70 results about "Organ region" patented technology

A method, system and device for measurement of a blood constituent level, including a light source, a light detector proximate an organ surface, adjustable gain amplifiers, and a processor / controller connected within a processing unit operative to separate AC and DC signal components. The device may determine the level of blood constituent, may use this level for monitoring and / or to activate an alarm when the level falls outside a predetermined range, may be applied to monitoring conditions of apnea, respiratory stress, and reduced blood flow in organ regions, heart rate, jaundice, and blood flow velocity, and may be incorporated within a monitoring system.

An ultrasound imaging diagnosis apparatus and a method for supporting safe and exact puncturing operation into a target region in a living body of a patient are provided. In the ultrasound imaging diagnosis apparatus, a regions setting unit sets a target tumor region for puncturing and blood vessel regions and organ region that are located near the tumor region based on the volume data acquired by 3-D scans on the object. To avoid insertions into the blood vessel regions and organ region, a puncturing needle position detecting unit detects the tip position and the inserting direction of the puncturing needle at just before and during insertion into the object. An expected inserting position calculating unit calculates an expected inserting position and an insertion error region to the tumor region based on the tip position data, inserting direction data and characteristic data of the puncturing needle. A puncturing navigation data generating unit generates a puncturing navigation data by composing the tumor region data, the organ region and blood vessel regions data, and the data relating to the expected inserting position and the insertion error region.

A system for segmenting a target organ tumor from an image includes a background model builder, a foreground model builder and a tumor region locator. The background model builder uses an intensity distribution estimate of voxels in an organ region in an image to build a background model. The foreground model builder uses an intensity distribution estimate of voxels in a target organ tumor to build a first foreground model. The tumor region locator uses the background model and the first foreground model to segment the target organ tumor to obtain a first segmentation result.

In an organ-region-indication system incorporated in an electronic endoscope system in which an endoscope image is displayed as a motion image on a monitor in accordance with a video signal produced therein, an organ-region-image data base is formed based on an organ map. A plurality of reference data indicating organ-regions and a plurality of image data representing the organ-region are correspondingly stored in the data base. Still image data is retrieved as referential image data from the video signal at suitable regular time intervals. The data base is searched for image data which coincides with the referential image data after the retrieval of the still image data. Corresponding reference data is displayed on the monitor only when the image data, which coincides with the referential image data, is found by the searching.

In a method, a device and a computer program for determining the blood flow in a tissue or organ region, the fluorescence intensity of an exogenous chromophore is measured as a function of time in the tissue region to be examined and from this the permeation rate of the chromophore is calculated, from which the blood flow can be derived.

A medical image diagnosis support device comprises an organ region setting means, a deformation degree calculating means for calculating the deformation degree of the organ region set by the organ region setting means, a reference value storing means, a lesion detecting means for comparing the stored reference value with the deformation degree calculated by the deformation calculating means and for detecting existence of a lesion of the organ region from the comparison result, and a presenting means for presenting the existence to the examiner at least either visually or auditorily. Thus, the device can make a diagnosis selectively only on an organ region deformed because of a lesion and present it to the examiner visually such as by means of an image display or auditorily such as by means of speech, thereby improving the efficiency of diagnosis.

A medical image diagnosis support device comprises an organ region setting means for setting an organ region on the medical image of the subject obtained by a medical imaging device, a deformation degree calculating means for calculating the deformation degree of the organ region set by the organ region setting means, a reference value storing means for storing the index of the deformation degree of the organ region as a reference value, a lesion detecting means for comparing the stored reference value with the deformation degree calculated by the deformation calculating means and for detecting existence of a lesion of the organ region from the comparison result, and a presenting means for presenting the existence to the examiner at least either visually or auditorily. Therefore, the device can make a diagnosis selectively only on an organ region deformed because of a lesion and present it to the examiner visually such as by means of an image display or auditorily such as by means of speech, thereby improving the efficiency of diagnosis.

The application provides a method and system for smart community face recognition. The method of the application includes: acquiring a face image of a target human body; performing edge detection on the face image, and dividing the face image into a plurality of regions according to a closed edge; performing texture extraction on a key region in the plurality of regions to generate a texture feature vector of the key region, wherein the key region being a face organ region determined according to a clustering rule; and comparing and recognizing the key region based on the texture feature vector, and then determining the identity information of the target human body. The method and system of the invention are a few in collected facial features, small in amount of calculation, simple in algorithm, and high recognition speed, thereby improving the speed of face recognition, adapting to actual conditions such as distributed low-configuration hardware resources, mass recognition objects andhigh-frequency triggering in a smart community scenario, and realizing face recognition in an efficient, reliable, fast and low-cost manner.

In accordance with at least some embodiments of the present disclosure, a process for calculating patient-specific organ dose is presented. The process may include constructing a computed tomography (CT) volume based on CT images generated by a CT scanner. The process may include segmenting the CT volume into a plurality of organ regions, generating a material density map for the CT volume based on Hounsfield Unit (HU) values, and generating a dose distribution map for the CT volume based on the material density map by simulating particles emitting from the CT scanner and flowing through the CT volume. The process may further generate a dose value delivered to a specific organ region of the plurality of organ regions based on the dose distribution map.

The invention provides an Asian human face age characteristic model generating method, and the method comprises the steps: S1), extracting a wrinkle difference characteristic pattern of each human face image in a training set, and obtaining an original feature vector of each human face image; S2), determining the number of reduced dimensions of each original feature vector, reducing the dimensions of the original feature vector of each original image based on a PCA method, and obtaining feature vectors after dimension reduction; S3), carrying out the training of the feature vectors based on a support vector machine regression algorithm after dimension reduction, and generating an age characteristic model. In addition, the invention also provides the age characteristic model generated through the above method, and an Asian human face age estimation method. The age characteristic model carries out the extraction of the features based on a human face important organ region and a human face wrinkle region, and guarantees that the features comprise the sufficient information sensitive to the age estimation. The age estimation method can obtain a more precise age estimation value, and meets the demands of an actual application scene.

The invention relates to an image feature acquisition method of a prostate MRI three-dimensional image. The method comprises: the prostate T2WI image being subjected to automatic organ segmentation; and mapping the prostate organ region to the registered ADC and DWI image based on a segmentation result to obtain a multi-parameter prostate organ region serving as input of a discrimination model, and obtaining image characteristics by combining the multi-parameter MRI image and a deep learning algorithm. The method is based on a large amount of prostate image data, the prostate organ automatic segmentation model is established, the interference of irrelevant background information on the discrimination model is reduced, the characteristics of the multi-parameter MRI image are fused by usinga deep learning method, high-precision prostate cancer characteristic extraction is realized, and a basis is provided for improving the prostate cancer diagnosis efficiency and accuracy.

The invention discloses a CT image endangered organ segmentation system based on deep learning. The CT image endangered organ segmentation system comprises a data acquisition module, a region-of-interest sketching module, an endangered organ segmentation model training module, a model test module and a segmented image generation module. A pyramid-type deep learning network integrating global information flow and an SCP module located on jump connection and used for extracting and fusing multi-scale information are provided, the weight for segmenting useful features is increased through utilization of the multi-scale global information flow and an attention mechanism, the nonlinearity of the structure is enhanced, the performance of a segmentation model is remarkably improved, and the segmentation efficiency is improved. Meanwhile, a cascade network structure based on an automatic context method is designed, after the positioning result of the organ region to be segmented is combined with the original CT image input by using the automatic context method, refined segmentation is carried out, and the segmentation accuracy of the whole system is remarkably improved.

The invention discloses an artificial vision intelligent traditional Chinese medicine face diagnosis five-internal-organ state diagnosis method and device. The method comprises: acquiring a face imagefrom a face video image through HAAR features and an ADABOOST algorithm; extracting68 key points of each frame of face image by using a DLIB library, and adopting an HOUGH transformation algorithm and a Delaunay triangulation criterion to locate and segment five internal organ regions of eyes, five internal organ regions of face miraculous pivot color and five internal organ regions of face plainquestion stabbing heat; extracting five-color five-organ features of each face image and five-organ regions thereof, and converting the five-color five-organ features into a five-organ body surface feature set; and sending the five-internal-organ body surface feature set into a preset SVM multi-classifier to identify five-internal-organ state information, thereby providing a digital objective basis for traditional Chinese medicine diagnosis. By the adoption of the diagnosis method and device, the state information of the five internal organs of the user can be recognized, and high accuracy and analysis efficiency are achieved.

The invention requests to protect an ultrasonic image diagnosis report generation method based on target detection and strategy gradient, which comprises the following steps: firstly, inputting an image into a target detection model, predicting position information of an organ region, and extracting a feature code of an organ region part according to the predicted position information; inputting the extracted feature codes into a language generation model, decoding the feature codes at different moments and generating words, and finally forming a sentence sequence by the generated words to obtain a final output diagnosis report, wherein the constructed loss function comprises the regional position of the target detection model and the error of the disease information, and the language generation model uses a return function to calculate the negative expected value of the generated diagnosis report and the corresponding label diagnosis report, and the training purpose is to minimize thereturn negative expectation. According to the invention, the diagnosis report corresponding to the ultrasonic image can be generated, and pathological information of the diagnosis report is kept accurate and grammars are natural.

To provide an ultrasonic diagnostic apparatus capable of producing a three-dimensional image of an object for an organ region within a range of elasticity values desired by an operator and allowing the operator to recognize the region easily, elasticity value data included in a desired elasticity value range among elasticity value data constituting a volume data are selected and rendered. Whereby, a three-dimensional elasticity image in the set elasticity value range is produced. An area corresponding to the elasticity value range is displayed on at least one of a two-dimensional elasticity image and a section image.

A medical image diagnosis device is provided with a medical image acquiring unit for acquiring a medical image, a three-dimensional image constructing unit for constructing a three-dimensional image including a moving organ region in the medical image, a tomogram creating unit for creating a two-dimensional tomogram to serve as a reference image from the three-dimensional image, a region dividing unit for dividing the reference image into a plurality of regions according to the criteria for region division, and a region-of-interest setting unit for computing the moving states of the regions, specifying at least one region from among the regions according to the computed moving states, and setting a region in the medical image including the specified region as a region of interest.

The invention discloses a living body detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining an image frame in a video in real time when itis determined that a living body detection starting condition is met; Identifying at least one organ area of a user in the image frame, wherein one organ area corresponds to at least one characteristic value set; If it is determined that each organ region identified in the target image frame meets an unshielded condition, respectively calculating feature values which are identified in the targetimage frame and are matched with each organ region, and updating and storing the feature values into a corresponding feature value set; And detecting at least one target action condition of the characteristic value set in real time, and determining whether the user is a living body or not according to a detection result of each target action condition when determining that a living body detectionending condition is met. According to the embodiment of the invention, the living body can be accurately identified, and the safety of identity authentication is improved.

The invention relates to an image processing method and device, electronic equipment and a storage medium, wherein the method comprises the steps: carrying out the segmentation processing of a to-be-processed image, and determining an organ region corresponding to a target organ in the to-be-processed image, and a focus region corresponding to a focus on the target organ; according to the positions of the organ region and the focus region, determining an abnormal sub-region corresponding to the part bearing the focus organ from the organ region; determining a lesion interface between the abnormal sub-region and the lesion region according to a position relationship between a first pixel point in the abnormal sub-region and a second pixel point in the lesion region; and according to the focus interface and the focus area, determining a morphological analysis result of the focus. According to the embodiment of the invention, the morphological analysis result of the focus in the image can be automatically and accurately determined, so that the workload of medical staff is reduced, and the working efficiency of the medical staff is improved.

The invention provides a scenic spot intelligent photographing system based on facial expression classification. The scenic spot intelligent photographing system comprises a face information collection module which is used for collecting a face video and carrying out the recognition of an important organ region of a face, a face information analysis module which is used for determining facial feature points according to the important organ regions of the human face and generating facial expression feature vectors according to the variation of the positions of the facial feature points, an expression type determining module which is used for judging whether the facial expression feature vectors belong to facial expression types corresponding to the trained SVM classification vector machinesor not and determining the facial expression type of the current facial expression of the tourist, and a face image shooting module which is used for automatically shooting facial expressions of tourists whose determined facial expression types are matched with scenic spot features. The invention provides an intelligent photographing method of the system. When the facial expression type of the tourist is matched with the scenic spot characteristics, the scenic spot intelligent photographing system shoots a facial image of a tourist, increases attraction of the scenic spot, and increases the printing amount of scenic spot photos.

The invention discloses a medical record image modeling system based on a medical image. The system includes a central platform and a plurality of hospital systems connected with the central platform; the central platform includes a modeling and division module and a knowledge base, the central platform obtains thin-layer scan images, sent from the hospital systems, of organs to be modeled and divided, the modeling and division module conducts modeling and organ region division on the thin-layer scan images of the organs, and organ models obtained after modeling and division are stored in the form of disease cases in the knowledge base and then issued to the corresponding hospital systems. The hospital systems upload the thin-layer scan images to the central platform, the central platform conducts modeling and division on the images and stores the images, and therefore the medical record image modeling system is convenient for different hospitals or different doctors to obtain data.

An embodiment of the invention discloses a method and a device for identifying organ blood vessels. The method includes respectively judging whether or not each pixel point in each section image is positioned in a target organ region, wherein each section image is divided into the target organ region and a non-target organ region; calculating blood vessel metrics corresponding to the pixel points positioned in the target organ regions; identifying the organ blood vessels according to the acquired blood vessel metrics. Whether or not the pixel points in the section images are positioned in the target organ regions is respectively judged, each section image is divided into the target organ region and the non-target organ region, only the blood vessel metrics corresponding to the pixel points positioned in the target organ regions are calculated, calculation of blood vessel metrics corresponding to all the pixel points is not needed, and the amount of calculation is reduced during calculation of the blood vessel metrics, so that processing efficiency of blood vessel identification is improved, data in need of storage is reduced during calculation, and storage space is saved. The problems of low organ blood vessel identification efficiency and occupation of substantial internal storage and video memory space are solved.

An organ region extracting section that extracts at least one organ region from a three dimensional image of a subject; a directional data obtaining section that obtains directional data of the subject based on one of the position of the organ region within the body of the subject and the shape of the organ region; a stage region extracting section that extracts a region of a stage on which the subject is placed from the three dimensional image; and a posture data obtaining section that obtains posture data of the subject on the stage, based on the region of the stage and the directional data of the subject; are provided.

To provide an ultrasonic diagnostic apparatus capable of producing a three-dimensional image of an object for an organ region within a range of elasticity values desired by an operator and allowing the operator to recognize the region easily, elasticity value data included in a desired elasticity value range among elasticity value data constituting a volume data are selected and rendered. Whereby, a three-dimensional elasticity image in the set elasticity value range is produced. An area corresponding to the elasticity value range is displayed on at least one of a two-dimensional elasticity image and a section image.

The present application provides a ROI template generation method, a ROI extraction method, a system, an apparatus, and a medium. Wherein the ROI region extraction method includes identifying an organregion in the obtained face image; the preset ROI region template is adjusted to the edge of the recognized organ region to obtain the ROI region of the face image. The present application solves theproblem in the prior art that the area data processed in the face image processing using the ROI area template is not accurate enough.

The invention discloses a teaching system based on a medical image classical medical record library. The teaching system comprises a center platform and multiple learning systems connected to the center platform. The center platform is used for storing an organ model with 3D modeling and splitting of an organ region, an operation plan corresponding to an organ model case, and data in an operation and before and after the operation. Each of the learning systems comprises a self-learning module used for obtaining the case of the center platform and the corresponding data, viewing the organ model and data before the operation and carrying out self designing of an operation plan, comparing the self-designed operation plan and an actual operation plan and viewing an operation process, viewing organ model comparison before and after the operation, and questioning and evaluating the operation process. According to the teaching system, a problem that a trained doctor has no clinical experience and a doctor on the job is inconvenient to obtain a similar case solution is solved.

To make it possible to search for a similar case on the basis of distribution of lesions in a disease in which lesions are distributed within an organ, such as a diffuse parenchymal lung disease. Provided is a similar case image search program, which causes a computer to execute processes to: extract an organ region from a medical image; segment the organ region into a plurality of regions; countthe number of pixels which denote lesions in each of the regions resulting from the segmentation; refer to a storage unit which stores the numbers of pixels denoting the lesions for each of the regions; and identify a similar case image that accords with a degree of similarity of the numbers of pixels denoting the lesions.