公开(公告)号：WO2019125790A1

公开(公告)日：2019-06-27

申请号：PCT/US2018/064483

申请日：2018-12-07

申请人： VERATHON INC.

发明人： YANG, Fuxing ,  CHOI, Joon Hwan

IPC分类号： A61B8/08 ,  A61B8/00 ,  A61B5/00 ,  G06N3/02 ,  G06T7/00 ,  G16H50/20 ,  G01S7/52

CPC分类号： A61B8/5223 ,  A61B5/4325 ,  A61B5/4381 ,  A61B5/7267 ,  A61B8/085 ,  A61B8/145 ,  A61B8/463 ,  A61B8/5269 ,  A61B8/5292 ,  G06K9/627 ,  G06K9/628 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06T5/001 ,  G06T7/0012 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30168 ,  G16H30/40 ,  G16H50/20

摘要： A method for providing artifact detection and visualization during ultrasound image collection is performed by a processor in an ultrasound system. The method includes receiving ultrasound image data from an ultrasound probe, detecting areas with artifacts in the ultrasound image data, classifying the areas with artifacts into one of a plurality of available artifact classes, generating an indication of the areas with artifact for an ultrasound-based image, wherein the indications include a designation of the artifact class, and presenting to an operator the ultrasound-based image and the indication of the areas with artifacts.

公开(公告)号：WO2019083227A1

公开(公告)日：2019-05-02

申请号：PCT/KR2018/012376

申请日：2018-10-19

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： LEE, Dong-jae ,  OH, Hyun-hwa ,  KIM, Se-min ,  SONG, Jeong-yong ,  LEE, Hyun-jung

IPC分类号： G16H50/20 ,  G06N3/02 ,  G16H50/30 ,  G06T7/00 ,  G06T1/00

CPC分类号： G06T7/0012 ,  A61B5/055 ,  A61B5/7267 ,  A61B6/032 ,  A61B6/06 ,  G06K9/4609 ,  G06K9/66 ,  G06K2209/05 ,  G06N3/08 ,  G06T7/0016 ,  G06T7/30 ,  G06T11/00 ,  G06T2207/10081 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30016 ,  G06T2207/30096 ,  G16H30/40 ,  G16H50/20

摘要： A device and a method for medical image processing are provided. The medical image processing method may include: obtaining a plurality of actual medical images corresponding to a plurality of patients and including lesions; training a deep neural network (DNN), based on the plurality of actual medical images, to obtain a first neural network for predicting a variation in a lesion over time, the lesion being included in a first medical image of the plurality of actual medical images, wherein the first medical image is obtained at a first time point; and obtaining, via the first neural network, a second medical image representing a state of the lesion at a second time point different from the first time point.

公开(公告)号：WO2018201857A1

公开(公告)日：2018-11-08

申请号：PCT/CN2018/082407

申请日：2018-04-09

申请人： JIANGSU HUABEN HEALTH LIFE SCIENCE AND TECHNOLOGY CO., LTD.

发明人： WU, Ben Jun

IPC分类号： A61B5/02

CPC分类号： A61B5/0205 ,  A61B5/021 ,  A61B5/022 ,  A61B5/024 ,  A61B5/02438 ,  A61B5/08 ,  A61B5/201 ,  A61B5/4064 ,  A61B5/416 ,  A61B5/4244 ,  A61B5/4854 ,  A61B5/6824 ,  A61B5/7267 ,  A61B5/7275 ,  G16H40/63 ,  G16H50/20 ,  G16H50/30

摘要： Techniques and examples pertaining to evaluating a health condition of an aspect of a patient are described. A method for evaluating the health condition of the aspect of the patient may involve obtaining successive measurement readings of a vital sign concurrently from both a left arm and a right arm of the patient for a plurality of times. The method may also involve calculating a characteristic value based on the measurement readings. The method may also involve designating a health indicator based on the characteristic value and a standard value associated with the aspect of the patient, such that the health indicator serves as an indication of the health condition of the aspect of the patient. The aspect of the patient may be a body organ of the patient. The method may further involve diagnosing the patient based on the health indicator.

公开(公告)号：WO2018047058A1

公开(公告)日：2018-03-15

申请号：PCT/IB2017/055322

申请日：2017-09-05

申请人： FACULDADE DE CIÊNCIAS E TECNOLOGIA DA UNIVERSIDADE NOVA DE LISBOA ,  NMT

发明人： BORÍSSOVNA VASSILENKO, Valentina ,  DA COSTA SANTOS, Paulo Henrique

IPC分类号： A61B5/097 ,  A61B5/00 ,  G06F19/00

CPC分类号： A61B5/097 ,  A61B5/7267 ,  A61B5/7475 ,  G16H20/40 ,  G16H40/63 ,  G16H50/20 ,  G16H50/30

摘要： The present application is related with a system (1) and respective method of operation, for controlled and selective sampling of exhaled air from a predetermined part of the respiratory tree. The system (1) is comprised by two attachable modules: a portable sampling device (3) and a hardware module (12), controlled by a machine learning software (16) loaded on a processing device. The technology developed detects and imposes a breathing rhythm to the subject according to its characteristics (age, genre and physiological condition) and to synchronize the subject's breathing cycle with a representative modelled breathing cycle using the machine learning process (16). Then, it is predicted the instants for opening/closing the valve (9) to conduct the selected breath portion into the analyser (17) or collector (18). The system (1) disclosed allows monitoring, diagnosing and assessing medical conditions of the patient, as well as assessing the inflammation degree of the respiratory airways of the subject.

摘要翻译： 本申请涉及用于对来自呼吸树的预定部分的呼出空气进行受控和选择性采样的系统（1）和相应的操作方法。 系统（1）由两个可附接模块组成：便携式采样装置（3）和硬件模块（12），由装载在处理装置上的机器学习软件（16）控制。 开发的技术根据其特点（年龄，流派和生理状况）检测受试者的呼吸节奏，并使用机器学习过程（16）将受试者的呼吸周期与代表性的模拟呼吸周期同步。 然后，预测打开/关闭阀（9）的时刻将选定的呼吸部分导入分析器（17）或收集器（18）。 所公开的系统（1）允许监测，诊断和评估患者的医疗状况，以及评估患者的呼吸道的炎症程度。

公开(公告)号：WO2018045274A1

公开(公告)日：2018-03-08

申请号：PCT/US2017/049832

申请日：2017-09-01

申请人： THE GENERAL HOSPITAL CORPORATION

发明人： ROSEN, Matthew, S. ,  ZHU, Bo ,  ROSEN, Bruce, R.

IPC分类号： G06N3/02 ,  G01R33/12 ,  G01R33/20 ,  G06K9/36

CPC分类号： G06T11/006 ,  A61B5/0035 ,  A61B5/0059 ,  A61B5/055 ,  A61B5/7267 ,  A61B5/7425 ,  A61B6/032 ,  A61B6/037 ,  A61B6/463 ,  A61B6/5247 ,  A61B8/463 ,  A61B8/5261 ,  G01R33/12 ,  G01R33/4818 ,  G01R33/4824 ,  G01R33/5608 ,  G06K9/623 ,  G06K9/6274 ,  G06K2209/05 ,  G06N3/0454 ,  G06N3/08 ,  G06T2210/41 ,  G16H30/40

摘要： A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.

摘要翻译： 系统可以使用数据驱动的流形学习技术将传感器数据从传感器域转换到图像域，所述数据驱动的流形学习技术例如可以使用神经网络来实现。 传感器数据可以由图像传感器产生，该图像传感器可以是成像系统的一部分。 系统中神经网络的完全连接层可以应用于传感器数据以将激活功能应用于传感器数据。 激活函数可以是双曲正切激活函数。 然后可以应用卷积层来卷积完全连接的层的输出以进行高级特征提取。 可以将输出层应用于卷积层的输出以对输出解卷积并在图像域中产生图像数据。

公开(公告)号：WO2017187269A1

公开(公告)日：2017-11-02

申请号：PCT/IB2017/000634

申请日：2017-04-28

申请人： SIEMENS HEALTHCARE GMBH

发明人： ITU, Lucian Mihai ,  PASSERINI, Tiziano ,  RAPAKA, Saikiran ,  SHARMA, Puneet

IPC分类号： A61B5/00 ,  A61B5/02 ,  A61B6/00 ,  A61B8/08 ,  A61B5/026

CPC分类号： A61B5/0035 ,  A61B5/0044 ,  A61B5/0073 ,  A61B5/02007 ,  A61B5/026 ,  A61B5/7221 ,  A61B5/7267 ,  A61B5/7275 ,  A61B5/7282 ,  A61B5/743 ,  A61B6/032 ,  A61B6/503 ,  A61B6/504 ,  A61B6/507 ,  A61B6/5217 ,  A61B6/5247 ,  A61B8/0883 ,  A61B8/0891 ,  A61B8/5223 ,  A61B8/5261 ,  A61B2576/023 ,  G16H40/20 ,  G16H50/20 ,  G16H50/50

摘要： A method for providing a personalized evaluation of CAD for a patient includes acquiring one or more non-invasive images depicting a patient's coronary arteries and extracting a first set of features of interest from the one or more non-invasive images. A machine learning model is applied to the first set of features of interest to yield a prediction of one or more coronary measures of interest. One or more invasive images depicting the patient's coronary arteries are acquired and a second set of features of interest are extracted from the one or more invasive images. The first set of features of interest and the second set of features of interest are combined to yield a combined set of features of interest. Then, the machine learning model may be applied to the combined set of features of interest to yield an enhanced prediction of the coronary measures of interest.

摘要翻译： 用于为患者提供CAD的个性化评估的方法包括获取描述患者的冠状动脉的一个或多个非侵入性图像并且从一个或多个非侵入性图像中提取第一组感兴趣特征， 无创图像。 机器学习模型被应用于第一组感兴趣的特征以产生一个或多个感兴趣的冠状动脉测量的预测。 获取描述患者冠状动脉的一个或多个侵入性图像，并从一个或多个侵入性图像提取第二组感兴趣特征。 第一组感兴趣特征和第二组感兴趣特征被组合以产生一组感兴趣特征的组合。 然后，可以将机器学习模型应用于感兴趣的特征的组合集合，以产生对感兴趣的冠状动脉测量的增强预测。

公开(公告)号：WO2017180643A1

公开(公告)日：2017-10-19

申请号：PCT/US2017/027037

申请日：2017-04-11

申请人： CANON U.S.A., INC. ,  THE BRIGHAM AND WOMEN'S HOSPITAL INC.

发明人： ABAYAZID, Momen ,  HATA, Nobuhiko ,  KATO, Takahisa ,  NINNI, Brian ,  TOKUDA, Junichi ,  SILVERMAN, Stuart G. ,  LU, Zhimin

IPC分类号： A61B34/20 ,  A61B5/05 ,  A61B5/11 ,  A61B6/00 ,  A61B6/03 ,  A61B10/02 ,  A61B10/04

CPC分类号： A61B34/20 ,  A61B5/066 ,  A61B5/113 ,  A61B5/6848 ,  A61B5/7267 ,  A61B6/032 ,  A61B6/5211 ,  A61B10/0233 ,  A61B17/3403 ,  A61B18/1477 ,  A61B90/11 ,  A61B2017/00115 ,  A61B2017/00699 ,  A61B2017/00716 ,  A61B2018/00577 ,  A61B2034/2048 ,  A61B2034/2051 ,  A61B2090/374 ,  A61B2090/3762 ,  A61B2562/0219

摘要： A method and system for motion tracking of a target organ are provided. A tracking needle is partially inserted into an organ. The needle has a sensor element for obtaining continuous needle orientation information which can be used to determine organ motion due to respiration during percutaneous needle insertion.

摘要翻译： 提供了一种用于目标器官的运动跟踪的方法和系统。 跟踪针部分插入器官。 针具有用于获得连续的针定向信息的传感器元件，该信息可以用于确定在经皮针插入期间由于呼吸而引起的器官运动。

公开(公告)号：WO2017117798A1

公开(公告)日：2017-07-13

申请号：PCT/CN2016/070471

申请日：2016-01-08

申请人： HEARTISANS LIMITED

发明人： LUI, Hin Wai

IPC分类号： A61B5/02 ,  A61B5/1455

CPC分类号： A61B5/6843 ,  A61B5/02405 ,  A61B5/02416 ,  A61B5/0531 ,  A61B5/681 ,  A61B5/7267 ,  G06F19/00

摘要： Device and method for assessing the likelihood of an imminent occurrence of cardiac arrest. The device comprises an optical sensor (203) for monitoring heart rhythm of a person. A Machine Learning Algorithm such as an Artificial Neural Network (ANN) algorithm analyses features from a trending of pulse intervals in the person's heart rhythm in real time to make the assessment. The device is provided in wearable form, such as a wrist worn device (101).

摘要翻译： 用于评估即将发生心脏骤停的可能性的装置和方法。 该装置包括用于监测人的心律的光学传感器（203）。 诸如人工神经网络（ANN）算法之类的机器学习算法通过实时分析人的心律中的脉搏间隔的特征来进行评估。 该设备以可穿戴形式提供，例如腕戴式设备（101）。

公开(公告)号：WO2017117183A1

公开(公告)日：2017-07-06

申请号：PCT/US2016/068814

申请日：2016-12-28

申请人： THE UNIVERSITY OF NORTH CAROLINA AT CHAPEL HILL ,  DUKE UNIVERSITY

发明人： BATTAGLINI, Claudio, Luiz ,  MANN, Brian, Patrick ,  MAZZOLENI, Michael, Joseph

IPC分类号： A61B5/0205 ,  A61B5/024 ,  A61B5/145 ,  A61B5/22

CPC分类号： A61B5/0205 ,  A61B5/024 ,  A61B5/091 ,  A61B5/1118 ,  A61B5/7267 ,  A61B2503/10 ,  G06F19/00 ,  G06F19/34

摘要： A system for estimating maximum heart rate and maximal oxygen uptake from submaximal exercise intensities can include an exercise intensity monitor, a cardiopulmonary monitor, and one or more computers. The computers can be configured, by virtue of appropriate programming, to receive submaximal exercise intensity data from the exercise intensity monitor and submaximal cardiopulmonary data from the cardiopulmonary monitor while a user, who coupled to the exercise intensity monitor and the cardiopulmonary monitor, is performing an exercise at a submaximal exercise intensity. The one or more computers then determine a heuristic estimate of a maximal cardiopulmonary state of the user based on the submaximal exercise intensity data and the submaximal cardiopulmonary data.

摘要翻译： 用于从次最大运动强度估计最大心率和最大氧摄取的系统可以包括运动强度监测器，心肺监测器以及一个或多个计算机。 通过适当的编程，计算机可以被配置为接收来自运动强度监视器的次最大运动强度数据和来自心肺监视器的次最大心肺数据，而耦合到运动强度监视器和心肺监视器的用户正在执行 以次最大运动强度进行锻炼。 一个或多个计算机然后基于次最大运动强度数据和次最大心肺数据确定用户的最大心肺状态的启发式估计。

公开(公告)号：WO2017106770A1

公开(公告)日：2017-06-22

申请号：PCT/US2016/067358

申请日：2016-12-16

申请人： COGNOA, INC. ,  ABBAS, Halim

发明人： ABBAS, Halim ,  VAUGHAN, Brent

IPC分类号： G06Q50/24 ,  G06Q50/22 ,  A61B5/00 ,  G06F15/18 ,  G06F17/30

CPC分类号： G06F19/30 ,  A61B5/0022 ,  A61B5/168 ,  A61B5/4088 ,  A61B5/4833 ,  A61B5/486 ,  A61B5/7267 ,  G06F19/00

摘要： The methods and apparatus disclosed herein provide digital diagnostics and digital therapeutics to patients. The digital personalized medicine system uses digital data to assess or diagnose symptoms of a patient, and feedback from the patient response to treatment is considered to update the personalized therapeutic interventions. The methods and apparatus disclosed herein can also diagnose and treat cognitive function of a subject, with fewer questions, decreased amounts of time, and determine a plurality of behavioral, neurological or mental health disorders, and provide clinically acceptable sensitivity and specificity in the diagnosis and treatment.

摘要翻译： 本文公开的方法和装置向患者提供数字诊断和数字治疗。 数字个性化医疗系统使用数字数据来评估或诊断患者的症状，并且来自患者对治疗的反应的反馈被认为是更新个性化治疗干预。 本文公开的方法和装置还可以用更少的问题，减少的时间量来诊断和治疗受试者的认知功能，并且确定多种行为，神经或精神健康障碍，并且在诊断中提供临床上可接受的敏感性和特异性，并且 治疗