91 results about "Whole body imaging" patented technology

A method for segmenting digitized images includes providing a training set comprising a plurality of digitized whole-body images, providing labels on anatomical landmarks in each image of said training set, aligning each said training set image, generating positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded.

A progressive series of five new coils is described. The first coil solves problems of transmit-field inefficiency and inhomogeneity for heart and body imaging, with a close-fitting, 16-channel TEM conformal array design with efficient shield-capacitance decoupling. The second coil progresses directly from the first with automatic tuning and matching, an innovation of huge importance for multi-channel transmit coils. The third coil combines the second, auto-tuned multi-channel transmitter with a 32-channel receiver for best transmit-efficiency, control, receive-sensitivity and parallel-imaging performance. The final two coils extend the innovative technology of the first three coils to multi-nuclear (31P-1H) designs to make practical human-cardiac imaging and spectroscopy possible for the first time at 7 T.

The invention discloses an access control system and a method based on face recognition. The access control system comprises a first trigger module, a second trigger module, a first image processing module, a second image processing module and a facial feature comparing module, wherein a first image collecting module can collect a wholly-body image of personnel in a first trigger area; a second image collecting module can collect a face image of personnel in a second trigger area, process the whole-body image and correct parameters; compared with all prestored outline information, all prestored face images in a correcting area can be screened out, and the prestored face images are matched and fused with the collected face image; the facial feature comparing module can control an access control system to unlock according to a matching degree of the face image; meanwhile, the access control system can sense that personnel enter and exit through a sensing module, so that advertisements can be broadcasted and interrupted in real time; the access control system disclosed by the invention can quickly and accurately perform image recognition, so that access control system response time delay is reduced, advertisement exchange is accurately achieved, a work efficiency of the access control system is improved, and convenience is brought to property management.

The invention provides a recurrent neural network attention model-based pedestrian attribute recognition network and technology. The pedestrian attribute recognition network comprises a first convolutional neural network, a recurrent neural network and a second convolutional neural network, wherein the first convolutional neural network is used for extracting a whole body image feature of a pedestrian by taking an original body image of the pedestrian as an input; the recurrent neural network is used for outputting an attention heat map of an attribute group concerned at the current moment andlocally highlighted pedestrian features by taking the whole body image feature of the pedestrian as a first input and taking an attention heat map of an attribute group concerned at the last moment as a second input; and the second convolutional neural network is used for outputting an attribute prediction probability of the currently concerned group by taking the locally highlighted pedestrian feature as an input. According to the network and technology, a recurrent neural network attention model is utilized to mine an association relationship of pedestrian attribute area space positions soas to highlight positions of areas corresponding to attributes in images, so that higher pedestrian attribute recognition precision is realized.

The invention provides a lung lesion detection method and system, a storage medium, a terminal and a display system. The lung lesion detection method comprises the steps of acquiring a patient image marked with a lesion; identifying the marked area contour, and training the identified area contour to obtain key feature points; extracting a thoracic cavity image from the whole body image of the patient, and judging whether the extracted thoracic cavity image belongs to the thoracic cavity or not; if so, executing the next step; if not, re-extracting the thoracic cavity image; reading the extracted thoracic cavity image, converting pixel values of the thoracic cavity image, and genertaing a medical image file and a medical image with a mask; performing focus detection on the medical image with the mask through the key feature points of the focus; and mapping the detected lesions to the extracted thoracic cavity image to realize visualization of the lung lesion and form a lung 3D model. Amedical auxiliary means is provided for doctors, and the doctors are assisted to accurately diagnose the position of the lung focus in the image.

The invention relates to magnetic resonance elastography detection system and method thereof. The detection system comprises a high-field nuclear magnetic resonance whole body imaging system which can carry out liver imaging, and a shear wave excitation device. The detection method comprises the following steps of: (1) inner particle displacement on a phantom or a detected part; (2) magnetic resonance elastography forming; and (3) fibration classification. For preliminary experiments on the phantom as well as studies on background phase noise and experiment researches on the relationship between shear wave transmission and shear wave frequency, the invention has good image quality and obvious effect. The invention establishes a foundation for subsequent MRE researches on the liver tissue, and provides directions and references for elastic researches on other parts.

Presented herein are systems and methods that provide for automated analysis of three-dimensional (3D) medical images of a subject in order to automatically identify specific 3D volumes within the 3D images that correspond to specific anatomical regions (e.g., organs and / or tissue). Notably, the image analysis approaches described herein are not limited to a single particular organ or portion of the body. Instead, they are robust and widely applicable, providing for consistent, efficient, and accurate detection of anatomical regions, including soft tissue organs, in the entire body. In certain embodiments, the accurate identification of one or more such volumes is used to automatically determine quantitative metrics that represent uptake of radiopharmaceuticals in particular organs and / or tissue regions. These uptake metrics can be used to assess disease state in a subject, determine a prognosis for a subject, and / or determine efficacy of a treatment modality.

The embodiment of the invention discloses a human body height measuring method, a human body height measuring device and an intelligent mirror. The human body height measuring method comprises the steps of obtaining an image through a camera; when a user image in the image is a whole body image, obtaining the distance from a user to a lens of the camera through a distance measuring sensor; calculating the user height according to the distance from the user to the lens of the camera, the distance from the lens of the camera to an image sensor, and the imaging height of the user on the image sensor of the camera; showing the user height to the user in the preset showing mode. The technical scheme provided by the embodiment has the advantages that the user image is obtained through the camera; the distance from the user to the camera is measured; the user height is calculated and showed to the user; the height measuring convenience is improved.

The invention discloses a figure image auxiliary shooting method and system based on image aesthetics. The method comprises the following steps: (1) framing a model through a viewing frame to perform pre-shooting, and performing face detection and human body region detection on a pre-shot image to obtain a face image and a human body area image; (2) detecting whether or not a straight line passes through a figure head background in the face image, and if so, prompting a user; (3) judging whether or not the pre-shot image is a whole-body image, prompting the user according to a main body optimal proportion rule if the pre-shot image is the whole-body image, judging whether or not a human body proportion meets a composition requirement if the pre-shot image is not the whole-body image, and prompting the user if the human body proportion does not meet the composition requirement; and (4) detecting the location of the model and the size of a human body region, and prompting the user according to a rule of the thirds in composition aesthetics. The invention also discloses a figure image auxiliary shooting system based on the image aesthetics. The figure image auxiliary shooting method and system are simple and effective, high in running speed and high in feasibility. Images shot by the user after guidance can meet a composition rule, and are more aesthetic.

A fuzzy video person identifying method includes extracting face and other human body characteristic information of different places and times to form optimal whole body image information, and identifying the identity of a person by comparing the whole body image information with an authentic image information registration database. Compared with the prior art, according to the technical scheme, the method has the advantages that the technical defects of the prior art that the persons cannot be identified in fuzzy videos are solved, and the timeliness of identification is improved by optimizing the database; in addition, according to the information that a target person appears in the video possibly, the fuzzy retrieval and identification can be performed.

A method for generating a positron emission tomography (PET) attenuation correction map from magnetic resonance (MR) images includes segmenting a 3-dimensional (3D) magnetic resonance (MR) whole-body image of a patient into low-signal regions, fat regions, and soft tissue regions; classifying the low-signal regions as either lungs, bones, or air by identifying lungs, identifying an abdominal station, and identifying a lower body station; and generating an attenuation map from the segmentation result by replacing the segmentation labels with corresponding representative attenuation coefficients.

The invention discloses a posture evaluation method, an electronic device, a computer device and a storage medium. The method comprises the following steps of: acquiring images to be detected, whereinthe images to be detected include a front whole-body image and a side whole-body image of a tester standing upright; extracting bone key points from the images to be detected; calculating posture vector quantity of the tester according to the bone key points; and acquiring the bending angle of the posture vector quantity of the tester. According to the posture evaluation method, the electronic device, the computer device and the storage medium provided by the invention, the method can extract the bone key points from the images to be tested of the tester, calculates the posture vector quantity of the tester according to the bone key points, acquires the bending angle of the posture vector quantity of the tester, further performs posture evaluation according to the bending angle, can improve the comprehensiveness and accuracy of posture evaluation, and is simple to operate.

A set of first modality data (e.g., MR or CT) is provided. The set of first modality data comprises a plurality of mu-maps, a plurality of motion vectors and a plurality of gated data. Each of the mu-maps corresponds to one of the beds. A set of second modality data (e.g., PET / SPECT) is provided. The set of second modality data comprises a plurality of frames for each of the beds. Each of the plurality of frames is warped by one or more motion vectors of the plurality of motion vectors. A single-bed image is generated for each bed by summing the frames corresponding to the bed. A whole body image is generated by summing the single-bed images for each of the beds.

A system for providing automatic diagnosis and decision support includes: a medical image database; generative learning and modeling modules that build distributional appearance models and spatial relational models of organs or structures using images from the medical image database; a statistical whole-body atlas that includes one or more distributional appearance models and spatial relational models of organs or structure, in one or more whole-body imaging modalities, built by the generative learning and modeling modules; and discriminative learning and modeling modules that build two-class or multi-class classifiers for performing at least one of organ, structure or disease detection or segmentation.

The invention discloses an intellectualized liquid-helium-free magnetic resonance whole-body imaging superconducting magnet system. The intellectualized liquid-helium-free magnetic resonance whole-body imaging superconducting magnet system comprises a vacuum container, a helium liquid storage box and a refrigerator, wherein a main magnetic field superconducting coil is arranged in a radial insidespace of the vacuum container, a shielding magnetic field superconducting coil is arranged in a radial outside space of the vacuum container, and a heat pipe air storage tank is placed in an idle areabetween the main magnetic field superconducting coil and the shielding magnetic field superconducting coil; the helium liquid storage box is communicated with a liquid storage box and air storage tank, is also connected with the main magnetic field superconducting coil or the shielding magnetic field superconducting coil through a helium self-oscillating heat pipe, and the helium self-oscillatingheat pipe is further communicated with the heat pipe air storage tank; the refrigerator is fixed to the vacuum container through a cold head automatic insertion and extraction assembly; the first-level cold head of the refrigerator is in close contact with a thermal radiation screen assembly, and the second-level cold head of the refrigerator is in close contact with the helium liquid storage box. By means of the intellectualized liquid-helium-free magnetic resonance whole-body imaging superconducting magnet system, the problems are solved that an existing superconducting magnet system is poor in cooling performance, once the refrigerator stops work, a magnet loses heat quickly due to excessive heat leakage, and the superconducting magnet system is complicated to maintain and poor in reliability.

The invention relates to a method for measuring human body dimension for garment customization through pictures. The method comprises the steps that the first picture and the second picture are obtained, wherein a front stand whole body image and a reference object with the given dimension are contained in the first picture, a side stand whole body image and the reference object with the given dimension in the first picture are contained in the second picture, and the body in the body images belongs to the same person; the body length data is worked out with a proportion method according to the length parameters of the body image and the length parameters of the reference object in the first picture; perimeter calculation values are worked out with an oval perimeter formula according to the perimeter parameters of the body image in the second picture and the perimeter parameters of the body image in the first picture, and the perimeter data is worked out with a proportion method according to the perimeter calculation values and the length parameters of the reference object. The method can solve the problem that the real time performance of a traditional manual measuring method is poor.

The invention discloses a low-cost large-field functional-molecular-structural imaging system and method aiming at medical isotope. The system comprises a functional-molecular-structural imaging coaxial detector, a data processing device and a computer device, wherein the functional-molecular-structural imaging coaxial detector is used for scanning a physical imaging object to obtain the functional and molecular imaging image information and structural imaging image information of the physical imaging object and outputting the information to the data processing device; the data processing device is used for receiving and storing the functional and molecular image information and decomposing the structural information, carrying out fusion calculation on the functional-structural images, drawing a multi-modality fused section image, and transmitting the image to the computer device for displaying; and the computer device is used for realizing image reconstruction and displaying the functional-molecular-structural multi-modality fused section image. According to the invention, a charge-coupled device and spiral CT (computerized tomography) are adopted for detecting effective information at coaxial aperture position, thus as compared with PET (positron emission tomography) / CT, SPECT (single photon emission computed tomography) / CT and other bi-modality imaging devices, the imaging axial-direction field is enlarged, the whole body imaging time is shortened, and the isotope imaging cost is greatly lowered.

A system for providing automatic diagnosis and decision support includes: a medical image database; generative learning and modeling modules that build distributional appearance models and spatial relational models of organs or structures using images from the medical image database; a statistical whole-body atlas that includes one or more distributional appearance models and spatial relational models of organs or structure, in one or more whole-body imaging modalities, built by the generative learning and modeling modules; and discriminative learning and modeling modules that build two-class or multi-class classifiers for performing at least one of organ, structure or disease detection or segmentation.

A single-impulse panoramic photoacoustic computed tomography (SIP-PACT) system for small-animal whole-body imaging is disclosed. In addition, a dual-speed of sound image universal back-projection reconstruction method is disclosed. Further, a PACT system for imaging a breast of a subject is disclosed.

An imaging station / booth for automated total body imaging having a small footprint and capable of quickly, efficiently, effectively, and consistently capturing multiple body images of a user or patient over time with minimal assistance from medical staff.

A method for segmenting vertebrae in digitized images includes providing a plurality of digitized whole-body images, detecting and segmenting a spinal cord using 3D polynomial spinal model in each of the plurality of images, finding a height of each vertebrae in each image from intensity projections along the spinal cord, and building a parametric model of a vertebrae from the plurality of images. The method further includes providing a new digitized whole-body image including a spinal cord, fitting an ellipse to each vertebrae of the spinal cord to find the major and minor axes, and applying constraints to the major and minor axes in the new image based on the parametric model to segment the vertebrae.

A method and apparatus are provided for forming a magnetic resonance image of a human. The method includes the steps of applying a plurality of relatively constant spatially non-selective radio frequency pulses to an imaging volume of the human, applying a plurality of combinations of magnitude of phase-encoding gradients in slice-selective and in-plane directions to the imaging volume of the human, wherein the plurality of combinations is adapted to undersample the imaging volume in k-space, detecting magnetic resonance imaging data from the imaging volume using a plurality of receiver coils and forming the magnetic resonance image of the imaging volume.

A method and apparatus are provided for forming a magnetic resonance angiographic image of a human body. A plurality of spatially non-selective radio-frequency pulses and a plurality of different combinations of phase-encoding gradients are applied to the human body, that are temporally non-coincident with the radio-frequency pulses and where each combination includes a pulse value in a slice selective direction and a pulse value in an in-plane direction and magnetic resonance imaging data are detected. A slice processor and / or a thickness processor identify the presence, location and / or thickness of a body portion of the human body. Identification of a body portion in a first imaging volume becomes the basis of application of a second plurality of spatially non-selective radio-frequency pulses to a second imaging volume of the human body.

The invention provides a local target re-recognition method, a device and a system, which relate to the technical field of image recognition. The method comprises the following steps: obtaining a whole-body image of an existing target and a local image of a target to be recognized; obtaining a local image of a target to be recognized; obtaining a whole-body image of an existing target. The whole body image and the local image are input to the pre-trained local target re-recognition model, so that the local target re-recognition model performs affine transformation on the whole body image basedon the local image, obtains the affine image of the whole body image, and determines the feature distance between the affine image and the local image; whether the target to be recognized matches with the existing target is judged based on the feature spacing. The invention can effectively improve the matching accuracy of the local image and the whole body image, thereby improving the re-identification accuracy.

A magnetic resonance system is provided which employs a shielded, electromagnetically asymmetric and low-stress magnet to produce a superior sized imaging region close to the patient side. The magnet has a double layered configuration. In the primary layer, the magnet includes at least two strongest coils at two ends of the magnet (end coils), which carry current in the same direction. The magnet may include at least one coil close to the end coils which carries current in a direction opposite to that of the end coils. The magnet employs a plurality of smaller sized coils (4-7, relative to the large end-coils) in the central region of the primary layer, and these coils are located asymmetrically relative to the imaging region centre. The magnet is shielded by a plurality (1-5) of shielding coils, which carry current in a direction opposite to that of the end-coils at primary layer. Compared with conventional short-bore magnets, the magnet of the invention offers an accessible imaging region with significantly enlarged imaging region, and it can be used in, for example, body-part or whole-body imaging.

The invention relates to a height measurement method, system and device based on video images and a medium, and the method comprises the steps: obtaining the video data of a measured person, and selecting a figure whole body image from the video data; performing face recognition on the figure whole-body image; obtaining facial feature information, judging whether the figure contained in the figurewhole-body image is a single figure or not according to the facial feature information; if not, performing image segmentation on the figure whole-body image according to the facial feature information to obtain a plurality of segmented figure images, obtaining a target figure image from all the segmented figure images, and if yes, directly taking the figure whole-body image as the target figure image; performing body part identification on the target person image to obtain body characteristic information of the measured person; generating a human body model according to the body characteristic information, and obtaining the height data of the measured person according to the human body model. Based on the video images, height measurement can be directly completed under the condition thata user does not feel, and high efficiency, accuracy and rapidness are achieved.

The invention discloses a cloths customized method, an image shooting device and a control system, and can be applied to clothes including coats, shirts and female underwear. The clothes customized method at the image shooting device side comprises that the image shooting device collects whole-body images in different angles; M body characteristic sizes are identified from the collected whole-body images, and M corresponding body portion sizes are obtained on the basis of the M body characteristic sizes and the present body characteristic proportion; and the M body portion sizes are led out to a customized production device, and according to the M body portion sizes, the customized production device generates a customized production control parameter which matches all the M body portion sizes. According to the invention, the technical problem that characteristic size data measured by a present measuring manner is inaccurate is solved effectively, and the obtained body portion sizes are more accurate.

The invention discloses a method, a device and a system for simulating a garment ornament worn by a user, and relates to the computer technical field. One embodiment of the method includes: acquiringa whole body image of a user, detecting the whole body image based on an evaluation model to evaluate a user posture; identifying the user and recommend clothing accessories according to the user's identity; the recognition algorithm based on geometric moment and edge detection recognizes user gestures and obtains gesture commands. A method for simulate a garment ornament worn by a user base on user gesture and gesture commands. This embodiment can reduce the amount of calculation, improve the calculation speed and identification accuracy.