165 results about "Medical imaging technology" patented technology

The present invention relates to a modular supramolecular bioresorbable or biomedical material comprising (i) a polymer comprising at least two 4H-units and (ii) a biologically active compound. Optionally, the supramolecular bioresorbable or bio medical material comprises a bioresorbable or biomedical polymer as third component to tune its properties (mechanical and bioresorption properties). The supramolecular bioresorbable or biomedical material is especially suitable for biomedical applications such as controlled release of drugs, materials for tissue-engineering, materials for the manufacture of a prosthesis or an implant, medical imaging technologies.

The invention belongs to the field of medical imaging technologies, and provides a method and a system for splicing digital X-ray images. The method and the system have the advantages that the images are aligned with one another in a template matching mode, accordingly, shortcomings of difficulty in extracting feature points, high matching computational complexity and easiness in causing matching failures in existing feature point detecting and matching modes can be overcome, the digital X-ray image splicing time can be shortened, and the efficiency can be improved.

A design method for an implantation body porous grid structure is characterized in that regional filling of an implantation body with a porous grid array is carried out by Boolean operations. The method is characterized in that a three-dimensional solid model of a defected human body bone is acquired by a medical imaging technology (CT); and according to elastic modulus distribution of the human body bone, namely the elastic modulus of a compact bone is 12-23.3 GPa and the elastic modulus of a cancellous bone is 6-10 GPa, regional grid filling is carried out to the extracted artificial bone model, wherein titanium or medical titanium alloy is taken as the filling material. The method can effectively reduce an equivalent elastic modulus of an implantation body, so that the implantation body can have good mechanical properties in a human body.

The invention belongs to the technical field of medical images, and relates to an automatic organ-at-risk sketching method and device based on a three-level convolutional neural network, and a storagemedium. The method comprises the following steps of: preprocessing the three-dimensional medical image, inputting the preprocessed three-dimensional medical image into the first-stage network, the second-stage network and the third-stage network of the trained three-stage convolutional neural network, sequentially identifying the cross section of the organ to be segmented, coarsely positioning the region of interest of the organ to be segmented, and classifying all pixel points in the region of interest; and then outputting a three-dimensional binary segmentation result; carrying out post-processing, edge extraction and edge smoothing on the binary segmentation result to obtain an automatically sketched organ. The three-level cascade convolutional neural network model is formed by cascading three convolutional neural networks, namely a first-level network, a second-level network and a third-level network. The three-level joint neural network has the advantages that priori knowledge isnot needed, the algorithm generalization ability is good, the robustness is high, the speed is high, full automation is achieved, and the segmentation accuracy is high.

The invention provides a computer-assisted recognition device and a corresponding computer-assisted recognition system. The computer-assisted recognition device comprises a scanning data acquiring module, a scanning image generating module, an acupoint information acquiring module and a lesion type recognizing module, wherein the scanning data acquiring module is used for receiving a scanning signal of a lesion region of a patient and acquiring the scanning data of the lesion region according to the scanning signal; the scanning image generating module is used for generating a scanning image of the lesion region according to the scanning data; the acupoint information acquiring module is used for receiving detection signals of at least one acupoint of the patient and acquiring the acupoint information of at least one acupoint according to the detection signals; and the lesion type recognizing module is used for recognizing the lesion type of the lesion region according to the image information in the scanning image and the acupoint information of at least one acupoint. Therefore, the research results of the meridian theory in the traditional Chinese medicine field can be effectively applied to the modern medical imaging technology to improve the probability of accurate diagnosis of lesions.

Embodiments of the invention disclose a medical imaging technology evaluation method. The method is used for evaluating a medical imaging technology on the basis of a pre-trained medical imaging technology evaluation model. The medical imaging technology evaluation model is trained according to a plurality of parameter indexes, for measuring the medical imaging technology, of a medical image training sample and a medical diagnosis information fidelity evaluation result of the medical image training sample, so that when the plurality of parameter indexes, for measuring the medical imaging technology, measured from a medical image are input into the medical imaging technology evaluation model, an output result reflecting medical diagnosis information fidelity can be obtained; and the outputresult serves as a medical imaging technology evaluation result and is capable of obtaining an evaluation result reflecting medical diagnosis information fidelity and measuring clinical diagnosis valeof the medical image. The embodiments of the invention furthermore disclose a medical imaging technology evaluation device.

The invention relates to a bone scaffold forming system comprising an image scanning unit, a three-dimensional reconstruction unit, a three-dimensional model building unit, a bone scaffold model building unit, a hierarchical processing unit and a low-temperature forming unit. By the aid of the bone scaffold forming system, scanning imaging is performed on the bone injury part of a patient before bone scaffold forming by means of medical imaging technology so as to obtain image data of the bone injury part, then the acquired image data are subjected to modular processing to obtain hierarchical data of a to-be-repaired bone scaffold model, bone formation materials are utilized to prepare a bone scaffold exactly matched with the bone defect part of the patient in size and shape by the low-temperature forming unit through the hierarchical data, and accordingly the bone scaffold matched with the implanting part is prepared for the patient in vitro before surgery implementation to the benefit of shortening implementing time, further implant materials are enabled to be closely bonded with the defect part to promote bone formation.

The invention belongs to the technical field of medical images, and discloses an intelligent AI PACS system and an examination report information processing method thereof. The intelligent AI PACS system comprises a patient information acquisition module, an image acquisition module, an image classification module, a central control module, a measurement module, an image processing module, an image analysis module, a report generation module, a compression encryption module, a wireless communication module, a data storage module, a terminal module, a synchronous updating module and a display module. All voxel data of a focus can be comprehensively collected through the measurement module, the measurement result is closer to the real volume of the focus, and objectivity and accuracy are high; through the synchronization module, image data of all hospital PACS systems can be synchronized with low cost, a convenient mode is provided for patient transfer, storage and management of self-image data by a patient are realized, and complete image data of the patient are provided for diagnosis of clinicians.

The invention belongs to the field of medical imaging technologies and optical image information processing, and provides a speckle noise filtering method for an optical coherence sectional image. The speckle noise filtering method for the optical coherence sectional image aims to improve visual quality of the image, reduces influences of speckle noises to the image and can carry out filtering noise reduction treatment on the optical coherence sectional image. According to the technical scheme, the speckle noise filtering method for the optical coherence sectional image comprises the following steps: step 1, inputting an optical coherence sectional image f; step 2, carrying out logarithm taking operation on the coherence sectional image; step 3, carrying out shearlet transform on the image to obtain shearlet coefficients after logarithm is taken; step 4, carrying out hard threshold operation on the obtained shearlet coefficients Sj, l, x and y; step 5, carrying out shearlet inverse transform on retained parts after hard threshold operation is carried out to achieve the purpose of filtering; and step 6, outputting the filtered image. The speckle noise filtering method for the optical coherence sectional image is mainly used for processing optical image information.

The invention belongs to the technical field of medical imaging, and particularly relates to a cardiac magnetic resonance image segmentation method. A cardiac anatomic structure-based left and right ventricle level set segmentation method specifically comprises the following steps: performing geometry decomposition to a cardiac structure; resolving a convex hull of an initialized contour; producing a signaled distance function; and generating intima and extima through a dual-level set algorithm, and the like. By using the method, the simultaneous segmentation of the ventricular intima and extima and cardiac muscle can be realized, and the segmentation results can meet the physiological structure characteristics of a heart as far as possible.

The present invention relates to a multi-source saddle-line locus conical beam CT approximate reconstruction method, belonging to the field of bio-medical imaging technology. It is characterized by that said invention adopts a structure with N x-ray sources and N detectors, uses N saddle-line loci to make scanning, utilizes projection data collected from N detectors to make them be formed into a complete projection data, and utilizes filter back projection approximate algorithm to directly reconstruct three-dimensional body data.

Described herein is medical imaging technology for concurrent and simultaneous synthesis of a medical CA-free-AI-enhanced image and medical diagnostic image analysis comprising: receiving a medical image acquired by a medical scanner in absence of contrast agent enhancement; providing the medical image to a computer-implemented machine learning model; concurrently performing a medical CA-free-AI-enhanced image synthesis task and a medical diagnostic image analysis task with the machine learning model; reciprocally communicating between the image synthesis task and the image analysis task for mutually dependent training of both tasks. Methods and systems and non-transitory computer readable media are described for execution of concurrent and simultaneous synthesis of a medical CA-free-AI-enhanced image and medical diagnostic image analysis.

The invention discloses an ultrasonic medical imaging method by utilizing a transmission method. As a novel ultrasonic medical imaging method, the invention is a fully digitalized ultrasonic medical imaging device realized by being based on a PC platform. The device particularly comprises a synchronizer, an emission control component, an ultrasonic emission transducer, an ultrasonic receiving transducer, a gating high pressure control component of an array element, a receiving control amplifying well-founded component, an A / D drive and transformation component, a digital beam forming component, a DSC data processing component, a display unit, the PC platform, a power supply unit, etc. The fully digitalized ultrasonic medical imaging device uses the parameters of sonic velocity and acoustic attenuation, and the like, and adopts medical imaging technology similar to a CT measuring method and the imaging algorithm. The measuring method is implemented by an ultrasonic emitter probe and an ultrasonic receiver probe which are coaxial and are arranged on both sides of a tested object. The imaging calculation method adopts algebraic reconstruction technique or back projection technique to reconstruct images. The ultrasonic medical imaging method has the advantages of good definition of the images reconstructed by digitization, no radiation to the human body and low cost, etc.

The invention relates to a quick modeling method for an artificial human chest structure in a car side collision test, and belongs to the field of car collision safety. The method comprises the stepsof 1, building a simplified chest outer contour model: by utilizing a medical image technology and human chest soft tissue characteristics, building a chest outer contour approximate geometric model;2, based on the geometric model, performing equivalent approximate processing on human thoracic spine, ribs and tissue structures in thoracic cavity by utilizing a mechanical equivalent thought according to a car side collision condition; 3, performing finite element grid division and material attribute assignment on the structures to generate a passenger chest initial finite element model under the side collision condition; and 4, building a passenger chest side collision structure optimization agent model, and finally building a quick modeling model of the artificial human chest structure inthe car side collision test. The quick modeling model of the artificial human chest structure, built by the method, improves the calculation efficiency by more than 3 times and provides quick and effective reference and data support for modeling in a car safety concept design stage and car passive safety performance analysis.

The invention belongs to the technical field of medical images and provides an image feature repeatability measurement method and apparatus. The method comprises the steps of obtaining a plurality of images and preprocessing the images; obtaining a region meeting a preset condition in each of the preprocessed images, and marking the region in each image; performing standardization processing on each image to enable a grayscale value of each pixel in each image to be located in a preset grayscale value region; extracting an image feature of the marked region, and obtaining a plurality of factor values related to the image feature; calculating an overall consistency correlation coefficient (OCCC) value of the image feature according to the factor values; and if the OCCC value is greater than a predetermined threshold, determining that the image has repeatability. Through the method and the apparatus, the problem of relatively low accuracy due to the fact that a single factor value is generally adopted for assessing the repeatability of the image feature in the prior art can be solved.

The invention provides an automatic extraction method for the vertebra in MRI lumbar vertebra image. The invention relates to the field of medical image processing technology and more particularly to an automatic extraction method for the vertebra in MRI (Magnetic resonance imaging) lumbar vertebra image. With the progress in medical image technology, MRI has already become an important means for diagnosing lumbar vertebra troubles. Traditionally, it takes about ten minutes to locate a troubled vertebra of a patient through the use of a mouse, which directly influences the working efficiency of a doctor to diagnose. The invention solves the problem of automatic identification and extraction of vertebra in MRI lumbar vertebra image. Through the use of the MRI lumbar vertebra's T2 image, it is possible to automatically extract the vertebra and to automatically calculate the size, the width, the height and the average grayscale of the vertebra so as to realize quantitative diagnosis of vertebra troubles rapidly and to increase the diagnosing efficiency of vertebra diseases.

The invention discloses an intelligent health check-up X-ray chest photography body position guidance method and a system, and belongs to the technical field of medical imaging. The intelligent healthcheck-up X-ray chest photography body position guidance method comprises the following steps: when a patient stands in a photography area, collecting a patient body position image, identifying a human body contour, and drawing a human body contour line a; drawing a human body contour line b under the correct posture of chest photography according to the human body contour line a; displaying the body position image of the patient and the human body contour line b in real time, prompting the patient to place a correct posture, and placing the body position image in the human body contour line b; and starting X-ray photography after judging that the posture of the patient meets the photography requirement. According to the method, the human body contour line of the patient in the correct chest photography posture is simulated through image recognition, only the corresponding body posture needs to be set out in comparison with the real-time image of the patient, great convenience is achieved, and the physical examination efficiency and the X-ray chest photography imaging quality can be effectively improved.

The invention relates to the field of medical image technology, and particularly to a breast nodules auxiliary diagnosis method based on DSSD and a system. The system comprises a breast image workstation, a breast cloud diagnosis system and a breast diagnosis mobile terminal. The breast image workstation performs breast image acquisition. The breast cloud diagnosis system comprise training set anda testing set preprocessing, marking and neural network discriminating, wherein the training set and the testing set preprocessing comprises multi-scale image de-noising and enhancing. The method comprises the steps of acquiring a breast graph by the breast image workstation, performing discriminating through mainly using a DSSD neural network, and finally transmitting a result which is obtainedthrough processing of the breast cloud diagnosis system to the breast diagnosis mobile terminal. According to the method and the system, a computer-aided diagnosis (CAD) system based on deep learningis developed for aiming at the field of the medical image (unnatural image), thereby supplying a second opinion for diagnosis to a radiology department doctor, and more effectively assisting the doctor in performing diagnosis.

The invention discloses a method for establishing image data through nuclear magnetic resonance and belongs to the technical field of medical images. The method comprises the following steps that nuclear magnetic resonance image sequential data of a target zone in the first pass process of a contrast agent are extracted; registration is conducted on an image sequence, so that displacement deviation of the target zone in the image sequence is eliminated; the myocardium outline in the target zone of an image is segmented, so that an inner outline and an outer outline of the myocardium are obtained; quantitative analysis is conducted, the myocardium in the image is segmented into a plurality of partial zones according to an ultrasonic cardiogram seventeen-segmentation division method along the outline, a pixel mean value of each zone is calculated, and a data curve of the relation of the signal intensity and time is obtained. The nuclear magnetic resonance image data are collected, image registration is conducted, the myocardium outline image data are obtained through segmentation, quantitative analysis is conducted, a data model and an accurate data analysis platform are established, and therefore waste of resources is avoided.

The invention provides equipment and a method for realizing dual-energy scanning by using flying focal spot switching and an X-ray filter, and relates to the technical field of medical images. The equipment comprises an X-ray bulb tube and an X-ray filter; the X-ray bulb tube can emit two X-ray beams from two different X-ray focal points; the X-ray filter is arranged between a CT detector array and the X-ray focal points and is provided with slits which are distributed periodically. According to the X-ray beam emitted by one of the X-ray focal points, X-rays of odd-numbered channels directly pass through the filter without attenuation, and X-rays of even-numbered channels are attenuated through a filter material, and the X-ray energy spectrum is changed. According to the X-ray beam emittedby the other X-ray focal point, X-rays of even-numbered channels directly pass through the filter without attenuation, and X-rays of odd-numbered channels are attenuated through the filter material,and the X-ray energy spectrum is changed. Therefore, the purpose of dual-energy CT scanning can be achieved. The scanning mode can combine a flying focal spot mode and an energy spectrum CT scanning mode when a heart is rapidly scanned, and requirements on the bandwidth of a slip ring is not high.

The invention relates to a medical imaging technology, in particular to a method for realizing fusion of an anisotropic image, a diffusion envelope surface image and a nerve distribution image. The method comprises the steps that corresponding anisotropic images, diffusion envelope surface images and nerve distribution images are acquired according to nuclear magnetic resonance data, and image fusion is completed by combining respective characteristics of the three images. The method is suitable for analyzing and reconstructing the complex biological tissue structure in the brain, and has important application values in the aspects of brain science, neuroscience, medical imaging and the like.

The invention is applicable to the technical field of medical images, and discloses a multi-mode imaging system. The multi-mode imaging system comprises a display, multi-mode imaging equipment and a mainframe electrically connected between the display and the multi-mode imaging equipment, the mainframe is internally provided with an image rebuilding and processing subsystem, the multi-mode imagingequipment is internally provided with an animal scanning control subsystem, a static computer tomography subsystem and a photoacoustic imaging subsystem, the static computer tomography subsystem comprises an electronic control circuit, a multi-beam carbon nano X-ray source array used for generating X-rays needed by static computer tomography scanning, a photon counting detector used for computertomography projection data acquisition and high-speed processing and a power supply used for supplying power to the multi-beam carbon nano X-ray source array, and the multi-beam carbon nano X-ray source array, the photon counting detector and the power supply are all electrically connected with the electronic control circuit. The multi-mode imaging system is high in image resolution, large in imaging depth and low in radiation dose.

The invention discloses an imaging method of a hard X-ray grating interferometer with single exposure. The imaging method is characterized by including the steps of 1, moving any grating, and fixing a working point of the hard X-ray grating interferometer at a left half waist and right half waist position of a light intensity curve; 2, obtaining a background projection image and a projection image of an imaged object respectively; 3, obtaining the normalized projection image of the imaged object, and conducting logarithm process on the normalized projection image; 4, constructing an expression formula to conduct one-dimensional Fourier transform according to the logarithm process result; 5, utilizing one-dimensional inverse Fourier transform to extract absorption of the imaged object and a relative phase shift signal respectively according to the result of the Fourier transform. According to the imaging method of the hard X-ray grating interferometer with the single exposure, the data collection procedure of the hard X-ray grating interferometer is simplified, the imaged object is subjected to single exposure, the imaging efficiency is improved, the radiation damage risk is reduced, and thus a new path of the development of a future fast and low-radiation-dose clinical medical imaging technology is provided.

The invention belongs to the technical field of medical imaging, and specifically relates to a tumor-targeting polypeptide probe and application of the probe in tumor imaging. The invention relates to the tumor-targeting polypeptide probe. The general formula of the polypeptide probe is R-X-YW7, the YW7 is a polypeptide specifically targeting ANXA2 in vivo, and the sequence is YWRGVYN; and X is a linker, R is a signal unit, and X and R are covalently connected. The polypeptide probe is applied to preparation of a tumor diagnosis reagent, a tumor imaging reagent, a tumor operation guiding agent and / or a tumor active targeted therapy related drug tracer. Experiments prove that the tumor-targeting polypeptide probe provided by the invention has strong specificity and high sensitivity, and through a nude mouse subcutaneous pancreatic cancer model, a nude mouse subcutaneous glioma model and a nude mouse in-situ glioma model which are cultured in sequence, the polypeptide probe can be specifically absorbed by glioma, and quickly accumulates in tumor cells or tumor tissues within 2 hours; and compared with a control group, the tumor-targeting polypeptide has a remarkable tumor targeting advantage, and is clinically used for tumor diagnosis and treatment.

The invention discloses a microwave thermoacoustic, optical acoustic and ultrasonic three-modal intestinal tissue imaging method and system, and relates to a medical imaging technology. The microwavethermoacoustic, optical acoustic and ultrasonic three-modal intestinal tissue imaging method comprises the steps that intestinal tissue ultrasonic images are obtained, a pulse laser and a pulse microwave are emitted to a to-be-imaged area of intestinal tissue, thus intestinal tissue optical acoustic signals and intestinal tissue thermoacoustic signals are generated in the to-be-imaged area of theintestinal tissue and converted into electrical signals, through amplification, filtering, A / D conversion and image reconstruction, intestinal tissue optical acoustic images and intestinal tissue thermoacoustic images are obtained, and the intestinal tissue optical acoustic images subjected to color coding and the intestinal tissue thermoacoustic images subjected to color coding are superimposed on intestinal tissue ultrasonic images. The microwave thermoacoustic, optical acoustic and ultrasonic three-modal intestinal tissue imaging system comprises an ultrasonic imaging module, a pulsed laser, a pulse microwave source, a ultrasonic transducer, a signal processing unit, a data collecting unit and a computer. The imaging method is a non-invasive method, operation is convenient, patients donot have pain, and imaging of the intestinal tissue can be realized more comprehensively.

The invention belongs to the technical field of medical images and particularly relates to a manufacturing process for high-toughness forged and pressed anti-abrasion liner plates. The manufacturing process for high-toughness forged and pressed anti-abrasion liner plates comprises the following steps of steel plate cutting and blanking, forging, machining, quenching, tempering, inspecting and product finishing. The manufacturing process has the beneficial effects that pollution and the production cost can be reduced during production, and the utilization efficiency of alloy elements can be improved; the liner plates can be used for semi-autogenous mills which are more than 13 meters high, and the phenomena of cracks and block falling are avoided.

The embodiment of the invention provides a method and device for detecting a micro-calcification cluster in a mammary gland molybdenum target image and electronic equipment, and relates to the technical field of medical images. The method comprises the following steps: firstly, partitioning a to-be-detected mammary gland molybdenum target image; after a plurality of to-be-detected mammary gland molybdenum target image blocks are obtained, feature extraction is carried out on the to-be-detected mammary gland molybdenum target image blocks; carrying out segmentation processing on the first feature image blocks containing the micro-calcification points; splicing the segmented first feature image blocks and the second feature image blocks which do not contain the micro-calcification points into a complete image; and finally, carrying out clustering processing on the micro-calcification points. According to the method, the micro-calcification clusters are obtained, and the to-be-detected mammary gland feature image containing at least one micro-calcification cluster is classified based on the pre-established classification model to determine the category of the to-be-detected mammary gland molybdenum target image, so that the image proportion of micro-calcification is improved, the difficulty of micro-calcification point segmentation is reduced, and the accuracy of subsequent analysis is improved.