021-05-03

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Vidya Madapusi Srinivas PRASAD ,  Srinivasa Rao KUNDETI ,  Manikanda Krishnan V ,  Vijayananda JAGANNATHA

IPC: G06T7/00 ,  G06T3/40 ,  G06V10/44 ,  G06V10/42 ,  G06V10/82 ,  G06V10/774 ,  G06V10/764 ,  G16H30/40 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G06T3/4053 ,  G06V10/44 ,  G06V10/42 ,  G06V10/82 ,  G06V10/774 ,  G06V10/764 ,  G16H30/40 ,  G16H50/20 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/10116 ,  G06T2207/30004 ,  G06V2201/031

Abstract: Disclosed herein is a method and system for identifying abnormal images in a set of medical images for optimal assessment of the medical images. A plurality of global features from each medical image is extracted based on pretrained weights associated with each global feature. Similarly, plurality of local features from each medical image is extracted analyzing a predefined number of image patches generated from a higher resolution image corresponding to each medical image. Further, an abnormality score for each medical image is determined based on weights associated with a combined feature set obtained by concatenating the plurality of global features and the plurality of local features. Thereafter, the medical image is identified as an abnormal image when the abnormality score of the medical image is higher than a predefined first threshold score.

公开(公告)号：US20230316796A1

公开(公告)日：2023-10-05

申请号：US17693272

申请日：2022-03-11

Applicant: Kanchan Ghimire ,  Quan Chen ,  Xue Feng

Inventor： Kanchan Ghimire ,  Quan Chen ,  Xue Feng

IPC: G06V40/10 ,  G06V10/26 ,  G06V10/44 ,  G06V10/28 ,  G06V10/34 ,  G16H30/20 ,  G16H30/40

CPC classification number: G06V40/10 ,  G06V10/267 ,  G06V10/273 ,  G06V10/28 ,  G06V10/34 ,  G06V10/457 ,  G16H30/20 ,  G16H30/40 ,  G06V2201/031

Abstract: 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.

公开(公告)号：US20230298136A1

公开(公告)日：2023-09-21

申请号：US17654864

申请日：2022-03-15

Applicant: GE Precision Healthcare LLC

Inventor： Bipul Das ,  Rakesh Mullick ,  Deepa Anand ,  Sandeep Dutta ,  Uday Damodar Patil ,  Maud Bonnard

IPC: G06T3/60 ,  G06T7/73 ,  G06V10/82 ,  G06V10/774 ,  G16H50/20

CPC classification number: G06T3/60 ,  G06T7/73 ,  G06V10/82 ,  G06V10/774 ,  G16H50/20 ,  G06T2200/04 ,  G06V2201/031 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: Systems/techniques that facilitate deep learning multi-planar reformatting of medical images are provided. In various embodiments, a system can access a three-dimensional medical image. In various aspects, the system can localize, via execution of a machine learning model, a set of landmarks depicted in the three-dimensional medical image, a set of principal anatomical planes depicted in the three-dimensional medical image, and a set of organs depicted in the three-dimensional medical image. In various instances, the system can determine an anatomical orientation exhibited by the three-dimensional medical image, based on the set of landmarks, the set of principal anatomical planes, or the set of organs. In various cases, the system can rotate the three-dimensional medical image, such that the anatomical orientation now matches a predetermined anatomical orientation.

公开(公告)号：US20230237771A1

公开(公告)日：2023-07-27

申请号：US18127657

申请日：2023-03-29

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Qingfu Wen ,  Yuexi Du ,  Sen Yang ,  Peng Yang ,  Jun Zhang ,  Xiao Han

IPC: G06V10/77 ,  G06T7/00

CPC classification number: G06V10/7715 ,  G06T7/0012 ,  G06T2207/20081 ,  G06V2201/031

Abstract: The present application provides a self-supervised learning method performed by a computer device. The method includes: performing a data enhancement on an original medical image to obtain a first enhanced image and a second enhanced image, the first enhanced image and the second enhanced image being positive samples of each other; performing feature extractions on the first enhanced image and the second enhanced image by a feature extraction model to obtain a first image feature of the first enhanced image and a second image feature of the second enhanced image; determining a model loss of the feature extraction model based on the first image feature, the second image feature, and a negative sample image feature, the negative sample image feature being an image feature corresponding to other original medical images; and training the feature extraction model based on the model loss.

公开(公告)号：US11710290B2

公开(公告)日：2023-07-25

申请号：US16379313

申请日：2019-04-09

Applicant: FUJIFILM Corporation

Inventor： Kazuhiro Hirota ,  Kaku Irisawa ,  Dai Murakoshi ,  Yoshiro Imai ,  Tsuyoshi Matsumoto

IPC: A61B5/00 ,  G06V10/143 ,  A61B5/02 ,  G06T7/00 ,  G06T7/33 ,  G06T7/11 ,  G01N29/24 ,  G06T7/149 ,  A61B8/13 ,  A61B8/06 ,  G06F18/22 ,  G06V10/74 ,  G06V40/14

CPC classification number: G06V10/143 ,  A61B5/0095 ,  A61B5/02007 ,  A61B5/7425 ,  A61B8/06 ,  A61B8/13 ,  G01N29/2418 ,  G06F18/22 ,  G06T7/0016 ,  G06T7/11 ,  G06T7/149 ,  G06T7/337 ,  G06V10/761 ,  G01N2291/02466 ,  G06T2207/10132 ,  G06T2207/20024 ,  G06T2207/20221 ,  G06V40/14 ,  G06V2201/03 ,  G06V2201/031

Abstract: A photoacoustic image evaluation apparatus includes a processor configured to acquire a first photoacoustic image generated at a first point in time and a second photoacoustic image generated at a second point in time before the first point in time, the first and second photoacoustic images being photoacoustic images generated by detecting photoacoustic waves generated inside a subject, who has been subjected to blood vessel regeneration treatment, by emission of light into the subject; acquire a blood vessel regeneration index, which indicates a state of a blood vessel by the regeneration treatment, based on a difference between a blood vessel included in the first photoacoustic image and a blood vessel included in the second photoacoustic image; and display the blood vessel regeneration index on a display.