公开(公告)号：US11961226B2

公开(公告)日：2024-04-16

申请号：US17078266

申请日：2020-10-23

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Kaiwen Xiao ,  Zhongqian Sun ,  Chen Cheng ,  Wei Yang

IPC: G06T7/00 ,  G06F16/583 ,  G06F18/214 ,  G06V10/32 ,  G06V10/75 ,  G06V10/774 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G16H70/20 ,  A61B5/055 ,  A61B6/00 ,  A61B8/08 ,  G06F17/11

CPC classification number: G06T7/0012 ,  G06F16/5854 ,  G06F18/214 ,  G06V10/32 ,  G06V10/751 ,  G06V10/774 ,  G16H30/20 ,  G16H30/40 ,  G16H50/20 ,  G16H50/70 ,  G16H70/20 ,  A61B5/055 ,  A61B6/5217 ,  A61B8/5223 ,  G06F17/11 ,  G06V2201/03

Abstract: In a medical image recognition method, applied to a computer device, a to-be-recognized medical image set is obtained, where the to-be-recognized medical image set includes at least one to-be-recognized medical image. A to-be-recognized area corresponding to each to-be-recognized medical image in the to-be-recognized medical image set is extracted. The to-be-recognized area is a part of the to-be-recognized medical image. A recognition result of each to-be-recognized area through a medical image recognition model is determined. The medical image recognition model is obtained through training according to a medical image sample set. The medical image sample set includes at least one medical image sample, and each medical image sample carries corresponding annotation information. The annotation information is used for representing a type of the medical image sample, and the recognition result is used for representing the a of the to-be-recognized medical image.

公开(公告)号：US11957299B2

公开(公告)日：2024-04-16

申请号：US17080847

申请日：2020-10-27

Applicant: FUJIFILM Corporation

Inventor： Toshihiro Usuda

IPC: G06F3/0482 ,  A61B1/00 ,  G06F18/23 ,  G06T7/00 ,  G06V20/69

CPC classification number: A61B1/000094 ,  A61B1/00006 ,  A61B1/0005 ,  G06F3/0482 ,  G06F18/23 ,  G06T7/0014 ,  G06V20/69 ,  G06T2200/24 ,  G06T2207/10068 ,  G06T2207/30096 ,  G06V2201/03

Abstract: An endoscope image processing apparatus includes: an image acquisition unit that acquires endoscopic images; a detection unit that detects lesion images representing lesions in the endoscopic images acquired by the image acquisition unit; a clustering unit that groups the endoscopic images on the basis of a degree of correlation between the lesion images and generates, for each lesion, a group formed of corresponding ones of the endoscopic images; a representative image selection unit that selects, for each group, a representative image from among the endoscopic images in the group; a saving unit that saves, for each group, the representative image and the endoscopic images that form the group to which the representative image belongs, in association with each other; and a display unit that displays a list of the representative images saved in the saving unit.

公开(公告)号：US20240112776A1

公开(公告)日：2024-04-04

申请号：US18539627

申请日：2023-12-14

Applicant: Sirona Medical, Inc.

Inventor： David Seungwon PAIK ,  Vernon MARSHALL ,  Mark D. LONGO ,  Cameron ANDREWS ,  Kojo Worai OSEI ,  Berk NORMAN ,  Ankit GOYAL

IPC: G16H15/00 ,  G06F3/01 ,  G06F3/16 ,  G06F18/214 ,  G06F18/22 ,  G06F18/40 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11 ,  G06V10/94 ,  G10L15/22

CPC classification number: G16H15/00 ,  G06F3/013 ,  G06F3/167 ,  G06F18/2148 ,  G06F18/22 ,  G06F18/41 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11 ,  G06V10/95 ,  G10L15/22 ,  G06T2200/24 ,  G06T2207/30041 ,  G06V2201/03

Abstract: Disclosed herein are systems, methods, and software for providing a platform for complex image data analysis using artificial intelligence and/or machine learning algorithms. One or more subsystems allow for the capturing of user input such as eye gaze and dictation for automated generation of findings. Additional features include quality metric tracking and feedback, and worklist management system and communications queueing.

公开(公告)号：US20240104736A1

公开(公告)日：2024-03-28

申请号：US18528923

申请日：2023-12-05

Applicant: LUNIT INC.

Inventor： Donggeun YOO

IPC: G06T7/00 ,  G06V10/22 ,  G06V10/774 ,  G16H30/40 ,  G16H70/60

CPC classification number: G06T7/0012 ,  G06V10/22 ,  G06V10/774 ,  G16H30/40 ,  G16H70/60 ,  G06T2207/20081 ,  G06T2207/30004 ,  G06V2201/03

Abstract: There is provided a method for parallel processing a digitally scanned pathology image, in which the method is performed by a plurality of processors and includes performing, by a first processor, a first operation of providing a second processor with a first patch included in the digitally scanned pathology image, performing, by the first processor, a second operation of providing the second processor with a second patch included in the digitally scanned pathology image, and performing, by the second processor, a third operation of outputting a first analysis result from the first patch using a machine learning model, in which at least a part of a time frame for the second operation performed by the first processor may overlap with at least a part of a time frame for the third operation performed by the second processor.

公开(公告)号：US11941812B2

公开(公告)日：2024-03-26

申请号：US17953505

申请日：2022-09-27

Applicant: CANON MEDICAL SYSTEMS CORPORATION

Inventor： Kota Aoyagi ,  Yasuko Fujisawa

IPC: G06T7/00 ,  G06F18/21 ,  G06T11/00 ,  G06V10/40 ,  G06V10/772

CPC classification number: G06T7/0014 ,  G06F18/217 ,  G06T11/003 ,  G06V10/40 ,  G06V10/772 ,  G06T2207/10081 ,  G06T2207/10116 ,  G06T2207/20081 ,  G06T2210/41 ,  G06V2201/03

Abstract: In one embodiment, a diagnosis support apparatus includes: an input circuit configured to acquire a first medical image; and processing circuitry configured to generate a second medical image from the first medical image in such a manner that information included in the second medical image is reduced from information included in the first medical image, extract auxiliary information from the first medical image, and perform inference of a disease by using the second medical image and the auxiliary information.

公开(公告)号：US11937986B2

公开(公告)日：2024-03-26

申请号：US17241978

申请日：2021-04-27

Applicant: Carl Zeiss Meditec AG

Inventor： Stefan Saur

IPC: G06T7/00 ,  A61B90/20 ,  G06F18/24 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778 ,  G16H20/40 ,  G16H30/20 ,  G16H30/40

CPC classification number: A61B90/20 ,  G06F18/24 ,  G06T7/0014 ,  G06V10/764 ,  G06V10/774 ,  G06V10/7784 ,  G16H20/40 ,  G16H30/20 ,  G16H30/40 ,  G06T2207/10056 ,  G06T2207/30004 ,  G06T2207/30168 ,  G06V2201/03

Abstract: A method for acquiring annotated data with the aid of surgical microscopy systems comprises obtaining desired criteria which are intended to be satisfied by desired data to be annotated, and storing the set of desired criteria in a plurality of surgical microscopy systems. In each surgical microscopy system, images are then recorded and current criteria which correspond to the recorded images are determined. The current criteria are compared with the desired criteria. If the desired criteria sufficiently correspond to the current criteria, a confirmation is requested from a user as to whether said user would like to annotate data. If the user provides the confirmation, annotations for images are received from the user and stored together with the images.

公开(公告)号：US20240095919A1

公开(公告)日：2024-03-21

申请号：US18522938

申请日：2023-11-29

Applicant: OLYMPUS CORPORATION

Inventor： Masato NARUSE

IPC: G06T7/00 ,  A61B5/02 ,  G06T7/70 ,  G06V20/50

CPC classification number: G06T7/0012 ,  A61B5/02042 ,  G06T7/70 ,  G06V20/50 ,  G06T2207/10068 ,  G06T2207/20081 ,  G06T2207/30101 ,  G06V2201/03

Abstract: An image processing device includes a processor. The processor is configured to: recognize blood vessel running information; recognize a first bleeding position from a surgery image; identify a second bleeding position in the blood vessel running information corresponding to the first bleeding position in the surgery image; and identify a bleeding stopping point corresponding to the second bleeding position as a bleeding stopping recommended point corresponding to the first bleeding position. The processor: acquires information about the bleeding stopping recommended point corresponding to each of one or more blood vessel areas in the blood vessel running information; identifies the blood vessel area among the one or more blood vessel areas, to which the second bleeding position belongs; and performs processing in which the bleeding stopping recommended point corresponding to the blood vessel area thus identified is superimposed on the surgery image and displayed on a display.

公开(公告)号：US11935279B1

公开(公告)日：2024-03-19

申请号：US18505639

申请日：2023-11-09

Applicant: GUILIN UNIVERSITY OF ELECTRONIC TECHNOLOGY

Inventor： Xipeng Pan ,  Huahu Deng ,  Rushi Lan ,  Zhenbing Liu ,  Lingqiao Li ,  Huadeng Wang ,  Xinjun Bian ,  Yajun An ,  Feihu Hou

IPC: G06V10/778 ,  G06T7/11 ,  G06T7/136 ,  G06T7/194 ,  G06V10/764 ,  G06V10/776 ,  G06V10/86 ,  G06V20/50 ,  G06V20/70 ,  G16H30/40 ,  G16H70/60

CPC classification number: G06V10/778 ,  G06T7/11 ,  G06T7/136 ,  G06T7/194 ,  G06V10/764 ,  G06V10/776 ,  G06V10/86 ,  G06V20/50 ,  G06V20/70 ,  G16H30/40 ,  G16H70/60 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30024 ,  G06T2207/30061 ,  G06T2207/30068 ,  G06T2207/30096 ,  G06V2201/03

Abstract: Provided is a weakly supervised pathological image tissue segmentation method based on an online noise suppression strategy, including: acquiring a hematoxylin-eosin (H&E) stained graph, processing the H&E stained graph to obtain a data set, dividing the data set, training a classification network based on a divided data set, and generating a pseudo-label; suppressing a noise existing in the pseudo-label based on the online noise suppression strategy, and training a semantic segmentation network through the pseudo-label after noise suppression and a training set corresponding to the pseudo-label to obtain a prediction result of the semantic segmentation network after the training, and taking the prediction result as a final segmentation result.

公开(公告)号：US11935235B2

公开(公告)日：2024-03-19

申请号：US17901582

申请日：2022-09-01

Applicant: UNIVERSITY OF IOWA RESEARCH FOUNDATION

Inventor： Michael Abramoff ,  Gwenole Quellec

IPC: G06T7/00 ,  G06F18/00 ,  G06T7/73 ,  G06V40/18

CPC classification number: G06T7/0012 ,  G06F18/00 ,  G06T7/75 ,  G06V40/193 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/30041 ,  G06T2207/30096 ,  G06V2201/03

Abstract: A method of identifying an object of interest can comprise obtaining first samples of an intensity distribution of one or more object of interest, obtaining second samples of an intensity distribution of confounder objects, transforming the first and second samples into an appropriate first space, performing dimension reduction on the transformed first and second samples, whereby the dimension reduction of the transformed first and second samples generates an object detector, transforming one or more of the digital images into the first space, performing dimension reduction on the transformed digital images, whereby the dimension reduction of the transformed digital images generates one or more reduced images, classifying one or more pixels of the one or more reduced images based on a comparison with the object detector, and identifying one or more objects of interest from the classified pixels.

公开(公告)号：US11931166B2

公开(公告)日：2024-03-19

申请号：US16922598

申请日：2020-07-07

Applicant: Applied Research Associates, Inc.

Inventor： Christopher Argenta ,  Aaron Williams ,  Greg Foderaro ,  Thomas Paniagua

IPC: A61B5/00 ,  G06T7/00 ,  G06T11/20 ,  G06T19/20 ,  G06V10/143 ,  G06V10/42 ,  G06V10/44 ,  G06V20/20 ,  G16H50/20

CPC classification number: A61B5/445 ,  A61B5/0013 ,  A61B5/0075 ,  A61B5/0077 ,  A61B5/6898 ,  A61B5/7264 ,  A61B5/7282 ,  A61B5/743 ,  A61B5/744 ,  G06T7/0014 ,  G06T11/206 ,  G06T19/20 ,  G06V10/143 ,  G06V10/42 ,  G06V10/44 ,  G06V20/20 ,  G16H50/20 ,  A61B2576/02 ,  G06T2219/2016 ,  G06V2201/03

Abstract: A system and method of generating an enhanced Lund and Browder chart and total body surface area burn score is described herein. In some embodiments, a plurality of images is obtained from of a patient using a camera system. The images may be taken by aligning the patient's body with pose templates presented on a display of the camera system. The non-skin portions of the images may be removed, and skin analysis performed on the skin portion to determine burn location, coverage, and depth. Further, landmarks may be detected in the images to morph and align the images with the pose templates to obtain standard poses. The plurality of images may be combined and presented in two-dimensional and three-dimensional models with labels and the total surface area burn score.