9 results about "Vascular structure" patented technology

The application relates to a kind of neural puncture dynamic obstacle avoidance navigation method and system based on multi-modal image fusion, belong to medical image navigation and surgical operation technical field, by fusing preoperative high-resolution static image and intraoperative real-time dynamic ultrasound data, construct unified space-time reference model, and utilize artificial intelligence technology to automatically segment and reconstruct the three-dimensional model of key neural vascular structure, can be based on real-time image data dynamic calculation optimal puncture path and real-time monitoring collision risk in the process of needle insertion, provide multi-sensory fusion intuitive navigation guide for operator through augmented reality technology, through recording and analyzing the whole process data of operation, utilize big data platform to continuously iterate optimization to segmentation and obstacle avoidance algorithm, form self-improving intelligent closed loop.The application effectively solves the problems that traditional neural puncture surgery depends on the experience of operator, cannot real-time dynamic obstacle avoidance and system lacks learning ability, significantly improves the precision, safety and intelligent level of operation.

A method of providing vascular effects includes emitting infrared light toward a body part of a guest, receiving the infrared light from the body part of the guest, generating a signal indicative of the received infrared light, generating a set of coordinates corresponding to a vascular structure of the body part of the guest based on the signal indicative of the received infrared light, mapping the vascular structure to the body part of the guest, retrieving a portion of code representing a sprite, generating a series of images of the vascular structure of the body part of the guest and the sprite, and projecting the series of images of the vascular structure and the sprite onto the body part of the guest.

This invention discloses a method and device for cerebral artery segmentation and classification based on MRI images, belonging to the field of medical image processing. The method uses a U-Net network as its basic architecture, introducing a Swing Transformer module in the encoder to achieve hierarchical feature extraction. First, the 3D MRI image is preprocessed; then, multi-scale features are extracted through a multi-level Swing Transformer encoding stage, and a shift-window attention mechanism is combined to enhance global context awareness; next, a graph structure is constructed to fuse and enhance multi-level features to preserve vascular topology; finally, a convolutional decoder upsamples layer by layer and performs skip connections with the graph fused features to achieve accurate reconstruction and classification of vascular structures. This invention effectively integrates the global modeling capabilities of the Transformer with the local detail extraction advantages of convolutional networks, improving the accuracy and structural integrity of vascular segmentation and classification.

The application discloses a method and system for jointly performing photoacoustic-ultrasound depth resolution multilayer craniocerebral microvessel imaging, and the method comprises the following steps: firstly, threshold processing is performed on the amplitude of collected photoacoustic-ultrasound data; secondly, a single pixel value on a scanning plane is cross-correlated with an ultrasonic echo signal of a reference glass to determine the outer surface of the skull, the process is repeated for all scanning points, and the inner surface of the skull is identified in combination with a photoacoustic image; the inner and outer surfaces of the skull in a selected region on the skull are manually segmented using the above information, the average skull thickness is calculated, then a skull angle correction uniform model is established, and the effective thickness of the skull is calculated; finally, the effective thickness of the skull is used to perform depth layer imaging on craniocerebral microvessels in a photoacoustic image. Based on the application, a fine craniocerebral microvessel network image can be obtained, which is helpful for the analysis of craniocerebral vascular structure and can be expected to be used in the field of medical image analysis.

The present application relates to the technical fields of magnetic resonance and medicine, and discloses a magnetic resonance-based vascular structure analysis method and apparatus, a computer device, and a storage medium. The method comprises: acquiring a first T2 relaxation time and a second T2 relaxation time, wherein the first T2 relaxation time is a T2 relaxation time obtained by performing nuclear magnetic resonance imaging using an SE sequence, and the second T2 relaxation time is a T2 relaxation time obtained by performing nuclear magnetic resonance imaging using a GE sequence; performing calculations on the basis of the first T2 relaxation time and the second T2 relaxation time, and determining an average radius of blood vessels and microvascular density within lesion tissue; and performing medical analysis on the basis of the average radius of blood vessels and the microvascular density. Hence, the average radius of blood vessels and the microvascular density within the lesion tissue can be provided and subsequently analyzed, thereby enabling evaluation of the vascular condition of the lesion tissue and quantitative analysis of vascular changes in regions surrounding the lesion tissue, facilitating comprehensive treatment effects, and improving the accuracy of early tumor diagnosis.

This invention relates to the field of image processing technology, specifically to an automated intracranial aneurysm detection system based on CT images. The system includes: analyzing all local regions of each vascular segment based on vascular CT images to obtain the probability of local vascular abnormalities; identifying potential abnormal bulging regions based on these probabilities; further obtaining candidate regions for the vascular segment and candidate regions for bifurcation points; obtaining a first aneurysm probability based on the degree of protrusion and perpendicularity of the growth direction of the candidate regions, and distinguishing between physiological curvature and aneurysm regions based on the first aneurysm probability; calculating a second aneurysm probability based on the positional difference value and sphericity matching degree of the candidate regions for bifurcation points, and distinguishing between natural bulges at bifurcation points and aneurysm regions based on the second aneurysm probability. By analyzing different morphologies and structures of intracranial vessels, the system distinguishes between normal vascular structures and aneurysm regions, thereby achieving accurate identification of intracranial aneurysms.

According to the present invention, one or more image pairs, each consisting of a fluoroscopic image and an angiographic image taken from the same position and the same viewing direction onto the patient and each being a non-stitched image, are acquired. A live fluoroscopic image is registered individually with the fluoroscopic image within the at least one of the one or more image pairs, such that the spatial relationship between the live fluoroscopic image and the at least one fluoroscopic image, and thus with the one or more angiographic images and the one or more image pairs in general, becomes known. Angiographic information representing the vascular structure can then be taken from those parts of the angiographic images within the one or more image pairs which overlap with the live fluoroscopic image and be overlayed over the live fluoroscopic image.

The invention discloses a cardiovascular disease risk prediction method based on retinal vascular structure bidirectional modulation guided by clinical information, and relates to the problem that in cardiovascular disease risk assessment, an existing method is difficult to effectively fuse retinal vascular structure features and non-invasive clinical indexes and describe abnormal differences of vascular forms in different crowd subgroups. Retinal vascular structure change is an important premature number of cardiovascular diseases, but a single-mode risk prediction method is difficult to represent an association relationship between vascular form information and clinical indexes. Therefore, the invention provides a cardiovascular disease risk prediction method for retinal vascular structure bidirectional modulation based on clinical information guidance. According to the method, the blood vessel morphological anomaly characterization capability is improved through blood vessel marker modeling guided by medical knowledge, and effective fusion of retinal blood vessel features and clinical features is realized through two-way modulation of subgroup perception and a cross-modal alignment mechanism guided by a prototype. The method can be used for risk assessment and early prediction of cardiovascular diseases.

The utility model relates to the technical field of medical instruments, and provides a limited aorta covered stent which comprises a stent body, the stent body is formed by weaving metal wires and is a hollow net-shaped cylinder, net-shaped intersections of the stent body are fixed through welding, the outer wall of the stent body is connected with a covering film through a connecting assembly, and the covering film is connected with the stent body through the connecting assembly. In order to cover lesions of multiple angles and quadrants, identification marks are arranged on the periphery of the covering film, the inner peripheries of the identification marks are fixedly connected with the outer periphery of the frame body, and 8 marks are arranged on the outer peripheries of the identification mark at the left end and the identification marks at the front end and the rear end. Through local film covering, on the premise that circulation of branch blood vessels is not hindered on the basis of a stent hollowed-out structure, the blood vessel crevasse is effectively blocked; extra windowing and branch stent positioning are not needed, so that the stent is simple in structure, easy to operate, free of customization and applicable to aorta and branch vascular structures of various different physiological structures, and flexibility and convenience of the stent are greatly improved.