187 results about "Low dose" patented technology

The invention provides a lightweight low-dose CT (Computed Tomography) (LDCT) image denoising method based on a Transform network, and belongs to the technical field of medical image processing. The method provided by the invention is called CT-Denomer, global context information in a CT image and local context details of complex space change can be captured, and a high-quality image is generated. A core of a framework of the CT-Denoimmer is a Transform module, and the CT-Denoimmer comprises two key components, namely a multi-head convolution transpose attention (MDTA) and a hybrid context feedforward network (MCFN). The MDTA module captures global context information in an image with linear computational complexity, while the MCFN module pays attention to multi-scale local static and dynamic context information through a series of enhanced context Transformer blocks (eCoT). Besides, an intelligent operation attention layer (OWALs) is introduced to cope with a complex and changing noise mode in the LDCT image, so that the network can optimize the denoising effect in diversified scenes. According to the method, the fine structure retention and noise suppression of the denoising result of the LDCT image reach advanced performance.

The invention provides a low-dose CTA image noise reduction model training method, a noise reduction method and equipment. The method comprises the following steps: acquiring cardiovascular and edge noise enhancement data of a low-dose CTA image based on a cardiovascular segmentation model and an edge extraction model; according to the data and the conventional dose CTA image, a cyclic generative adversarial network is trained based on target loss so as to train the cyclic generative adversarial network into a low dose CTA image noise reduction model, and the target loss comprises cardiovascular maintenance loss obtained based on a cardiovascular segmentation model and edge maintenance loss obtained based on an edge extraction model. According to the invention, the blood vessel and edge enhancement and the global noise reduction of the low-dose CTA image can be combined in the training process of the low-dose CTA image noise reduction model, so that the model can give consideration to the reservation of the fine structure of the image and the improvement of the overall image quality. Therefore, the application effectiveness and reliability of a low-dose CTA image noise reduction result obtained by adopting the model can be effectively improved, and the reliability of CTA clinical diagnosis is improved.

The invention is applied to the technical field of image denoising, and particularly discloses a low-dose CT image denoising generalization method based on a diffusion model. The method comprises the following steps: S1, constructing a low-dose CT denoising and generalization network model; s2, acquiring CT images of a low dose and a corresponding normal dose; according to the low-dose CT image denoising generalization method based on the diffusion model, the multi-stage diffusion model and the dynamic double-attention network are designed, the problem of error accumulation in a traditional single-stage method is effectively relieved through a cascade optimization mechanism, meanwhile, the dynamic double-attention network DDA-Net is combined, and the low-dose CT image denoising generalization method based on the diffusion model is obtained. A channel-space self-adaptive attention mechanism is utilized to realize cross-dose level unsupervised generalization ability, clinical variable dose scenes can be adapted without relying on pairing training data, key high-frequency details for diagnosis are reserved, and discrimination of anatomical edges and textures is enhanced through a selective scanning mechanism.

The invention discloses a low-dose 3D spiral CT reconstruction method and system based on a context cold diffusion model, and the method comprises the following steps: converting a linear inverse problem of CT imaging into an optimization problem, and adding a regularization term; based on a near-end gradient descent framework, solving the optimization problem by adopting an iterative shrinkage threshold algorithm, replacing a near-end operator in the near-end gradient descent method with a pre-trained two-dimensional cold diffusion model, and replacing a regularization item with the pre-trained cold diffusion model; when the cold diffusion model is pre-trained, three-dimensional context information formed by a current slice and two adjacent slices is used as the input of the cold diffusion model; taking a low-dose two-dimensional CT image as input, and performing low-dose 3D spiral CT image reconstruction by adopting the trained network; by combining the physical imaging model and the deep learning prior, the reconstruction quality and efficiency of the low-dose CT are remarkably improved, the noise and artifacts in the low-dose CT image are remarkably reduced, and the quality of the low-dose CT image is remarkably improved.

The present invention relates to method for medical imaging, the method being characterized in that it comprises the implementation, by a data processor (11b) of a second server (1b), of steps of: (a) Obtaining at least one candidate pre-contrast image and a candidate contrast image respectively depicting a body part prior to and after an injection of a first dose of contrast agent, wherein said first dose is higher than a predetermined low dose, the predetermined reduced dose being lower than a predetermined standard dose; a convolutional neural network, CNN, being trained to reconstruct, from at least a pre-contrast input image and a low dose contrast input image respectively depicting a body part prior to and after an injection of said low dose of contrast agent, a standard dose contrast image depicting said body part after an injection of said standard dose of contrast agent; (b) Simulating an injection of a second dose of contrast agent which is higher than the standard dose, wherein said simulating comprises generating a synthetic contrast image by applying the CNN to the at least one candidate pre-contrast image and the candidate contrast image.

The invention relates to a low-dose computed tomography (CT) denoising method of a tight frame wavelet, and the method comprises the steps: S1, collecting a low-dose CT picture and a conventional-dose CT picture to construct a CT data set, and converting the CT data set into a Numpy matrix; s2, GTF (Geometric Tigh Framelet) transformation is carried out on the image data to obtain one low-frequency component and eight high-frequency components, the high-frequency components are grouped, and the number of the high-frequency components in each group is 2, 3 and 3; s3, creating a tight frame diffusion model (Tight Frame Diffusion Model), and carrying out the denoising of the low-frequency component; s4, a group high-frequency enhanced network (GHFEN) is created, and the high-frequency component is recovered by the group high-frequency enhanced network (GHFEN), and the high-frequency component of the high-frequency component is recovered by the group high-frequency enhanced network (GHFEN), and the high-frequency component of the high-frequency component is recovered by the group high-frequency enhanced network (GHFEN); and S5, finally, carrying out inverse GTF transformation on the enhanced and denoised components to obtain a denoised image. By using the CT image denoising method and the CT image denoising device, a CT image denoising service which is more in line with a human eye observation effect can be provided for a low-dose CT obtained by a user through a CT scanner. The multi-level feature perception low-dose CT denoising method can be widely applied to the field of CT denoising.

Provided herein are methods to treat various neurodegenerative disorders comprising delivering a viral particles to the whole brain, including both superficial and deep structures. In some aspects, the viral particles are administered at low dose levels to the CSF, in conjunction with microbubbles followed by application of focused ultrasound (FUS) to a region of interest of the brain, thereby causing entry of the viral particles to the brain.

Provided herein are methods for the treatment or prevention of sickle cell crisis and symptoms associated therewith by the administration of low doses of tocilizumab to a subject. In particular embodiments, provided herein are pharmaceutical compositions comprising doses of 200 mg or less of tocilizumab and methods for the treatment or prevention of sickle cell crisis and symptoms or other conditions arising as a result thereof.

The invention relates to a double-cavity radiotherapy and chemotherapy integrated treatment capsule for brain glioma, which aims to solve the problems that the existing radioactive seed source or chemotherapy carrier cannot give consideration to radiotherapy and chemotherapy, the dosage is difficult to regulate and control, the medicine distribution is non-uniform and the like. The brain glioma double-cavity radiotherapy and chemotherapy integrated treatment bag is composed of a radiotherapy pipeline and a chemotherapy pipeline, the whole integrated treatment bag is a spiral pipe body, the radiotherapy pipeline is located in an inner ring, the chemotherapy pipeline is located in an outer ring, the radiotherapy pipeline is a closed cavity, a liquid radioactive source is contained in the closed cavity, and the liquid radioactive source is located in an outer ring. The chemotherapy medicine is released from the head end of the chemotherapy pipeline, the chemotherapy medicine is injected from the tail end of the chemotherapy pipeline, and the surface of the integrated treatment bag is coated with a composite antibacterial layer. According to the integrated treatment capsule, radiopharmaceuticals and chemical drugs are placed in the inner cavity and the outer cavity respectively, synergistic treatment of radiotherapy and chemotherapy is achieved through the synchronous effect of the two channels, and long-term low-dose release of the radiopharmaceuticals and the chemotherapy drugs is achieved and toxic and side effects are reduced by adjusting the screw pitch and the thickness of the tube wall.

The invention provides a wireless electronic personal dosimeter capable of dynamically adjusting an alarm threshold value and a control method, and relates to the technical field of radiation monitoring. Comprising a detection module used for collecting historical dose data of a user and constructing a personal dose management library. And the wireless communication module is used for extracting accumulated dose data. And the man-machine interaction module is used for setting a fixed alarm threshold value, setting a personalized alarm threshold value according to the real-time accumulated dose and the accumulated dose data, comparing the fixed alarm threshold value with the personalized alarm threshold value in real time, and selecting a lower value as a real-time alarm triggering standard. And the alarming and updating module is used for judging whether the current dose of the user exceeds a real-time alarming triggering standard, if so, alarming, and uploading the current dose to the personal dose management library for updating. According to the invention, through setting the personalized alarm threshold value, the personal dose accumulation risk can be effectively reduced, the personnel in a low-dose environment for a long time can be more effectively protected, and personalized and precise management of radiation protection is realized.

The invention discloses a low-dose computed tomography image denoising method and device based on self-supervised learning and a medium, and belongs to the technical field of medical image processing, aiming at solving the technical problem that the accuracy of clinical diagnosis is affected due to the fact that low X-ray dose is adopted by LDCT, and image quality is often interfered by noise. According to the method, denoising can be completed only by processing a single low-dose CT image by using a self-supervised learning framework. According to the method, the denoising mode is learned from the LDCT image containing noise, real ground truth is not needed, and the limitation that a traditional method depends on a real high-dose CT image to serve as training data is avoided. According to the method, the requirements of low-radiation exposure and high-quality imaging are balanced, the de-noising effect of the low-dose CT image can be remarkably improved, and the method is suitable for de-noising processing of the low-dose CT image in medical diagnosis.

The invention discloses a low-dose CT (Computed Tomography) imaging method and equipment based on semantic priori knowledge guidance. In order to solve the problems of excessive smoothness of images, detail loss and the like in low-dose CT imaging, semantic prior information is extracted through a pre-trained visual model by utilizing significant differences of different anatomical structures (such as bones, soft tissues, gas regions and the like) on noise levels, so that different tissue types are effectively distinguished, and noise modes of specific regions are captured. Meanwhile, a semantic perception module is provided, detail features concerned by the noise reduction network and high-level anatomical semantic features captured by the semantic network are aligned and fused, and it is ensured that the anatomical structure is perceived more accurately in the denoising process. Further, a segmentation network is introduced behind the noise reduction network, and a multi-task learning strategy is adopted to realize joint optimization of noise reduction and semantic segmentation. According to the design, the denoising performance of the image is improved, key anatomical details are effectively reserved, and clearer image support is provided for clinical diagnosis.

The present application relates to positron emission tomography (PET) imaging in the medical and industrial fields, and discloses a low-dose PET image enhancement method and system, used for solving the problem in the prior art of having poor effect when an MR image of anatomical structure information is used as prior information to generate a normal-dose PET image from low-dose PET image data. According to the solution, spatial features of an anatomical structure are obtained from an MR image and spatial anatomical alignment information, and the spatial features of the anatomical structure are used to spatially adjust low-dose PET image features to achieve adaptive enhancement of spatial regional information and fusion of different modalities, so as to improve the display quality of the anatomical structure of low-dose image data, improve the definition of the anatomical structure, provide effective reference for clinical diagnosis, reduce the use amount of a tracer, reduce economic costs, and lessen the radiation load on patients.

The invention provides a transfer learning-based CT image pulmonary nodule intelligent detection method and system, and the method comprises the steps: carrying out the training and testing of a noise reduction network through employing a low-dose and full-dose CT data set, and building a pulmonary nodule noise reduction model; a lung CT data set is adopted, a U-shaped segmentation network is trained and tested, and a pulmonary nodule segmentation model is established through transfer learning; and based on the coding module structure of the pulmonary nodule segmentation model, establishing a pulmonary nodule classification model through transfer learning. According to the method, a transfer learning method is comprehensively used, part of structures and parameters of the segmentation model are obtained through transfer of the noise reduction model, and part of structures and parameters of the classification model are obtained through transfer of the segmentation model. According to the method, end-to-end auxiliary algorithm research is realized, hyper-parameters required by training are reduced by using task-to-task transfer learning, the fitting speed is accelerated, and a more accurate and reliable auxiliary detection tool is provided for clinicians.

A composition for treating Huntington's disease (HD) by reducing endogenous Huntingtin (HTT) levels in a target includes a siRNA including a siRNA sequence selected from SEQ ID NOs:47 to 149, and a carrier peptide comprising a peptide sequence of SEQ ID NO:1. The carrier peptide may target the nicotinic acetylcholine receptor (nAChR) of neuronal cells in order to deliver the siRNA across the blood-brain barrier (BBB). In some embodiments, the siRNA may be conjugated with the carrier peptide. A method of reducing endogenous HTT levels to treat HD in the target may include administering a composition including a siRNA sequence selected from SEQ ID NOs: 47 to 149 to the target.

Disclosed are methods and devices for obtaining patent hemostasis of the radial artery by compressing the uninstrumented ulnar artery to increase radial artery flow. The device comprises a band having an inflatable bladder for applying blunt pressure to the ulnar artery. The method comprises applying a pressure to the homolateral ulnar artery and applying a pressure to the radial artery at the access site to obtain hemostasis at the access site. The method further comprises administering an anticoagulant to a patient at a dose ranging from about 20 units per kg of body weight to about 30 units per kg of body weight.

The invention relates to the technical field of medical X-ray, radio frequency and high-frequency diagnosis and treatment equipment, in particular to a full-static X-ray radiotherapy system and method. The system is composed of an electron source, an accelerating cavity, a two-dimensional deflector, an annular magnet set, a strip-shaped anode target, a multi-leaf collimator set, a vacuum cavity and the like. The electron beam enters the two-dimensional deflector after being accelerated, and any plane angle is obtained under the pure electromagnetic action; and then the X-rays are guided to the strip-shaped anode target along each electron channel in an annular magnetic field of the annular magnet group to bombard and generate the X-rays. The multi-leaf collimator performs spatial modulation on rays to form an irradiation field matched with a target region, so that multi-angle high-precision radiation irradiation without mechanical rotation is realized. The strip-shaped target surface increases the heat dissipation area and cooperates with an efficient cooling loop, so that the dose rate upper limit is improved, and the FLASH radiotherapy requirement is met. The scheme is compact in structure, low in cost and simple and convenient to maintain, overcomes the defects of large size, low efficiency, limited dosage and the like of traditional rotary radiotherapy equipment, and has wide clinical popularization value.

The invention provides a low-dose CT image processing method and device, electronic equipment and a medium, and relates to the field of medical image processing, and the method comprises the steps: obtaining a to-be-processed low-dose CT image; performing noise characteristic quantization on the low-dose CT image to generate noise characteristics; extracting image features of the low-dose CT image by adopting a trained image processing model, fusing the image features with the noise features to obtain fused features, and processing the fused features to obtain a target CT image; according to the method, accurate denoising of the low-dose CT image can be realized, diagnosis details such as organ boundaries and blood vessels are efficiently reserved, the robustness of the model to various noise scenes is enhanced, the calculation overhead is reduced, and a high-quality target CT image meeting clinical diagnosis requirements is output.

A CT scanner for performing a brain scan performs a low-dose 3D scan in a first field of view. By analyzing the low-dose 3D scan, for example using landmark detection, a proposed field of view for a full-dose 3D brain scan is obtained. A representation of the proposed field of view is displayed and a final field of view is generated as the proposed field of view or an updated version of the proposed field of view provided by a user of the CT scanner.

[Problem] The present invention addresses the problem of improving, by the use of glutathione, skin brightness or disorders in the skin caused by ultraviolet rays. [Solution] The present inventors have arrived at the present invention as a result of discovering a method with which skin brightness is improved through the use of a glutathione-containing composition containing a dipeptide derived particularly from a yeast extract or the like, even at a low dose where the glutathione content intake is 100 mg / day or less.

An object is to provide a Th1-increasing agent that can reduce constraints on storage conditions and feeding form and sufficiently increase Th1 at lower doses. A Th1-increasing agent containing a cellulose derivative as an active ingredient, the cellulose derivative having a degree of butyryl substitution of 0.3 or greater and 2.6 or less, and a total degree of substitution of 0.5 or greater and 2.8 or less.

The invention relates to the technical field of animal model construction, and particularly discloses a construction method of an atherosclerotic plaque thrombosis model. Comprising the following steps: 1) selecting carotid artery constricted ApoE- / -mice fed with high-fat feed; and 2) injecting LPS (Lipopolysaccharide) into the abdominal cavity to obtain the atherosclerotic plaque thrombosis animal model. The construction method provided by the invention is simple to operate and high in repeatability, atherosclerotic plaque thrombus formation can be induced under the stimulation of low-dose LPS, the thrombus occurrence rate equivalent to the thrombus occurrence rate in the prior art can be obtained, the construction method can be closer to the formation of atherosclerotic thrombus related to clinical endotoxemia, and the clinical pathological process can be better simulated.

Compositions and methods are provided for stabilization of RNA encapsulated by lipid nanoparticles during lyophilization. The compositions and methods involve the use of empty lipid nanoparticles to stabilize the lyophilized composition. These techniques may be used to prevent the need for cold chain storage and may also simplify the procedure at the clinic for reconstituting the vaccine to prepare an injectable composition.

A method, system, and device for ultra-low-dose imaging of oral cone-beam computed tomography (CBCT) are provided. The method encompasses high-dose oral CBCT image data acquisition, data segmentation processing, three-dimensional (3D) reconstruction processing, model training, image data input, image enhancement, and image data output. Specifically, the process involves performing 3D reconstruction on 2D projection data of oral CBCT acquired in ultra-low-dose mode to obtain ultra-low-dose oral CBCT 3D reconstructed image data. This ultra-low-dose oral CBCT 3D reconstructed image data is then input into the oral CBCT ultra-low-dose imaging enhancement network model, from which high-quality oral CBCT image data is output for subsequent clinical diagnosis and treatment processes. This method significantly reduces the radiation dose of imaging while ensuring imaging quality, accelerates imaging speed, and enhances the safety of oral CBCT imaging, holding broad clinical application prospects.

The invention provides a low-dose X-ray multi-contrast high-precision signal analysis method, and belongs to the technical field of deep learning and X-ray grating contrast imaging. Comprising the following steps: acquiring a grating stepping projection sequence under a low-dose condition; a convolutional neural network model is constructed, the model is composed of a contrast analysis module and a U-net, the contrast analysis module is used for extracting a contrast signal, and the U-net is used for further image enhancement and noise removal; training a convolutional neural network model; and obtaining high-quality absorption, phase and dark field projection by using a trained convolutional neural network model and utilizing a low-dose grating stepping projection sequence. According to the method, the physical information in the grating stepping projection sequence is extracted by using the convolutional neural network, so that the influence of noise introduced by low-dose X-rays on contrast signals can be reduced, the radiation dose borne by a sample is effectively reduced, the imaging quality is remarkably improved, and the application potential of X-ray grating differential phase contrast imaging is improved.

This invention discloses a method for detecting the toxicity threshold of a substance based on a rat drinking experiment. The method of this invention includes the following steps: First, a drinking preference experiment is conducted, and then the toxicity threshold is determined: the amount of substance water and pure water consumed in the drinking preference is compared to determine the time when the rat begins to significantly avoid substance water, the mass of the toxic substance in the rat's body at that time is calculated, and the toxicity threshold of the rat is calculated; (3) dose conversion from rat to human: based on the interspecies dose conversion of body surface area, the toxicity threshold of the rat is first converted into the equivalent dose for humans to obtain the acute exposure dose, and then the acute exposure dose is converted into the chronic exposure dose for humans to obtain the substance toxicity threshold. This invention can accurately determine the toxicity threshold: it achieves toxicity assessment of low-dose exposure through spontaneous recognition behavior; it is easy to operate; and it is applicable to the toxicity assessment and non-destructive threshold determination of various substances such as environmental pollutants, chemical substances, and drugs.

State of the art mechanisms being used for achieving diagnostic-quality images under low-dose settings for general CT imaging have the disadvantages that CT images are fixed during the optimization process to generate perfusion maps, which can lead to suboptimal CT images with respect to the perfusion maps generated, although they might appear spatially smooth or denoised. The disclosure herein generally relates to Computer Tomography (CT) scanning, and, more particularly, to a method and system for CT image reconstruction. The system performs modelling an optimization problem for joint estimation of a set of structural CT images and a perfusion map, and further solves the optimization problem for the reconstruction of the CT images of a subject.

The present disclosure provides an IL-6 formulation, comprising about 40 μg / mL to about 2 mg / ml IL-6, about 5 to about 15 mM histidine, about 5 to about 15 mg / mL glycine, about 40 to about 60 mg / mL trehalose, about 0.1 to about 0.3 mg / mL polysorbate 20, and about 1 to about 1000 μM DTPA, wherein the formulation has a pH of about 6.0 to about 8.0. Such formulations may be useful to treat and / or prevent a disease or disorder in a subject in need thereof.

The invention relates to a low-dose liquid-free detection system, which is used for a net type atomizer and comprises an acquisition unit, an analysis unit, a calculation unit, a data storage unit and an execution unit, the acquisition unit is used for acquiring current or voltage signals of an atomizing sheet in one or more periods and sending the current or voltage signals to the calculation unit; the calculation unit is used for acquiring the current or voltage signal sent by the acquisition unit, obtaining a change fitting curve of the current or voltage signal through differential operation, and sending data of the change fitting curve to the analysis unit; and the analysis unit is used for receiving the change fitting curve data sent by the calculation unit, comparing the change fitting curve data with the pre-stored threshold data of the atomization sheet in the data storage unit, carrying out final judgment on a liquid medicine atomization state or a non-liquid medicine atomization state, and sending a judgment result to the execution unit. The liquid-free detection system is suitable for low-dose atomization detection.

A system and method for creating multi-phase kidney computed tomography (CT) images of a patient are provided. The method includes acquiring or accessing CT data that includes a first dataset acquired from the patient during a first phase when a dose of a contrast agent is being excreted from a kidney of the patient and does not include a second dataset acquired from the patient during a second phase after the dose of the contrast agent is delivered but before the dose of a contrast agent is being excreted from a kidney. The method also includes using the first dataset, and without the second dataset, generating a set of multi-phase kidney images of the patient showing the patient prior to receiving the dose of the contrast agent, images showing the patient during the second phase following the dose of the contrast agent and before the dose of a contrast agent is being excreted from a kidney, and showing the patient during the first phase when the dose of a contrast agent is being excreted from a kidney of the patient. The method also includes communicating the multi-phase kidney images.