MEDICAL IMAGE ANALYSIS APPARATUS, METHOD AND MEDICAL IMAGING DEVICE

A medical image analysis apparatus according to an embodiment includes an area motion analysis section and an object motion analysis section. The area motion analysis section configured to carry out a motion analysis on an area including an adjacent tissue of an object in a dynamic image to obtain the motion vector of the adjacent tissue. The object motion analysis section configured to determine the motion vector of the object based on the motion vector of the adjacent tissue.

Moving object contour extraction apparatus, left ventricle image segmentation apparatus, moving object contour extraction method and left ventricle image segmentation method

According to one embodiment, a moving object contour extraction apparatus includes a contour acquisition unit and a contour correction unit. The contour acquisition unit is configured to acquire a contour of a moving object in each image slice. The contour correction unit is configured to correct the contours of the moving object in image slices of at least one image slice time series based on motion trend information of the moving object in each of a plurality of image slice time series.

MOVING OBJECT CONTOUR EXTRACTION APPARATUS, LEFT VENTRICLE IMAGE SEGMENTATION APPARATUS, MOVING OBJECT CONTOUR EXTRACTION METHOD AND LEFT VENTRICLE IMAGE SEGMENTATION METHOD

According to one embodiment, a moving object contour extraction apparatus includes a contour acquisition unit and a contour correction unit. The contour acquisition unit is configured to acquire a contour of a moving object in each image slice. The contour correction unit is configured to correct the contours of the moving object in image slices of at least one image slice time series based on motion trend information of the moving object in each of a plurality of image slice time series. 1. A moving object contour extraction apparatus for extracting from a three-dimensional image time series contours of a moving object which performs a deforming motion , the three-dimensional image time series comprising a plurality of three-dimensional images acquired at a plurality of time points , each of the three-dimensional images consisting of a plurality of parallel two-dimensional image slices , and the two-dimensional image slices located at the same location in the plurality of three-dimensional images forming an image slice time series , the apparatus comprising:a contour acquisition unit configured to acquire a contour of the moving object in each image slice; anda contour correction unit configured to correct the contours of the moving object in the image slices of at least one image slice time series based on motion trend information of the moving object in each of a plurality of the image slice time series.2. The apparatus according to claim 1 , wherein the contour correction unit comprises:a motion trend determination unit configured to determine motion trend information of the moving object in each image slice time series;a similarity calculation unit configured to calculate a similarity between the motion trend information of the moving object in each image slice time series and reference motion trend information of the moving object; anda correction execution unit configured to correct the contours of the moving object in the image slices of a certain image ...

Apparatus and method for tracking contour of moving object, and apparatus and method for analyzing myocardial motion

A moving object contour tracking apparatus includes a contour tracking section for performing, by taking an initial contour of the moving object in a predetermined image slice as a starting contour, contour tracking in a first time direction to acquire a first contour of the moving object and contour tracking in a second time direction to acquire a second contour of the moving object in each image slice; a contour comparison section for calculating, in the predetermined image slice, a similarity between the first contour and the initial contour and a similarity between the second contour and the initial contour; and a contour correction section for taking the contours in the image slices that are acquired in a contour tracking direction corresponding to the greater one of the two similarities as the contours of the moving object in the respective image slices.

Apparatus and method for tracking contour of moving object, and apparatus and method for analyzing myocardial motion

A moving object contour tracking apparatus includes a contour tracking section for performing, by taking an initial contour of the moving object in a predetermined image slice as a starting contour, contour tracking in a first time direction to acquire a first contour of the moving object and contour tracking in a second time direction to acquire a second contour of the moving object in each image slice; a contour comparison section for calculating, in the predetermined image slice, a similarity between the first contour and the initial contour and a similarity between the second contour and the initial contour; and a contour correction section for taking the contours in the image slices that are acquired in a contour tracking direction corresponding to the greater one of the two similarities as the contours of the moving object in the respective image slices.

APPARATUS AND METHOD FOR TRACKING CONTOUR OF MOVING OBJECT, AND APPARATUS AND METHOD FOR ANALYZING MYOCARDIAL MOTION

A moving object contour tracking apparatus includes a contour tracking section for performing, by taking an initial contour of the moving object in a predetermined image slice as a starting contour, contour tracking in a first time direction to acquire a first contour of the moving object and contour tracking in a second time direction to acquire a second contour of the moving object in each image slice; a contour comparison section for calculating, in the predetermined image slice, a similarity between the first contour and the initial contour and a similarity between the second contour and the initial contour; and a contour correction section for taking the contours in the image slices that are acquired in a contour tracking direction corresponding to the greater one of the two similarities as the contours of the moving object in the respective image slices. 1. A moving object contour tracking apparatus for tracking a contour of a periodically deforming object in an image slice time series , the image slice time series comprising a plurality of image slices acquired at a plurality of time points in a motion period of the moving object , the moving object contour tracking apparatus comprising:a contour tracking section configured toperform, by taking an initial contour of the moving object in a predetermined image slice of the image slice time series as a starting contour, contour tracking in the image slice time series in a first time direction to acquire a first contour of the moving object in each image slice of the image slice time series, andperform, by taking the initial contour as a starting contour, contour tracking in the image slice time series in a second time direction to acquire a second contour of the moving object in each image slice of the image slice time series;a contour comparison section configured to calculate a similarity between the first contour of the moving object in the predetermined image slice and the initial contour as a first ...

APPARATUS AND METHOD FOR TRACKING CONTOUR OF MOVING OBJECT, AND APPARATUS AND METHOD FOR ANALYZING MYOCARDIAL MOTION

A moving object contour tracking apparatus includes a contour tracking section for performing, by taking an initial contour of the moving object in a predetermined image slice as a starting contour, contour tracking in a first time direction to acquire a first contour of the moving object and contour tracking in a second time direction to acquire a second contour of the moving object in each image slice; a contour comparison section for calculating, in the predetermined image slice, a similarity between the first contour and the initial contour and a similarity between the second contour and the initial contour; and a contour correction section for taking the contours in the image slices that are acquired in a contour tracking direction corresponding to the greater one of the two similarities as the contours of the moving object in the respective image slices. 1. A myocardial motion analysis apparatus for analyzing a motion of a myocardium of a left ventricle in a medical image slice time series , the medical image slice time series comprising a plurality of image slices acquired with respect to a section of the left ventricle intersected with a long axis of the left ventricle at a plurality of time points in a cardiac cycle , the apparatus comprising:a contour acquisition section configured to acquire an endocardial contour and an epicardial contour of the left ventricle in each image slice;a point linking pair configuration section configured to configure contour points on the endocardial contour and the epicardial contour in a reference image slice of the image slice time series as a plurality of point linking pairs, each point linking pair comprising a contour point on the endocardial contour and a contour point on the epicardial contour, and the two contour points of each point linking pair being located on the same normal of a reference contour of a left ventricle wall in the reference image slice;a point linking pair tracking section configured to determine ...

Industrial device matching method and apparatus

An industrial device matching method and apparatus are used for acquiring a corresponding relationship between industrial devices in different industrial data sources to provide basis for industrial data analysis. The method, in an embodiment, includes collecting data of at least two industrial data sources; determining a first relationship between various industrial devices in each industrial data source, and determining a first relationship topology between the industrial devices in the industrial data source; and comparing the first relationship topologies corresponding to various industrial data sources, to determine a first corresponding relationship between industrial devices in industrial data sources, the first corresponding relationship enabling the first relationship topologies corresponding to at least two industrial data sources to be similar. A relationship between industrial devices in different industrial data sources is determined by comparing a relationship topology between devices according to the similarity of relationships between the devices in different industrial data sources.

Array substrate and display device

【課題】アレイ基板に表示される画面の輝度の均一性を確保する。【解決手段】発光素子を含むサブ画素（１１）と、表示領域（Ｂ１）に位置しかつ第１電極に電気的に接続される正電源線（１２）と、周辺領域（Ｂ２）に位置する正電源線（１２）、正電源バス（１３）と、３つの正電源アクセス端子（１４、１５、１６）と、周辺領域（Ｂ２）に位置する負電源線（１７）と、周辺領域（Ｂ２）に位置する負電源線（１７）及び第２電極にそれぞれ電気的に接続される補助電極（１８）と、負電源線（１７）に電気的に接続される３つの負電源アクセス端子（１９、２０、２１）と、周辺領域（Ｂ２）に位置しかつ負電源アクセス端子（２０）及び補助電極（１８）にそれぞれ電気的に接続される負電源補助線（２２）とを含む。【選択図】図４

アレイ基板及び表示装置

【解決手段】アレイ基板は、表示領域Ｂ１に位置し、かつ第１電極、発光層、及び第２電極を含む発光素子を含むサブ画素１１と、表示領域に位置しかつ第１電極に電気的に接続される正電源線１２と、周辺領域Ｂ２に位置しかつ正電源線に電気的に接続される正電源バス１３と、正電源バスの表示領域から離れた側に位置しかつそれぞれが正電源バスに電気的に接続される３つの正電源アクセス端子１４、１５、１６と、周辺領域に位置する負電源線１７と、周辺領域に位置しかつ負電源線及び第２電極にそれぞれ電気的に接続される補助電極１８と、正電源バスの表示領域から離れた側に位置しかつそれぞれが負電源線に電気的に接続される３つの負電源アクセス端子１９、２０、２１と、周辺領域に位置しかつ負電源アクセス端子２０及び補助電極にそれぞれ電気的に接続される負電源補助線２２とを含む。【効果】表示される画面の輝度の均一性を確保するのに有利である。【選択図】図４

Anomaly Detection Method and Apparatus for Dynamic Control System, and Computer-Readable Medium

Various embodiments of the teachings herein include anomaly detection methods for a dynamic control system. An example method includes: using a g network to initialize a hidden state distribution of the system; receiving a measurement value of a sensor and a state value of a trigger at a current point of time; receiving a sampling point into an f network to perform a prediction to obtain a second sampling point; using an h network to map the second sampling point into a sensor measurement value space to perform a prediction to obtain a probability distribution of a measurement value of the sensor in the dynamic control system at the current point of time; and determining whether an anomaly exists in the dynamic control system by comparing the measurement value obtained from real-time monitoring and the probability distribution obtained from a prediction.

輸出級驅動電路

Industrial device matching method and apparatus

An industrial device matching method and apparatus used for simply acquiring a corresponding relationship between industrial devices in different industrial data sources to provide basis for industrial data analysis is disclosed. The method includes: collecting data of at least two industrial data sources (S101); determining a first relationship between various industrial devices in each industrial data source (S102); and determining a first relationship topology between the industrial devices in the industrial data source (S103); and comparing the first relationship topologies corresponding to various industrial data sources, so as to determine a first corresponding relationship between industrial devices in industrial data sources (S104); checking the corresponding relationship (S105); determining a final corresponding relationship (S105).

Defect detection method and defect detection system based on machine vision

A defect detection system based on machine vision includes a monitoring module, a detection module, an early warning module, and a screening module. A method and the system are implemented by timely screening out an empty bottle having a different specification in detection, monitoring whether a content in each of empty bottles meets requirement, monitoring whether foreign matter is contained in each of filled bottles, and displaying a monitored image on a display device. Bottles that are normal in the detection are filled, filled bottles are monitored through the monitoring module. The monitoring module is configured to monitor whether the content in the filled bottles meets requirement, whether foreign matter is contained in the filled bottles.

Method and Apparatus for Product Quality Inspection

Various embodiments include a method for product quality inspection on a group of products. The method may include: getting for each product in the group of products: image, value for each known fabrication parameter affecting quality of the group of products, and quality evaluation result; training a neural network. A layer of the neural network comprises at least one first neuron and at least one second neuron; each first neuron represents a known fabrication parameter affecting quality of the group of products and each second neuron represents an unknown fabrication parameter affecting quality of the group of products; and the images of the group of products are input to the neural network, the quality evaluation results are output of the neural network, and the value of each first neuron is set to the value for the known fabrication parameter the first neuron representing.

Method and Apparatus for Training a Model

Various embodiments of the teachings herein include a method for training a model configured to monitor a working status of equipment based on sensor data. An example method includes: training a model using a training data set including historical sensor data gathered only when the equipment is under normal working conditions; testing the model with sensor data causing a false alarm, sensor data of the equipment's historical confirmed failure, and sensor data within pre-defined recent time period when the equipment is under normal working conditions; and activating the model if the model passes test, otherwise rejecting the model.

Anomaly detection method and apparatus for dynamic control system, and computer-readable medium

Various embodiments of the teachings herein include anomaly detection methods for a dynamic control system. An example method includes: using a g network to initialize a hidden state distribution of the system; receiving a measurement value of a sensor and a state value of a trigger at a current point of time; receiving a sampling point into an f network to perform a prediction to obtain a second sampling point; using an h network to map the second sampling point into a sensor measurement value space to perform a prediction to obtain a probability distribution of a measurement value of the sensor in the dynamic control system at the current point of time; and determining whether an anomaly exists in the dynamic control system by comparing the measurement value obtained from real-time monitoring and the probability distribution obtained from a prediction.