公开(公告)号：US20240153243A1

公开(公告)日：2024-05-09

申请号：US18447328

申请日：2023-08-10

Applicant: Hangzhou Dianzi University

Inventor： Bishi He ,  Zhe Xu ,  Yuanjiao Chen ,  Diao Wang ,  Hui Chen

IPC: G06V10/764 ,  G06T7/00

CPC classification number: G06V10/765 ,  G06T7/0012 ,  G06T2207/10081 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30061 ,  G06V2201/031

Abstract: A Wasserstein distance and difference metric-combined chest radiograph anomaly identification domain adaptation method and a corresponding system are provided. The method includes the following steps: step 1, data preparation and data pre-processing for chest radiographs; step 2, multi-scale feature extraction based on a swin transformer network; step 3, loss minimization based on a Wasserstein distance and a contrastive domain discrepancy; and step 4, using the model to perform chest radiograph prediction after verifying the model. The method selects source domain samples closest to target domain samples, narrows a distance of the same class between the target domain samples and the source domain samples in feature space, and expands a distance between different classes. Meanwhile, a classification prediction task for the chest radiographs is performed by using the multi-scale features, improving a receptive field and capturing more information conducive to the classification prediction task.

公开(公告)号：US11929174B2

公开(公告)日：2024-03-12

申请号：US16985237

申请日：2020-08-05

Applicant: FUJIFILM Corporation

Inventor： Yoshiro Kitamura

IPC: G06N3/08 ,  G06F18/21 ,  G06F18/2431 ,  G06N3/045 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G16H50/20 ,  G16H30/40

CPC classification number: G16H50/20 ,  G06F18/217 ,  G06F18/2431 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V2201/031 ,  G16H30/40

Abstract: A machine learning method and an apparatus, a program, a learned model, and a discrimination apparatus capable of controlling a calculation amount by learning a new task without changing output performance for an existing task in a learned network are provided. A machine learning method according to one aspect of the present disclosure includes a step of adding a new feature amount to at least one intermediate layer included in a learned first neural network that has learned a task of performing first class classification, a step of generating a second neural network having a structure in which a network structure of a calculation path of an existing feature amount of the first neural network is maintained and a new feature amount of a subsequent layer is calculated by performing processing of convolving each of the existing feature amount and the new feature amount, and a step of causing the second neural network to acquire a processing function of performing second class classification by performing learning of the second neural network using a set of learning data corresponding to the second class classification.

公开(公告)号：US20240062515A1

公开(公告)日：2024-02-22

申请号：US18260461

申请日：2021-11-09

Applicant: VUNO Inc.

Inventor： Hyunwoo OH ,  Sejin PARK ,  Eunpyeong HONG ,  Dongsoo LEE

IPC: G06V10/764 ,  G06N3/042 ,  G06N3/045 ,  G06T7/00 ,  G06V10/40 ,  G06V10/766 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V10/764 ,  G06N3/042 ,  G06N3/045 ,  G06T7/0012 ,  G06V10/40 ,  G06V10/766 ,  G06V10/776 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06V2201/031

Abstract: According to an exemplary embodiment of the present disclosure, a method for classification by using a deep learning model, the method being performed by a computing device, is disclosed. The method may include: extracting a feature vector interpretable based on domain knowledge by inputting an image including at least one object of interest into a first neural network of a deep learning model; and estimating a probability value corresponding to a classification task by inputting the feature vector into a second neural network of the deep learning model. In this case, the deep learning model may be pre-trained based on a loss function having an output value of the first neural network and an output value of the second neural network as input variables.

公开(公告)号：US20240062439A1

公开(公告)日：2024-02-22

申请号：US18495787

申请日：2023-10-27

Applicant: FUJIFILM Corporation

Inventor： Takuya TSUTAOKA

IPC: G06T11/20 ,  G06T7/13 ,  G06V10/764 ,  G06T7/11

CPC classification number: G06T11/203 ,  G06T7/13 ,  G06V10/764 ,  G06T7/11 ,  G06V2201/031 ,  G06T2207/10132 ,  G06T2207/10068 ,  G06T2207/30092 ,  G06T2207/20081

Abstract: Provided are a display processing apparatus, method, and program for displaying a region of a detection target object in an image in a manner intelligible to a user even if the contour or boundary of the detection target object is unclear. A transmitting/receiving unit (100) and an image generation unit (102), which function as an image acquisition unit, perform an image acquisition process for sequentially acquiring ultrasound images. A region extraction unit (106) extracts a rectangular region including an organ, which is a detection target object, from an acquired ultrasound image. A curve generation unit (108) generates, in the extracted rectangular region, a curve corresponding to the organ in the rectangular region. An image combining unit (109) combines the ultrasound image and the generated curve corresponding to the organ. A display control unit (110) causes a monitor (18) to display the ultrasound image combined with the curve.

公开(公告)号：US20240024037A1

公开(公告)日：2024-01-25

申请号：US18265470

申请日：2021-12-06

Applicant: KONINKLIJKE PHILIPS N.V.

Inventor： Towa Matsumura ,  Eduardo Ortiz Vazquez ,  Maarten Heye ,  Andrea Laghi

IPC: A61B34/20 ,  A61B8/08 ,  A61B8/00 ,  G06T15/08 ,  G06V20/50 ,  G06V10/44 ,  G06V10/98

CPC classification number: A61B34/20 ,  A61B8/0841 ,  A61B8/463 ,  A61B8/467 ,  A61B8/483 ,  A61B8/0883 ,  A61B8/54 ,  G06T15/08 ,  G06V20/50 ,  G06V10/44 ,  G06V10/98 ,  A61B2034/2063 ,  A61B2034/2065 ,  G06T2200/24 ,  G06V2201/031

Abstract: Systems and methods for providing image guidance during interventional medical procedures are disclosed. Methods involve receiving a user selection of an interventional medical procedure at an adaptive user interface, acquiring volumetric image data of a region of interest using 3D ultrasound, and identifying at least one anatomical landmark within the volumetric image data specific to the selected procedure. Methods further involve reconstructing one or more ultrasound images along predefined image planes necessary for performing the selected procedure. The reconstructed images are displayed on the user interface for providing real-time guidance to a clinician performing the procedure, which may involve deploying one or more interventional instruments within the region of interest.

公开(公告)号：US20240013434A1

公开(公告)日：2024-01-11

申请号：US18470514

申请日：2023-09-20

Applicant: TERUMO KABUSHIKI KAISHA

Inventor： Kohtaroh KUSU ,  Yuki SAKAGUCHI

IPC: G06T7/73 ,  G06V20/50 ,  G16H30/40

CPC classification number: G06T7/74 ,  G06V20/50 ,  G16H30/40 ,  G06V2201/031 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06T2207/30204 ,  G06T2207/10132 ,  G06T2207/10101

Abstract: The program causes a computer to execute processing of: acquiring a medical image obtained by imaging a luminal organ using a catheter; specifying a direction of interest indicating a direction of a site of interest with respect to the medical image on the basis of the acquired medical image; and displaying information indicating the specified direction of interest in association with the medical image or displaying the medical image subjected to image processing on the basis of the information indicating the direction of interest.

公开(公告)号：US20230414288A1

公开(公告)日：2023-12-28

申请号：US18242888

申请日：2023-09-06

Applicant: Advanced Neuromodulation Systems, Inc.

Inventor： Yagna Pathak ,  Simeng Zhang ,  Dehan Zhu ,  Anahita Kyani ,  Hyun-Joo Park ,  Erika Ross

IPC: A61B34/10 ,  G06T7/70 ,  G16H30/40 ,  G06V10/25 ,  A61B5/055 ,  A61B6/03 ,  A61B6/00 ,  G06N3/08 ,  G06T7/00 ,  G06F18/214

CPC classification number: A61B34/10 ,  G06T7/70 ,  G16H30/40 ,  G06V10/25 ,  A61B5/055 ,  A61B6/032 ,  A61B6/469 ,  A61B6/501 ,  A61B6/5223 ,  A61B6/5247 ,  G06N3/08 ,  G06T7/0014 ,  G06F18/214 ,  A61B2034/107 ,  G06V2201/031 ,  A61B2505/05 ,  A61N1/0534

Abstract: A system and method for facilitating DBS electrode trajectory planning using a machine learning (ML)-based feature identification scheme configured to identify and distinguish between various regions of interest (ROIs) and regions of avoidance (ROAs) in a patient's brain scan image. In one arrangement, standard orientation image slices as well as re-sliced images in non-standard orientations are provided in a labeled input dataset for training a CNN/ANN for distinguishing between ROIs and ROAs. Upon identification of the ROIs and ROAs in the patient's brain scan image, an optimal trajectory for implanting a DBS lead may be determined relative to a particular ROI while avoiding any ROAs.

公开(公告)号：US11836925B2

公开(公告)日：2023-12-05

申请号：US17664422

申请日：2022-05-22

Applicant: SHANGHAI UNITED IMAGING INTELLIGENCE CO., LTD.

Inventor： Miaofei Han ,  Yaozong Gao ,  Yu Zhang ,  Yiqiang Zhan

IPC: G06T7/11 ,  G06T7/62 ,  G06T7/149 ,  A61B5/107 ,  G06V30/24

CPC classification number: G06T7/11 ,  A61B5/1073 ,  G06T7/149 ,  G06T7/62 ,  G06V30/2504 ,  A61B2576/02 ,  G06T2207/30084 ,  G06V2201/031 ,  G06V2201/032

Abstract: A system for image segmentation is provided. The system may obtain a target image including an ROI, and segment a preliminary region representative of the ROI from the target image using a first ROI segmentation model corresponding to a first image resolution. The system may segment a target region representative of the ROI from the preliminary region using a second ROI segmentation model corresponding to a second image resolution. At least one model of the first and second ROI segmentation models may at least include a first convolutional layer and a second convolutional layer downstream to the first convolutional layer. A count of input channels of the first convolutional layer may be greater than a count of output channels of the first convolutional layer, and a count of input channels of the second convolutional layer may be smaller than a count of output channels of the second convolutional layer.

公开(公告)号：US20230386113A1

公开(公告)日：2023-11-30

申请号：US18322719

申请日：2023-05-24

Applicant: Rigshospitalet ,  CANON MEDICAL SYSTEMS CORPORATION

Inventor： Takahiko NISHIOKA ,  Klaus FUGLSANG KOFOED ,  Mathias BECH MOELLER

IPC: G06T11/60 ,  G06T7/00 ,  G06V20/50 ,  G06T7/70 ,  G16H30/40

CPC classification number: G06T11/60 ,  G06T7/0012 ,  G06V20/50 ,  G06T7/70 ,  G16H30/40 ,  G06T2207/30048 ,  G06T2207/30101 ,  G06V2201/031 ,  G06T2210/41

Abstract: A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to obtain a medical image related to the heart. The processing circuitry is configured to generate a polar map indicating myocardial function information on the basis of the medical image. The processing circuitry is configured to cause a display to display a blood vessel image indicating forms of blood vessels included in the heart so as to be superimposed on the polar map. The processing circuitry is configured to receive an operation to designate at least one of the blood vessels displayed over the polar map. The processing circuitry is configured to identify information associated with the blood vessel designated by the operation. The processing circuitry is configured to cause the display to display the information associated with the blood vessel.

公开(公告)号：US20230368375A1

公开(公告)日：2023-11-16

申请号：US17935619

申请日：2022-09-27

Applicant: Taichung Veterans General Hospital ,  Tunghai University

Inventor： Ming-Cheng CHAN ,  Kai-Chih PAI ,  Wen-Cheng CHAO ,  Yu-Jen HUANG ,  Chieh-Liang WU ,  Min-Shian WANG ,  Chien-Lun LIAO ,  Ta-Chun HUNG ,  Yan-Nan LIN ,  Hui-Chiao YANG ,  Ruey-Kai SHEU ,  Lun-Chi CHEN

IPC: G06T7/00 ,  G06T7/11 ,  G06T7/174 ,  G06V10/764

CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T7/174 ,  G06V10/764 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/30061 ,  G06T2207/30048 ,  G06V2201/031

Abstract: A respiratory status classifying method is for classifying as one of at least two respiratory statuses and includes a training's physiological parameter inputting step, a training's chest image inputting step, a characteristic physiological parameter generating step, a characteristic chest image generating step, a training step and a classifier generating step. The characteristic chest image generating step includes processing at least a part of the training's chest images, segmenting images of a left lung, a right lung and a heart from each of the training's chest images that are processed, and enhancing image data of the images being segmented, so as to generate a plurality of characteristic chest images. The training step includes training a plurality of characteristic physiological parameters and the characteristic chest images by at least one machine learning algorithm.