12 results about "Anatomical sites" patented technology

The application provides a wearable portable hairband for mental fatigue detection and intervention, a flexible conductive polymer dry electrode is embedded in the inner side of the hairband, the dry electrode is attached to the scalp through mechanical pressure, and thus inductive collection is realized without conductive paste; the output end of the dry electrode collection signal is directly connected to a collection front end located at the side edge of the hairband through FPC, the front end is integrated with an amplifier and an analog-to-digital converter, weak electrical signals on the cerebral cortex are amplified and converted into a data format; a SoC chip is selected as a processor to build a full-integrated edge computing platform inside the flexible fabric hairband, and the calculation task of mental fatigue detection is sunk to the hairband end; an ultrathin bone conduction unit is used as an acoustic output component, which is connected through a flexible circuit and embedded in the inner side of the hairband corresponding to the anatomical site of the user's temple, when the mental fatigue detection result triggers the fatigue warning threshold, a binaural rhythm intervention module is activated to perform binaural rhythm intervention. The application can perform mental fatigue detection and intervention.

This invention discloses an injection method for CaHA microsphere products that enhance facial three-dimensionality through multi-layering, relating to the field of cosmetic technology. The method includes: precise injection techniques and area division based on specific needs; and a combination of needle angle, injection depth, layer, and dosage for specific anatomical locations. Specifically designed for Asian facial structures, it provides a strong, naturally integrated solution. By using CaHA microsphere injection products, the following effects can be achieved: Facial volume replenishment: effectively replenishing facial soft tissue atrophy and fat loss caused by aging, skin aging, or genetic factors, restoring facial fullness. It is commonly used to fill sunken areas of the face, such as tear troughs, nasolabial folds, sunken temples, and sunken cheeks.

This invention relates to a bipolar adjustable plasma electrode, comprising: an electrosurgical head; two first tubes, the electrosurgical head spanning between the two first tubes, and the first tubes containing a high-temperature resistant wire that is in contact with and conductive to the electrosurgical head; a second tube connected to the end of the two first tubes away from the electrosurgical head, and the first and second tubes being rotatably coupled; and a third tube containing a phosphor bronze rod, the phosphor bronze rod being electrically connected to a plug via a cable. Only a brief energization of the heating wire is needed to melt the phase-change conductive material, allowing easy adjustment of the angle between the two first tubes, thereby changing the shape of the electrosurgical head to adapt to different anatomical sites or surgical approaches. The frictional force between the first and second tubes maintains the shape of the electrosurgical head in the absence of external force. After power is cut off, the phase-change conductive material rapidly solidifies, locking the relative positions of the high-temperature resistant wire and the phosphor bronze rod.

This invention discloses a method for generating virtual ultrasound images from magnetic resonance images based on a physics-guided Transformer adversarial network, belonging to the field of medical imaging diagnostic technology. The method includes: acquiring three-dimensional magnetic resonance images and real ultrasound images of the same anatomical location to construct a training dataset; building a dual-branch generator containing a semantic coding branch, an acoustic physical simulation branch, and a feature fusion decoder; the semantic coding branch extracts global anatomical features, and the acoustic physical simulation branch generates physical prior features; combining a dual-domain discriminator with a hybrid objective function containing adversarial and perceptual losses for end-to-end joint training; inputting the magnetic resonance image to be processed into the trained generator; and outputting a virtual ultrasound image for medical diagnosis after dual-branch collaborative processing. This method overcomes the shortcomings of traditional methods, such as insufficient physical consistency and poor feature fusion effects. The generated virtual ultrasound image possesses both anatomical accuracy and texture realism, providing reliable support for clinical diagnosis and related medical scenarios.

The application discloses a training method and device of a prediction model and a processor. In the case, a training sample set is obtained; anatomical site entities extracted from medical text data of multi-modal medical data of the training sample are mapped to corresponding spatial anchor points in a medical image coordinate system, a spatial bias matrix is constructed by an initial prediction model according to spatial distances between the spatial anchor points and image blocks of the medical image data; the model performs cross-attention fusion on the medical image data and the medical text data according to the spatial bias matrix to obtain an image-text fusion feature sequence, generates a prediction result according to the feature sequence and structured inspection data; and parameters of the initial prediction model are adjusted based on differences between the prediction result and a real label to obtain the prediction model. The application solves the technical problem of low prediction accuracy of the model caused by insufficient utilization of complementary information between multi-modal data in the prior art, and improves the auxiliary value of the prediction result for drug use and treatment of medical workers.

This invention relates to the fields of computer vision and medical image processing technology, and discloses a method for extracting lesion structures from cardiac magnetic resonance imaging (MRI) images based on deep learning. The method first retrieves dynamic cardiac cine sequences and delayed gadolinium-enhanced sequences from the same anatomical location, extracts the centroid trajectory of the left ventricular blood pool, and performs cross-sequence axial alignment and non-rigid deformation correction. Subsequently, a local orthogonal coordinate system based on the myocardial anatomical topology is constructed, and pixel-level motion vector fields with physical constraints are calculated in the dynamic cardiac cine sequences. By projecting the motion vectors onto the local orthogonal coordinate system and performing vector clipping according to the centripetal contraction physical constraint, an effective motion vector field is generated. Finally, dynamic features and image grayscale features are fused, and a logic gating operator is used to extract the lesion structure mask.

The application relates to the technical field of impact biomechanics and human engineering, in particular to a biomechanics response mapping method and device, an electronic device and a medium. The mapping method comprises the following steps: acquiring first information, wherein the first information comprises source body type biomechanics response channel data, body type parameters of a source body type and body type parameters of a target body type; constructing a regionalized dynamics mapping relationship according to a dynamics dominant mechanism of an impact response; the mapping relationship is used for representing the relationship among the body type parameters of the source body type, the body type parameters of the target body type, the biomechanics response channels of each anatomical region of the source body type and the biomechanics response channels of each anatomical region of the target body type; and determining the biomechanics response channel data of each anatomical region of the target body type according to the regionalized dynamics mapping relationship and the first information. The application can realize the effect that each anatomical part simultaneously meets the physical consistency requirement and the scaling result has high reliability.

This invention relates to the field of medical device technology and discloses an intelligent microneedle implantable sensing device and its monitoring method for real-time monitoring of intervertebral disc degeneration. The device includes a sensor assembly, sensor circuitry, a wireless communication module, and a signal processing device. The sensor assembly is integrated onto an implantable carrier. The sensor assembly includes a pressure sensor, an inflammatory factor detection sensor, and pH and ROS sensors. This intelligent microneedle implantable sensing device and its monitoring method for real-time monitoring of intervertebral disc degeneration utilizes an integrated sensor assembly design and a multi-dimensional synchronous sensing setup encompassing "mechanics-inflammation-oxidative stress" to achieve simultaneous acquisition of intervertebral disc pressure, inflammatory factors, pH value, and ROS levels at the same anatomical site. The signal processing device can then depict the complete dynamic evolution trajectory from early mechanical instability to later inflammatory outbreaks.

The present application relates to the technical field of medical thrombus prevention equipment, in particular to a lower limb intelligent pressure regulating elastic sock integrated with ultrasonic monitoring and a working method thereof, which comprises a medical elastic sock body and further comprises: a plurality of patch ultrasonic transducer units, which are correspondingly arranged in a plurality of internal fixing cavities of the medical elastic sock body and are sequentially arranged from top to bottom along the anatomical sites of the main trunk veins of the lower limbs of human bodies, and the sound window surfaces of the patch ultrasonic transducer units are all attached to the skin through coupling gel, and are used for non-invasive quantitative collection of ultrasonic echo signals of lower limb venous hemodynamics. The present application realizes efficient and safe prevention through innovative closed-loop linkage, differentiated driving and precise controllable pressurization. Taking the ultrasonic monitoring quantitative blood flow index as the core trigger signal, the present application breaks through the technical barriers of traditional ultrasonic diagnosis and passive prevention of elastic socks, constructs an integrated closed loop of "monitoring-early warning-intervention", dynamically adapts the risk level, and significantly improves the timeliness and accuracy of prevention.

An image classification apparatus for an endoscope has a site determination section that determines an anatomical site in a human body based on a succession of captured images obtained during insertion or withdrawal of an endoscope into or from the body, a feature determination section that determines features of the determined site, i.e., each site feature, for one or more determination items to obtain each site feature information, and a correlation section that records each site's each site feature information in association with the captured images.

The present application relates to otoscope image intelligent diagnosis technical field, especially to an otoscope image open set quality control method, comprising the following steps: constructing a quality control training set, the quality control training set contains positive samples and negative samples, the positive samples are effective otoscope images meeting the diagnostic criteria, and the negative samples include at least one type selected from adjacent anatomical site images, other department endoscope images and general visual interference images; using the quality control training set, adopting a lightweight convolutional neural network as a backbone network, training through a binary classification loss function to obtain a binary classification verification network; obtaining an otoscope image to be diagnosed, inputting the otoscope image to be diagnosed into the binary classification verification network, and outputting an effective probability representing that the image is an effective otoscope image; the present application adopts a lightweight convolutional neural network as a backbone, realizes extremely low false positive rate while ensuring high interception rate, and effectively protects effective images from being misblocked.

This invention relates to the field of medical teaching model manufacturing technology, and particularly to a biomimetic temporal bone model manufacturing method and system, comprising the following steps: S1, acquiring a three-dimensional digital model of the target anatomical site, identifying the anatomical channels of the heterogeneous structure to be constructed within the three-dimensional digital model, extracting the topological morphology and apical closed section position of the anatomical channels, and reserving an implantation operation window based on the apical closed section position; S2, calculating a preset interruption layer height based on the implantation operation window, and generating an additive manufacturing slice path file containing a suspension command triggered at the preset interruption layer height. In this invention, by implanting heterogeneous units in situ and constructing physical interfaces during the manufacturing interruption period, seamless integration of non-adhesive heterogeneous structures is achieved, thereby improving the problem that traditional models mostly use multi-material integrated printing, where thermal fusion adhesion between materials results in the inability to simulate the feel of real anatomical dissection.