公开(公告)号：US20190029625A1

公开(公告)日：2019-01-31

申请号：US15563547

申请日：2016-03-30

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH ,  SINGAPORE HEALTH SERVICES PTE LTD

Inventor： Liang ZHONG ,  Ru San TAN ,  Weimin HUANG ,  Jiayin ZHOU ,  Yuping DUAN ,  Wei XIONG ,  Yanling CHI ,  Kyaw Kyar TOE

IPC: A61B6/00 ,  A61B6/03 ,  A61B5/055 ,  A61B8/12 ,  G06T7/00

CPC classification number: A61B6/5217 ,  A61B5/02007 ,  A61B5/055 ,  A61B5/1075 ,  A61B5/1076 ,  A61B5/489 ,  A61B6/032 ,  A61B6/504 ,  A61B6/507 ,  A61B8/12 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/62 ,  G06T2207/10081 ,  G06T2207/20168 ,  G06T2207/30104 ,  G06T2207/30172

Abstract: A method for assessing blood vessel stenosis using image data of a subject is disclosed. The image data represents a vascular structure of the subject. The method comprises: (a) segmenting, from the image data, a vessel segment representing a segment of a blood vessel, (b) obtaining, using the image data, a plurality of two-dimensional images of the vessel segment; said plurality of two-dimensional images representing respective cross-sections of the vessel segment, (c) identifying, for each of the plurality of two-dimensional images, a lumen area comprising lumen pixels representing a lumen of the corresponding cross-section, (d) obtaining a quantitative measure using the lumen areas of successive cross-sections of the vessel segment, and (e) assessing blood vessel stenosis using the quantitative measure. A computer system for performing the above method is disclosed.

公开(公告)号：US20230014823A1

公开(公告)日：2023-01-19

申请号：US17782015

申请日：2020-12-08

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH

Inventor： Jierong CHENG ,  Ying SUN ,  Wei XIONG ,  Wenyu CHEN ,  Yusha LI ,  Ying QUAN

IPC: G06T7/00 ,  G06T7/149 ,  G06T7/11 ,  G06T5/20 ,  G06T5/00

Abstract: This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

公开(公告)号：US20220189044A1

公开(公告)日：2022-06-16

申请号：US17598800

申请日：2020-03-27

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH

Inventor： Wei XIONG ,  Wenyu CHEN ,  Jierong CHENG ,  Jia DU

IPC: G06T7/277 ,  G06K9/62

Abstract: This disclosure relates to method and system for visual inspection of rotating components. The method includes representing rotation cycles of a rotating component as spatial features based on video or image frames, ascertaining and/or evolving Hidden Markov Model (HMM) chains for the cycles, ascertaining a count of the rotating component in the frames and/or labelling the frames with ascertained states of the HMM chains.

公开(公告)号：US20190120770A1

公开(公告)日：2019-04-25

申请号：US16090170

申请日：2017-03-30

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH

Inventor： Wenyu CHEN ,  Wei XIONG ,  Jia DU ,  Jierong CHENG ,  Teck Sun Marcus WAN

IPC: G01N21/88 ,  G01B11/30 ,  G06T7/00 ,  G06K9/32 ,  G06T7/40

Abstract: A system and a method for imaging a surface defect on an object are provided. The system includes an actuator, a sensor assembly connected to the actuator, and a processor configured to control the actuator and the sensor assembly. The sensor assembly includes at least one sensor configured to capture at least one image of the object. The processor is configured to control the actuator and the sensor assembly to identify the actuator and the sensor assembly, a region of a region of interest associated with the surface defect using an using an image of the object and to repeatedly identify at least one subsequent region of interest associated with the surface defect using at least a preceding region of interest such that the surface defect is identified according to a predetermined criterion.

公开(公告)号：US20160143697A1

公开(公告)日：2016-05-26

申请号：US14898059

申请日：2014-06-11

Applicant: AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH ,  NATIONAL UNIVERSITY HOSPITAL (SINGAPORE) PTE LTD

Inventor： Wenyu CHEN ,  Sudhakar K. VENKATESH ,  Qi TIAN ,  Jianyin ZHOU ,  Weimin HUANG ,  Wei XIONG ,  Oo THIHA

IPC: A61B34/10 ,  G06F17/13 ,  G06F17/17 ,  A61B6/03 ,  G06F19/00

CPC classification number: A61B34/10 ,  A61B6/032 ,  A61B6/5217 ,  A61B2034/101 ,  A61B2034/105 ,  A61B2034/107 ,  G06F17/13 ,  G06F17/17 ,  G06T19/00 ,  G06T2210/41 ,  G06T2219/008 ,  G16H50/50

Abstract: A method for surgical resection planning of a mass is disclosed, the method comprises the steps of modelling the mass based on a plurality of physical dimensions, determining a plurality of safety margins around a plurality of features within the mass, simulating a resection surface on the mass comprising a plurality of triangles, optimizing local area and position of a first of the plurality of triangles on the resection surface based on a triangle-based algorithm, updating the simulation of the resection surface, and repeating the steps of optimizing and updating for each of the plurality of triangles on the resection surface.

Abstract translation: 公开了一种用于大规模的手术切除规划的方法，所述方法包括以下步骤：基于多个物理尺寸对质量进行建模，确定围绕质量块内的多个特征周围的多个安全边缘，模拟所述块体中的切除面 质量包括多个三角形，基于基于三角形的算法来优化切割表面上的多个三角形中的第一个三角形的局部区域和位置，更新切割表面的模拟，并且重复每一个的优化和更新步骤 的切除面上的多个三角形。