专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2023089459A1 SYSTEMS AND METHODS FOR VITREOUS DISEASE SEVERITY MEASUREMENT 审中-公开
公开(公告)号：WO2023089459A1
公开(公告)日：2023-05-25
申请号：PCT/IB2022/060853
申请日：2022-11-10
申请人： ALCON INC.
发明人： HALLEN, Paul R.
IPC分类号： G16H10/20 , G16H20/30 , G16H30/40 , G16H50/20 , A61B8/10 , G16H50/30
摘要： Certain aspects presented herein provide systems and methods utilizing one or more machine learning models in determining a severity of vitreous disease, and in particular, vitreous opacities. Such machine learning models are trained based on historical patient data to determine the severity of vitreous opacities afflicting a current patient. The severity determination may thereafter be utilized to inform treatment decisions for the current patient, including patient suitability for certain types of treatment.

2. 发明申请

WO2023086411A1 CAMERA PROBE NAVIGATION WITHIN CAVITY 审中-公开
公开(公告)号：WO2023086411A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/049443
申请日：2022-11-09
申请人： UNIVERSITY OF WASHINGTON
发明人： SEIBEL, Eric, J. , GONG, Chen , LEWIS, Andrew , ZHOU, Yaxuan , HANNAFORD, Blake
IPC分类号： G06T7/73 , G16H30/40 , A61B1/307 , G06T7/10 , G06T7/246
摘要： A method includes capturing, via a camera that is inserted into a cavity, a first image of a surface defining the cavity and compressing the first image, using a compression algorithm, to generate a first feature vector. The method also includes identifying a second feature vector of a plurality of second feature vectors that best matches the first feature vector. The plurality of second feature vectors was generated by compressing second images of the surface using the compression algorithm. The second images were captured prior to insertion of the camera into the cavity and prior to capturing the first image. The method also includes generating, using the second feature vector, output indicating a position and/or an orientation of the camera as the camera captured the first image.

3. 发明申请

WO2023076836A1 METHODS, SYSTEMS, AND DEVICES FOR CACHING AND MANAGING MEDICAL IMAGE FILES 审中-公开
公开(公告)号：WO2023076836A1
公开(公告)日：2023-05-04
申请号：PCT/US2022/078500
申请日：2022-10-21
申请人： ZEBRE TECHNOLOGIES, INC.
发明人： COPPERMAN, Ross , STUNKEL, Bryan , SAVOIE, Brent
IPC分类号： G16H30/20 , G16H30/40 , G16H10/60
摘要： Disclosed herein are methods, systems, and devices for solving the problem of caching large medical images during workflow. In one embodiment, a method is implemented on at least one computing device. The method includes receiving a source medical image file from a first remote device; caching the source medical image file in local memory; determining relevant medical image data, first non-relevant medical image data, and second non-relevant medical image data within the source medical image file; removing the second non-relevant medical image data to create a memory reduced medical image file; storing the memory reduced medical image file in the local memory; and transmitting the memory reduced medical image file to a second remote device.

4. 发明申请

WO2023076104A1 AUTOMATIC DEPTH SELECTION FOR ULTRASOUND IMAGING 审中-公开
公开(公告)号：WO2023076104A1
公开(公告)日：2023-05-04
申请号：PCT/US2022/047320
申请日：2022-10-20
申请人： ECHONOUS, INC.
发明人： COOK, Matthew , AYINDE, Babajide
IPC分类号： A61B8/00 , A61B8/08 , G16H30/40 , G16H40/40 , G06N3/08
摘要： A facility for assessing an ultrasound image captured from a patient with a particular depth setting is described. The facility subjects the received ultrasound image to at least one neural network to produce, for each neural network, an inference. On the basis of the produced inferences, the facility determines whether the depth setting at which the ultrasound image was captured was optimal.

5. 发明申请

WO2023075303A1 인공지능 기반의 내시경 진단 보조 시스템 및 이의 제어방법 审中-公开
公开(公告)号：WO2023075303A1
公开(公告)日：2023-05-04
申请号：PCT/KR2022/016127
申请日：2022-10-21
申请人： 주식회사 카이미
发明人： 정준원 , 김광기
IPC分类号： A61B1/00 , G16H50/20 , G16H30/40 , G06T7/00
摘要： 본 발명은 환자의 신체 내부기관에 대한 내시경 영상을 제공하는 내시경 모듈; 상기 환자에 대한 임의의 의료정보를 입력가능하게 구성되는 입력모듈; 상기 내시경 모듈로부터 제공되는 내시경 영상을 미리 저장된 이미지 프로세싱 프로그램을 통해 분석하여 병변정보를 검출하고, 미리 저장된 병변진단 프로그램을 통해 상기 검출된 병변정보와 상기 입력모듈로부터 입력되는 의료정보를 매칭시키면서 상기 매칭결과에 대응하는 악성여부 및 악성확률 중 적어도 하나의 진단정보를 생성하며, 상기 병변정보 및 상기 진단정보에 따라 미리 설정된 알림신호를 출력하는 제어모듈; 및 상기 제어모듈로부터 출력되는 알림신호에 따라 임의의 화면 상에 시각적으로 디스플레이하는 알림모듈을 포함하되, 상기 제어모듈은, 딥러닝 모델이 적용된 이미지 프로세싱 프로그램을 통해 상기 내시경 영상에 대한 복수개의 프레임 이미지를 상기 신체 내부기관의 각 구역에 각각 매칭시키면서 분류하고, 상기 분류결과에 따라 탐색완료 구역과 미탐색 구역을 구분하는 탐색정보를 더 생성하며, 상기 생성된 탐색정보에 따라 미리 설정된 알림신호를 출력하는 것을 특징으로 하여, 병변의 악성정도 진단 정확도와 효율성을 향상시킬 수 있으며, 블라인드 스팟을 방지할 수 있는 효과가 있다.

6. 发明申请

WO2023075055A1 초음파 내시경 영상을 이용한 딥러닝 기반 췌장암의 혈관 침범 분류 방법 및 분석장치 审中-公开
公开(公告)号：WO2023075055A1
公开(公告)日：2023-05-04
申请号：PCT/KR2022/007654
申请日：2022-05-30
申请人： 이화여자대학교 산학협력단
发明人： 박수현 , 서강원 , 서정웅
IPC分类号： A61B8/08 , A61B8/00 , G16H30/40 , G16H50/20 , G06T7/11 , G06T7/00
摘要： 초음파 내시경 영상을 이용한 딥러닝 기반 췌장암의 혈관 침범 분류 방법은 분석장치가 대상자의 췌장 초음파 내시경 영상을 입력받는 단계, 상기 분석장치가 상기 췌장 초음파 내시경 영상을 제1 세그멘테이션 모델에 입력하여 췌장암 영역을 구분하는 단계, 상기 분석장치가 상기 췌장 초음파 내시경 영상을 분류 모델에 입력하여 췌장암의 혈관 침범 여부를 판단하는 단계 및 상기 분석장치가 상기 췌장 초음파 내시경 영상을 제2 세그멘테이션 모델에 입력하여 상기 췌장암 영역의 주변에 위치한 혈관 영역을 구분하는 단계를 포함한다.

7. 发明申请

WO2023070144A1 METHOD AND SYSTEM OF VISUALIZATION DURING ORTHOPAEDIC SURGERY 审中-公开
公开(公告)号：WO2023070144A1
公开(公告)日：2023-05-04
申请号：PCT/AU2021/051256
申请日：2021-10-28
申请人： AKUNAH MEDICAL TECHNOLOGY PTY LTD
发明人： GUPTA, Ashish , LAUNAY, Marine Mathilde Madeleine
IPC分类号： A61B34/10 , A61B90/00 , G06T15/08 , G06T19/00 , G16H30/40
摘要： A method of visualization during orthopaedic surgery. The method includes the step of a pre-operative planning step comprising displaying an initial three-dimensional image depicting anatomical features of a patient's bone. The image is retrieved by undertaking imaging or scanning of the patient's bone. The image is processed using a processor operable to carry out one or more image processing steps to generate a modified three-dimensional image. A mixed reality visualization device receives the modified three-dimensional image. The method also includes the step of displaying the modified three-dimensional image, via the mixed reality visualization device, and overlaying the modified three-dimensional image on or adjacent the anatomical features of the patient's bone to provide a visual guide to a surgeon while conducting surgery.

8. 发明申请

WO2023065042A1 FAST RETINA TRACKING 审中-公开
公开(公告)号：WO2023065042A1
公开(公告)日：2023-04-27
申请号：PCT/CA2022/051556
申请日：2022-10-21
申请人： PULSEMEDICA CORP.
发明人： KATCHINSKIY, Nir , KUROTOBI, Tomoko
IPC分类号： A61B3/113 , A61F9/008 , G06T7/246 , G16H30/40
摘要： Tracking of a patient's retina, or eye movements, may be useful when treating the patient's eye. The tracking may be done using an imaging system and may use two tracking processes. A first tracking process may determine eye movement based on a comparison between full frames of images. The second tracking process determines eye movement based on partial frames, or strips, of the images. The first tracking process must wait until the full frame is received, while the second tracking process may be performed quicker as it only requires a portion of the image to be received.

9. 发明申请

WO2023060185A1 CONTENT DISTRIBUTION SYSTEM AND METHOD 审中-公开
公开(公告)号：WO2023060185A1
公开(公告)日：2023-04-13
申请号：PCT/US2022/077687
申请日：2022-10-06
申请人： SURGIYO LLC
发明人： PARK, Stanley Seung Kwan
IPC分类号： G16H80/00 , G11B27/036 , G11B27/06 , G16H30/40 , H04L67/1097 , H04N21/231 , H04N21/2743
摘要： A computer-implemented method, computer program product and computing system for enabling a user to select raw procedure content for processing; enabling the user to select one or more sub-portions of the raw procedure content for inclusion within processed procedure content; and processing the one or more sub-portions of the raw procedure content to generate the processed procedure content.

10. 发明申请

WO2023059746A1 ESTIMATING UNCERTAINTY IN PREDICTIONS GENERATED BY MACHINE LEARNING MODELS 审中-公开
公开(公告)号：WO2023059746A1
公开(公告)日：2023-04-13
申请号：PCT/US2022/045817
申请日：2022-10-05
申请人： NEUMORA THERAPEUTICS, INC.
发明人： BANERJEE, Tathagata , KOLLADA, Matthew Edward , TORFI, Amirsina , CROCKER, Peter
IPC分类号： G06N3/042 , G06N3/0455 , G06N3/084 , G06N3/088 , G06N3/0895 , G06N3/0985 , G16B40/20 , G16H30/40 , G16H50/30 , G16H50/70 , G06N3/0464 , G06N20/00 , G06N3/02 , G06N3/045 , G06N3/08 , G06T2207/10088 , G06T2207/10104 , G06T2207/20081 , G06T2207/20084 , G06T2207/30016 , G06T2207/30104 , G06T7/0016 , G06V10/7715 , G06V10/774 , G06V10/82 , G06V2201/03 , G16H40/20 , G16H50/20
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a clinical recommendation for medical treatment of a patient. In one aspect a method comprises: receiving multi-modal data characterizing a patient, wherein the multi-modal data comprises a respective feature representation for each of a plurality of modalities; processing the multi-modal data characterizing the patient using a machine learning model, in accordance with values of a set of machine learning model parameters, to generate a patient classification that classifies the patient as being included in a patient category from a set of patient categories; determining an uncertainty measure that characterizes an uncertainty of the patient classification generated by the machine learning model; and generating a clinical recommendation for medical treatment of the patient based on: (i) the patient classification, and (ii) the uncertainty measure that characterizes the uncertainty of the patient classification.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式