51 results about "Anatomic Location" patented technology

The invention provides an osteoporosis automatic diagnosis method and system based on position specific attention, and the method comprises the steps: carrying out the dual-channel enhancement preprocessing of a lumbar CT image, and generating an enhanced image taking the bone mineral density and the bone trabecula structure characteristics into consideration; inputting the enhanced image into a deep convolutional neural network for multi-scale feature extraction to obtain a feature map containing spatial semantic information; on the basis of the anatomical position index information, generating attention weighted features which highlight the key diagnosis area of the vertebral body; global pooling is carried out on the attention weighted features, and then comprehensive diagnosis features containing anatomical priori knowledge are constructed; and inputting the comprehensive diagnosis features into a classifier to realize centrum-level accurate diagnosis. According to the invention, the workload of radiologists can be effectively relieved, and the efficiency and coverage of osteoporosis screening can be improved. Especially under the condition that primary medical institutions are lack of experienced radiologists, the primary medical service level can be improved.

The present disclosure provides a method for assessing cardiorespiratory health. The method comprising: generating mechanical movement data associated with a torso of a subject's body using a plurality of ballistocardiography (BCG) sensors; filtering the mechanical movement data to extract respiratory signal waveforms and heart signal waveforms; decomposing the respiratory signal waveforms into thoracic, diaphragmatic, and abdominal breathing components based on waveform characteristics and anatomical location of the plurality of BCG sensors; analyzing phase differences between the thoracic, diaphragmatic, and abdominal breathing components over time to quantify a degree of synchrony or asynchrony; evaluating relative contributions of thoracic, diaphragmatic, and abdominal breathing components to an overall breathing effort; identifying a breathing abnormality based on the analysed phase differences and the evaluated relative contributions; and detecting a potential cardiorespiratory condition based on the identified breathing abnormality.

A stabilizer sleeve is disclosed for use with cardiac implantable electronic device leads. The sleeve comprises a tubular body sized to receive the lead and shaped to bias the lead toward a desired anatomical location, thereby reducing migration, dislodgement, and interference with cardiac structures. The sleeve may be introduced with the lead as a unitary assembly or added after lead placement. Various embodiments include a slitted body for expansion, radiopaque markers for visualization, detachable nose-cone tips for guidewire tracking, and antimicrobial coatings. The sleeve may be formed of polymers, alloys, or composite materials, and may include features such as texturing or anchoring projections for tissue engagement. Applications include positioning within a tricuspid valve commissure to minimize regurgitation and stabilizing left ventricular leads within branches of the coronary sinus. The device and methods described provide improved long-term stability and performance of implanted cardiac leads.

The invention particularly relates to a neural decoding method based on multi-scale electroencephalogram signals and heterogeneous visual stimulation alignment, which comprises the following steps: firstly, performing frequency domain transformation, processing and inverse mapping on original EEG signals through an FADE module to effectively integrate frequency specific information; then, the signals are input into an ACC module, and the module achieves self-adaptive multi-channel relation modeling based on a functional relation instead of a fixed anatomical position through a dynamic clustering center and a cross attention mechanism; then, the encoded EEG features and CLIP visual features are subjected to alignment training under a joint loss function, and the loss function optimizes the semantic fidelity and discrimination of the features at the same time; finally, the EVA frame obtained through training can be used for heterogeneous visual stimulation decoding tasks such as zero-sample image retrieval, video classification and high-quality image reconstruction. According to the method, the capture capability of the EEG features on visual semantic information and the generalization of the model can be effectively improved, and the challenge of multi-scale and multi-modal neural decoding is solved to a certain extent.

In some embodiments, disclosed herein are systems and methods of treating a patient that can include the steps of accessing the sphenopalatine fossa, and cannulating the inferior orbital fissure from the sphenopalatine fossa to access the retro-orbital space. The sphenopalatine fossa can be accessed via various routes, including percutaneously. Accessing the sphenopalatine fossa can include the step of inserting a needle-catheter system into the sphenopalatine fossa. Integrated needle-catheter systems as described herein can also be configured to access the trigeminal ganglion, epidural space, intrathecal space, and other desired anatomical locations.

The application provides a key frame extraction and report generation method for a light reflection-oriented endoscopic video, comprising: evaluating the aggregation degree of the visible arc length at the lesion edge, determining the attention priority order of the lesion edge area according to the aggregation degree; dynamically adjusting the key frame screening condition by combining the attention priority order with the contour concave-convex degree, preferentially retaining the image frames with obvious local morphology of the lesion, and obtaining a candidate key frame set; positioning the abnormal area in each frame according to the candidate key frame set, matching the abnormal area with a reference template of an anatomical position description, and evaluating the specific position of the abnormal area in the anatomical structure; combining the anatomical position description and the abnormal area positioning information according to the final output key frame combination, generating a structured endoscopic video analysis report, and completing the lesion identification and description task under the interference of light reflection.

The application discloses a kind of lung edema and pneumothorax identification and quantitative evaluation device based on multi-modal flexible ultrasound, the method is by synchronously obtaining the morphological ultrasound image and the elastic mechanics image of the same anatomical position, B line quantitative index, pleural line sliding index and the average strain value of region of interest are extracted from morphological ultrasound image and elastic mechanics image;B line quantitative index, pleural line sliding index, average strain value are combined into feature vector, feature vector is input into multi-parameter fusion decision model, obtains lung edema index and pneumothorax risk probability;Lung edema index and pneumothorax risk probability are displayed in display terminal, and when lung edema index exceeds preset index threshold or pneumothorax risk probability exceeds preset probability threshold, alarm is triggered;It can reduce the misdiagnosis rate under emergency scene, reduce end-to-end response time, provide objective, real-time, quantifiable decision support for clinician, significantly reduce the risk of missed diagnosis and improve emergency treatment efficiency.

The utility model discloses a multifunctional enemator for treatment, and relates to the technical field of medical nursing appliances, in particular to the multifunctional enemator for treatment, which comprises a liquid medicine bag, a liquid medicine box, a connecting tube and an anal tube, and the anal tube is connected with the liquid medicine bag and the liquid medicine box through a Y-shaped connecting tube; the liquid medicine box comprises a liquid medicine shell and a metering pump, and the metering pump is provided with an adjusting valve. The utility model has the advantages that the two enema liquid containers with different capacities can be respectively suitable for the operations of large-amount non-retention enema, retention enema and small-amount non-retention enema, and the Y-shaped enema design can meet the requirements of pipe washing before and after medicine use during retention enema, ensure the accuracy of the medicine use and avoid the waste of the liquid medicine. The optimized design of the anal tube can reduce stimulation and friction force of enema to the anus, the depth of the anal tube entering the intestinal tract and the anatomical position of the anal tube entering the intestinal tract can be visually judged, and the accuracy and safety of treatment are improved. The operation process is simplified, and the workload of medical staff is reduced.

An endolumenal robotic system provides the surgeon with the ability to drive a robotically-driven endoscopic device to a desired anatomical position in a patient without the need for awkward motions and positions, while also enjoying improved image quality from a digital camera mounted on the endoscopic device.

The invention belongs to the technical field of waist protection back cushions, and particularly relates to an intelligent waist cushion. In the acquisition mechanism, first to sixth sensor groups corresponding to an erector spine muscle monitoring area, a squarely lumbar muscle monitoring area, a multifidus muscle monitoring area, a pelvic floor muscle monitoring area, a diaphragm muscle monitoring area and a transverse abdominal muscle monitoring area respectively acquire pressure data of corresponding muscle groups; and the control module receives the data, analyzes and processes the data, and then drives corresponding parts of the supporting part to act according to an analysis result, so that targeted supporting adjustment on specific fatigue muscles is realized. The intelligent waist pad has the advantages that the sensor layout accurately corresponds to the anatomical position of the core muscle group of the waist of the human body, the crossing from regional pressure monitoring to muscle-level accurate recognition is realized, so that a reliable data basis is provided for accurate adjustment of the intelligent waist pad, and the effectiveness of support and the comfort level of a user are remarkably improved.

The application discloses a positioning guide and an additive manufacturing method thereof. The positioning guide is used for hip arthroplasty and comprises a positioning base, a main guide structure and first and second guide piles arranged on both sides of the main guide structure. The positioning base comprises first and second fitting parts respectively fitted with local bony surfaces on both sides of a patient's acetabular notch and a connecting part connecting the first and second fitting parts. The main guide structure is arranged on the connecting part and has a guide channel for accommodating a handle of a surgical tool to exert geometric constraint on a placement direction of an acetabular reamer tool. The guide channel is determined according to an acetabular cup designed to a target anatomical position and a simulation handle arranged in association with the acetabular cup. The first and second guide piles are used for guiding the arrangement of Kirschner wires to fix the positioning guide to the acetabular region of the patient, thereby improving the accuracy and stability of acetabular polishing and acetabular cup implantation.

The application discloses a method for identifying gastric anatomical structure based on magnetic control capsule endoscopy image of deep learning, screening the pictures output by the magnetic control capsule endoscopy detection, classifying according to the anatomical position, expanding the data set, and dividing into a training set and a test set; constructing, training and testing a multi-scale fusion pyramid visual Transformer network and a target detection network with an attention module, after the test, using the multi-scale fusion pyramid visual Transformer network to extract the global features of the image from the gastric magnetic control capsule endoscopy image, and classifying the magnetic control capsule endoscopy image; using the target detection network with the attention module to locate the classified pictures and identify the gastric anatomical structure. The application solves the problem of low resolution of the magnetic control capsule endoscopy examination pictures in the prior art, and can accurately identify the gastric anatomical position, further achieving the purpose of positioning the magnetic control capsule endoscopy in the stomach.

The invention relates to the technical field of medical instruments, in particular to a telescopic protective sleeve used under an endoscope and an installation method of the telescopic protective sleeve. The telescopic protective sleeve comprises a protective sleeve main body and an adjusting part, one end of the protective sleeve main body is provided with a duck tongue, and the other end is connected with the adjusting part; and under the control of the adjusting part, the protective sleeve main body can axially move relative to the endoscope so as to adjust the relative extension amount of the duck tongue and the front end of the endoscope. Axial sliding of the protective sleeve body is achieved through the lead screw pair and other structures so that the relative extension amount of the duck tongue can be changed, the protective sleeve can adapt to different anatomical positions without replacing the sleeve, the number of times of instrument replacement in an operation is reduced, the operation time is shortened, and the sealing structure can stabilize intraendoscopic perfusion pressure and avoid liquid backflow and pollution risks.

The present application relates to a digital twin driven perioperative nursing scheme dynamic optimization method, sets an intervention sensitive area associated with the current postoperative state of the patient, and limits the physical limit conditions of the nursing operation trigger threshold according to the operation type and anatomical position of the patient; the time period from the completion of the operation to the recovery of the related physiological indicators to the steady state is set as the impact period, and other nursing tasks that produce physical effects on the same area or its physiologically related areas are prohibited from entering the execution sequence; a damping feedback component is embedded in the nursing feedback channel of the digital twin, and when the change rate is higher than the preset physiological tolerance threshold, a rhythm slowing mechanism is started to adjust the execution rhythm of the subsequent tasks; an artificial operation behavior monitoring node is set in the nursing terminal or the bed area; based on the data collected by the monitoring node, an execution behavior deviation judgment unit is constructed for comparison with the system recommended path to identify the implicit correction behavior of the system strategy.

An emergency cardiac and electrocardiogram (ECG) electrode placement device with artificial intelligence is disclosed herein. The emergency cardiac and electrocardiogram (ECG) electrode placement device incorporates electrical conducting materials and elastic material into a pad that is applied to a chest wall of a patient, which places multiple electrodes in the appropriate anatomic locations on the patient to quickly obtain an ECG in a pre-hospital setting. The AI program continuously runs EKGs to continuously monitor a patient.

The application relates to the technical field of neck braces, and particularly provides a neck flexible fixing brace design method and system, the neck flexible fixing brace design method comprises the following steps: obtaining individual neck three-dimensional shape data; identifying a key anatomical position of the neck according to the individual neck three-dimensional shape data, and designing a flexible fixing brace according to the individual neck three-dimensional shape data to obtain a first flexible fixing brace preliminary design scheme; obtaining skin physiological parameters of the key anatomical position of the neck; and adjusting the first flexible fixing brace preliminary design scheme according to the skin physiological parameters to obtain an individualized flexible fixing brace design scheme; the method can significantly improve the adaptability, wearing comfort and safety of the neck flexible fixing brace and the neck of a patient.

The present application relates to the technical field of digital image processing, in particular to a tumor interstitial proportion quantitative evaluation system based on pathological images. The present application automatically obtains tumor epithelial region, tumor interstitial region, tumor region and tumor infiltration front region based on image segmentation, without pre-selecting histological evaluation position for visual evaluation by artificial selection, avoiding the subjective experience dependence of traditional methods, and improving the efficiency of tumor interstitial proportion evaluation. In addition, the present application comprehensively quantitatively evaluates the first tumor interstitial proportion under the overall scale of the to-be-tested pathological image, the second tumor interstitial proportion under the scale of the tumor infiltration front region and the third tumor interstitial proportion under the scale of the tumor region, and finally obtains the tumor interstitial proportion score value which can reflect the tumor interstitial proportion characteristics of different anatomical positions, further improving the accuracy of the evaluation result. The preset rule is to select the window tumor interstitial proportion with the highest tumor interstitial proportion value.

Methods, systems, and apparatus, including computer programs encoded on computer storage media for treating medical conditions such as neurological disorders. A user device can be used to communicate with a user and can be used to control a treatment device. The treatment device can be an ear pressure treatment device. The system can execute treatment parameter profiles, and selection of the treatment parameter profiles can depend, at least in part, on feedback provided by the user, such as via the user device. One, two, or more nerves associated with target anatomical locations (e.g., one or both ears) can be stimulated. Some embodiments involve combination therapy including stimulating one or more nerves associated with at least one ear with a first stimulus modality, and a second stimulus modality that is the same as, or different from the first stimulus modality.

A dental prosthetic positioning assembly comprises an occlusal assembly and a maxillary arch subassembly. The occlusal assembly includes a maxillary tray configured to be formed in a patient's maxillary alveolar ridge, wherein the maxillary tray comprises a occlusal rim component. The occlusal assembly further includes a carriage frame component composed of biocompatible magnetic metal material anchored to the maxillary tray. The maxillary arch subassembly comprises a plurality of prosthetic maxillary teeth components magnetically anchored to the occlusal rim component. The carriage frame component is moveable with respect to the maxillary tray. The prosthetic maxillary teeth components are individually moveable with respect to each other to achieve a desired dental positioning.

The invention relates to a heart magnetic resonance dynamic image analysis method and system. Acquiring heart magnetic resonance dynamic image data; establishing multiple types of anchor point marks in the initial heart magnetic resonance dynamic image data; and analyzing and detecting the heart magnetic resonance dynamic image data on which the multiple types of anchor point marks are established, and triggering an anchor point correction process to correct the abnormal anchor point marks when analyzing and detecting that the anchor point marks are abnormal. According to the method, the multi-type anchor point marks including the anatomical anchor point mark, the functional anchor point mark and the texture anchor point mark are established, so that the deviation can be automatically corrected based on a multi-type anchor point cooperative tracking mechanism when body movement interference occurs in the process of analyzing the cardiac magnetic resonance dynamic image data, and the accuracy of the cardiac magnetic resonance dynamic image data is improved. The anatomical position accuracy of myocardial segment marking is ensured, so that the requirement of manual re-marking is avoided, and the efficiency and reliability of cardiac function quantitative analysis are improved.

The invention provides a multi-modal health data feature extraction method and system, and relates to the technical field of medical data processing, and the method comprises the steps: obtaining a multi-modal health data set which comprises time sequence physiological data, image data and text data; performing random noise processing on the time sequence physiological data to extract blood pressure fluctuation characteristics; based on the blood pressure fluctuation characteristics, performing structural noise processing on the image data to extract morphological characteristics of the fundus blood vessels; in the process of extracting the morphological features of the fundus blood vessels, dynamically positioning three feature anchor points on a fundus image corresponding to the image data; the anatomical positions of the three characteristic anchor points are respectively an optic disc edge upper quadrant reference point, a macular region bitamporal trunk blood vessel bifurcation core point and an arteriovenous cross indentation center point; and constructing a dynamic response area based on the three feature anchor points. The cardiovascular event risk assessment precision can be improved.

The method of the present application obtains a chest X-ray image and corresponding text description information, extracts the anatomical position information related to the lesion or abnormality from the text description information, and constructs the region constraint information corresponding to the image space based on the anatomical position information. The chest X-ray image, text description information and region constraint information are input into a visual positioning model to output the target region positioning result corresponding to the text description semantics. The visual positioning model is trained in a semi-supervised learning manner, and a training framework of a teacher model and a student model is introduced in the training process. The region constraint information is used to screen, weight or constrain the candidate positioning results generated in the unannotated samples, so as to improve the quality of the pseudo labels and thus improve the accuracy and stability of the target region positioning.

The utility model discloses a stomach tube device with a positioning function, which belongs to the technical field of medical devices and comprises a stomach tube component, a control switch, a positioning emitter, a check valve, a fixing device and an insertion tube, the stomach tube component comprises an outer tube, a connecting line and an inner tube, the connecting line and the inner tube are fixedly mounted in the outer tube, the connecting line is positioned on one side of the inner tube, and the inner tube is positioned on the other side of the inner tube. One end of the connecting wire is electrically connected with the control switch, the other end of the connecting wire is electrically connected with the positioning emitter, and the fixing device is connected with the outer end of the outer pipe. Through circuit connection formed by the positioning emitter, the connecting line and the control switch, the positioning emitter can be controlled to emit sound waves, the sound source can be heard when the stethoscope is placed on the surface of the body, the position where the front end of the stomach tube reaches can be judged according to different anatomical positions, and due to the fact that the trachea and the esophagus are far away from each other, the positioning emitter can be controlled to emit sound waves. Whether the front end of the stomach tube enters the airway by mistake can be judged, and a patient is prevented from aspirating by mistake and suffocating.

The invention provides a bone plating system provides combined bone fixation and adjustable soft-tissue reattachment through an integrated, knotless tensioning construct. The system includes a bone plate having screw holes for bone fixation and one or more integrated suture pathways formed by holes, tunnels, or slots that guide a flexible member through the plate. The flexible member includes a series of integrally formed loops spaced along its length, each configured to engage a cleat or anchor feature on the bone plate. Engagement of a selected loop enables the surgeon to apply and maintain a desired level of soft-tissue tension without manual knot-tying. The cleat or anchor may incorporate a hook-and-ramp or snap-fit design that provides self-locking engagement under physiological loading. The system allows reproducible, incremental tension control, reduces operative time, and enables low-profile, knotless fixation adaptable for various anatomical locations including the ulna, patella, and humerus.

The invention discloses a structured report generation method and device, electronic equipment and a computer program product. The method comprises the following steps; acquiring image data obtained by a patient through medical examination and an original report corresponding to the image data; the original report is preprocessed to obtain a report to be processed, and the report to be processed can be recognized by a preset multi-modal model; taking the image data as a reference, performing information extraction on the to-be-processed report through the multi-modal model to obtain candidate triple information, the triple information comprising at least one of the following elements: a disease name, an abnormal sign and an anatomical position; retrieving in a preset medical library on the basis of the candidate triple information, so as to obtain standardized triple information according to a retrieval result; and generating a structured report according to the standardized triple information. According to the method and the device, the accuracy and the consistency of the structured result can be improved when the image report is subjected to structured processing.

The invention relates to the technical field of medical image processing and three-dimensional visualization, and discloses a human body tomographic anatomical image three-dimensional visualization reconstruction method and system. The method comprises five steps of interlayer registration and gray normalization, multi-organ semantic segmentation based on an anatomical position attention module, surface-volume hybrid three-dimensional reconstruction, interactive virtual anatomy layer-by-layer stripping visualization and anatomical knowledge graph driving labeling, and a segmentation module sends a quality feedback signal to a registration module to form closed-loop cooperation. And a reusable digital three-dimensional anatomy resource is provided for anatomy teaching in medical colleges and universities.

The invention relates to the technical field of digital image processing, in particular to a tumor interstitial proportion quantitative evaluation system based on pathological images. According to the method, the tumor epithelium region, the tumor interstitial region, the tumor region and the tumor infiltration leading edge region are automatically obtained based on image segmentation, a histological evaluation position does not need to be manually selected in advance for visual evaluation, the subjective experience dependence of a traditional method is avoided, and the efficiency of tumor interstitial proportion evaluation is improved. Besides, quantitative evaluation is carried out by synthesizing the first tumor interstitial proportion under the overall scale of the pathological image to be detected, the second tumor interstitial proportion under the tumor infiltration leading edge area scale and the third tumor interstitial proportion under the tumor area scale; the finally obtained tumor interstitial proportion score value can reflect the tumor interstitial proportion characteristics of different anatomical positions, and the accuracy of the evaluation result is further improved. Wherein the preset rule is to select the window tumor interstitial proportion with the highest tumor interstitial proportion value.

A wearable cardiac monitoring device for providing an improved fit to a body of a patient during long term cardiac monitoring of the patient is provided. The device includes a garment configured to be worn about a torso of the patient and including a flexible material and physiological sensors configured to detect a physiological signal of the patient, the physiological sensors disposed on the flexible material and positioned at one or more anatomical locations of the patient's torso. The device also includes force applicators disposed on the flexible material proximate to the one or more physiological sensors, each of the force applicators configured to be adjustable during the long term cardiac monitoring of the patient to cause a pressure in a range of 0.05 psi to 0.65 psi to be exerted by the physiological sensors onto the one or more anatomical locations of the patient's torso.

The invention provides a paranasal sinus bone structure medical image segmentation system based on Mamb-UNet, and relates to the technical field of medical image processing.The paranasal sinus bone structure medical image segmentation system comprises the steps that firstly, a low-resolution global abstract graph is extracted, original features are injected, and a local extractor is endowed with context sensing capacity; and the bone slices with similar forms and different meanings can be distinguished according to anatomical positions, so that false alarms are remarkably reduced. The invention aims to ensure that the boundary of the segmented bone structure is clear by introducing a gating type bidirectional fusion mechanism and dynamically arbitrating the weights of forward and backward information streams by utilizing a learnable gating unit. According to the method, a hierarchical parallel Mama (H-Mama) architecture is designed, and parallel multi-scale feature extraction of features is realized in the same feature level. By operating high-frequency, intermediate-frequency and low-frequency branches in parallel, the model can capture fine bone wall details and macroanatomical layout simultaneously without compromise so as to adapt to violent size changes.