77 results about "Imaging technique" patented technology

This invention relates to a pair of intelligent, multimodal smart eyeglasses designed for adaptive vision, biometric ocular monitoring, and predictive emergency response. The system integrates multilayer lenses filled with electrochromic gel and surrounded by elastic structures to enable dynamic focal length modulation in response to user visual behavior. An array of sensors—including visible light, ultraviolet, micro-cameras, infrared emitters, gyroscopes, and ultrasonic transceivers—collects multispectral data to evaluate environmental and physiological parameters. Real-time data processing is performed by an embedded quantum microcontroller, which manages light transmittance, detects eye fatigue, maps ocular surfaces, and identifies hemodynamic abnormalities such as fainting, seizure, or ocular stroke. Advanced imaging techniques, such as ultrasonic ptychography and wave diffraction analysis, enable non-invasive 3D mapping of ocular layers and internal eye motion. The system also supports wireless communication with external platforms including smartphones, vehicles, and brain-machine interfaces, enabling proactive safety interventions. These features work in tandem to support early diagnosis of critical conditions, protect vision, and personalize user experiences through machine learning and adaptive feedback mechanisms.

The invention discloses a coagulant addition control method and system based on visual identification of dynamic change of floc, and the method comprises the steps: collecting image data of a flocculation process in a water body in real time, and carrying out the image enhancement processing, so as to obtain a clear particle distribution image; identifying the size and quantity characteristics of floc particles through an image analysis technology, and determining the average diameter and density value of the particles in the current flocculation stage; calculating the deviation between the current floc state deviation and a preset standard value, and obtaining a preliminary adding adjustment coefficient matched with the current floc state deviation; combining with water body flow data monitored in real time to obtain an optimized adding amount for the current working condition; and generating a control instruction to adjust the input acceleration or stroke of the pump adding equipment, and continuously monitoring the updated floc image to verify the adjustment effect. According to the method, the floc state can be identified on line through an image technology, the adding amount is accurately calculated in combination with historical experience and real-time flow, and closed-loop optimization control over the intrinsic nature of the coagulation process is achieved.

The invention relates to the technical field of OCT imaging, and discloses an OCT automatic control system and method, and the system comprises a pushing and injecting device which is used for pushing and injecting a medium to be pushed and injected into a blood vessel through an injector connected with a catheter; the OCT pullback device is used for rotating the pullback catheter; and the OCT control module is connected with the injection device and the OCT pull-back device, is used for sending an injection instruction to the injection device and is also used for sending a pull-back instruction to the OCT pull-back device. The OCT control module is used for sending the control instruction, automatic synchronous work of the injection device and the OCT pull-back device can be achieved, injection of the contrast agent is accurately controlled, waste of the contrast agent and influence on life safety of a patient are avoided, meanwhile, OCT imaging quality can be effectively improved, and then the accuracy of subsequent diagnosis result judgment is improved.

Laser speckle contrast imaging techniques that apply a temporal sliding window to a sequence of speckle frames of an avian egg to determine overlapping sets of speckle frames used to reconstruct a sequence of extraembryonic blood vessel images (e.g., movie) showing blood flow dynamics, and where input to a machine learning model based on the overlapping sets of speckle frames can be used to predict the developmental stage of the avian egg, and where the overlapping sets of speckle frames can be used in drug screening.

A medical system includes an elongate vascular device having an optical fiber and a sensor module configured to detect pressure pulses at the skin surface resulting light pulses projected from a distal tip of the optical fiber within the vasculature of a patient. Logic of a system console processes pressure pulse data using photo-acoustic imaging techniques to obtain an image the vasculature. The processing also can include determining properties of the vasculature, such as a cross-sectional size of the vasculature, and determines therefrom a location of the distal tip.

The invention discloses a large-view-field and high-temporal-spatial-resolution transmission electron microscope in-situ imaging method for a microcosmic electrochemical process, which comprises the following steps: step 1, loading an electrode material particle sample to be detected on a carrying table, inserting the sample into a transmission electron microscope vacuum lens cone along with a sample rod, identifying a target sample under low magnification, and carrying out basic adjustment on an electron microscope; 2, adjusting magnification times to ensure that an observation area is completely incorporated into an imaging view field, selecting an imaging mode, eliminating astigmatism, and adjusting the focal length of an objective lens until a sample particle image interface is clear; and step 3, selecting a CCD camera, setting an acquisition frame rate, and performing ultrafast acquisition of images or videos. The transmission electron microscope in-situ imaging technology giving consideration to both the large view field and the high space-time resolution has practical application value in research of the electrochemical reaction kinetics process of the granular material.

A multi-modality cancer screening and diagnosis system is provided that allows cancer screening and diagnosis of a patient using at least two different and sequential three-dimensional imaging techniques without patient repositioning. The system includes a first three-dimensional image acquisition device, a second three-dimensional image acquisition device having a probe with a transmitter mounted thereon, and a positioning paddle for positioning and immobilizing an object to be imaged during the cancer screening and diagnosis procedure. The positioning paddle is designed to facilitate visualization of the breast in both three-dimensional modalities without movement of the patient, and preferably is designed to position the patient with comfort during a diagnosis procedure which uses both imaging modalities.

Surgical visualization can compensate for partially captured images that are obscured, incomplete, damaged, or interfered by replacing those portions of the image with corresponding portions of other images. The other images can include images previously generated by the surgical visualization system or images generated using multispectral imaging techniques. The present disclosure relates to a surgical imaging system comprising a multispectral electromagnetic radiation (EMR) source configured to emit EMR at a first wavelength range and a second wavelength range, an image sensor configured to sense the EMR emitted from a target site at each of the first wavelength range and the second wavelength range, and a control circuit configured to generate a first image of the target site from the EMR emitted at the first wavelength range, generate a second image of the target site from light emitted at the second wavelength range, determine whether the first image is at least partially occluded, and generate a fused image containing a fusion between unoccluded segments of the first image and segments of the second image corresponding to occluded segments of the first image. Alternatively, the control circuit is configured to generate an image of the target site from the emitted EMR, determine whether the image is at least partially occluded, retrieve a previous image of the target site, and generate a fused image containing a fusion between unoccluded segments of the image and segments of the image corresponding to occluded segments of the previous image.

The application claims a kind of neonatal brain imaging system and method based on photoacoustic technology, belong to the field of medical devices. Including control module, excitation source module, neonatal brain photoacoustic data acquisition module, data output module and quantitative calculation module. The control module includes two computers and laser control instrument;The excitation source module includes high-frequency laser and its water cooling system;Neonatal brain photoacoustic data acquisition module contains focusing lens and optical fiber, wearable flexible ultrasonic transducer, multichannel acquisition card;The data output module contains computer matched with real-time imaging MarsonicsDAQ software and the imaging algorithm embedded in the software;Quantitative calculation module contains multispectral linear demixing algorithm and imaging software. The application provides high-resolution, high-contrast real-time imaging of neonatal brain tissue structure and cerebral hemodynamic parameters, which can be used as a complementary method to existing brain imaging techniques for auxiliary diagnosis.

The invention discloses a spectrometer optical path structure based on photoacoustic composite film thickness detection, a mechanical device and an adjustment method thereof, and relates to the technical field of optical coherence tomography. The light path structure comprises a collimating lens group used for collimating an incident light beam into parallel light; the reflecting element is obliquely arranged and is used for reflecting the collimated light beam; and the grating element is used for splitting the reflected light beam. An achromatic collimating lens group, a high-diffraction-efficiency body phase holographic grating and a glass material with an extremely low dispersion coefficient are used as focusing lenses to build a light path structure, through precise optical design, the RMS radius of a light spot with a single wavelength is optimized to be close to a diffraction limit, more than 95% of light energy is concentrated in a tiny area, and the light path structure is optimized to be uniform. The extremely high energy concentration ratio effectively reduces the requirement for the pixel size of the camera, the overall signal-to-noise ratio and spectral resolution of the system are remarkably improved, and the inherent disadvantages that an infrared indium gallium arsenic camera is small in pixel and low in signal-to-noise ratio are successfully overcome.

A method includes positioning a patient in a first orientation relative to a radiation source. The method further includes measuring one or more locations of a patient's thorax using a 3D imaging technique. The method further includes, while measuring the one or more locations of the patient's thorax using the 3D imaging technique: generating a model of the patient's thorax using the one or more locations of the patient's thorax; updating the model of the patient's thorax as the patient breathes; and exposing the patient to a radiation dose using the radiation source, wherein the dose is determined according to the model of the patient's thorax.

Phase-based methods can be used for one or more of acquisition, storage, or subsequent analysis (e.g., A-scan reconstruction or full focus method imaging) to support acoustic inspection. For example, binarization or other quantization techniques can be used to compress the amount of data associated with time series signal acquisition. A representation of phase information from the time series signals can be generated, e.g., by processing the binarized time series signals or otherwise quantized time series signals. As an illustrative example, using the representation of phase information, one or more A-scan reconstructions can be performed using phase summing techniques, e.g., for pulse echo A-scan inspection, or TFM imaging techniques can be used. In such phase summing methods, the time series representations of phase data can be summed, e.g., where each time series can be delayed (or phase-rotated) by an appropriate delay value, and then aggregated.

Techniques are described for enhancing the quality of three-dimensional (3D) anatomy scan images using deep learning. According to an embodiment, a system is provided that comprises a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory. The computer executable components comprise a reception component that receives a scan image generated from 3D scan data relative to a first axis of a 3D volume, and an enhancement component that applies an enhancement model to the scan image to generate an enhanced scan image having a higher resolution relative to the scan image. The enhancement model comprises a deep learning neural network model trained on training image pairs respectively comprising a low-resolution scan image and a corresponding high-resolution scan image respectively generated relative to a second axis of the 3D volume.

Mid-infrared photothermal heterodyne imaging (MIR-PHI) techniques described herein overcome the diffraction limit of traditional MIR imaging and uses visible photodiodes as detectors. MIR-PHI experiments are shown that achieve high sensitivity, sub-diffraction limit spatial resolution, and high acquisition speed. Sensitive, affordable, and widely applicable, photothermal imaging techniques described herein can serve as a useful imaging tool for biological systems and other submicron-scale applications.

Aspects of the present disclosure provide improved fluorescence imaging techniques suitable for fluorescence-based analysis (e.g., sequencing) of an excited sample. Some aspects relate to directing an imaging aperture of a fluorescence imaging device towards a sample well region and capturing an image of the sample well region. Some aspects relate to selecting a sample well region and capturing an image of the selected sample well region. Some aspects relate to, during at least a portion of performing a controlled cleavage of a terminal amino acid in a first sample well, capturing a fluorescence image of a second sample well. Some aspects relate to setting a duration of imaging by and / or a location of an imaging aperture of a fluorescence imaging device. In some embodiments, aspects of the present disclosure provide for faster, less expensive, and / or greater control over fluorescence imaging and analysis of a sample.

Improved magnetic resonance imaging systems, methods and software are described including a low field strength main magnet, a gradient coil assembly, an RF coil system, and a control system configured for the acquisition and processing of magnetic resonance imaging data from a patient while utilizing a sparse sampling imaging technique.

The invention relates to the technical field of concrete preparation, in particular to a concrete multi-scale structure regulation and anti-abrasion performance optimization method which comprises the following steps: acquiring a two-dimensional slice image of a concrete sample by adopting an X-ray tomography technology, and observing the internal aperture characteristics of the sample; performing three-dimensional reconstruction on the sample, detecting pores and counting layered porosity; analyzing the pore distribution and porosity of the concrete sample by adopting a mercury intrusion method and a nitrogen adsorption test method; cellulose nanofibers CNFs are doped into the concrete, and the pore structure of the concrete is optimized by regulating and controlling the addition amount of the CNFs; the concrete doped with the CNFs is subjected to an abrasion resistance test, and the optimal CNFs addition amount is determined according to a test result. By reasonably controlling the addition amount of the CNFs, the ultra-high performance concrete with different pore structures and abrasion resistance can be prepared according to different requirements so as to meet different building structure requirements.

The invention provides a low-contrast imaging method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of mammary gland CT imaging, and the method comprises the steps: hardware installation: adding a grating beam limiting device behind a radiation source main body, so as to achieve the formation of horizontal stripes on detection; data acquisition: acquiring bright field images, acquiring a plurality of circles of images during shooting, and moving each circle for the same distance to ensure that the bright area of the scanning result can completely reconstruct a visual field area; and data processing: calculating a grating shielding area value and an unshielded area value. According to the method, direct X-rays are completely shielded in the adjacent area, signals collected by the detector are scattering signals, and scattering signals of the non-shielded area are estimated by using the scattering interpolation of the shielded area, so that scattering artifacts can be removed, and the low-contrast resolution is remarkably improved.

A 3D single-molecule super-resolution imaging technique is disclosed herein. In particular, the techniques described herein combine an optical platform including a tilted single-objective dithered light sheet illumination, a microfluidic system, and point spread function engineering to achieve precise 3D single-molecule super-resolution imaging of subcellular structures (e.g., a sample (110)) with easy control of the extracellular environment. In certain embodiments, the single-objective dithered light sheet (102) of the optical setup (100) includes a plurality of galvanometric mirrors (116, 118, 124) and a tunable lens (122) that may steer a light sheet (102) for optimized optical sectioning of the sample (110). In some embodiments, the sample (110) is positioned in the microfluidic device (160) during imaging. In this way, traditional challenges (e.g., high out-of-focus background fluorescence and lack of environmental control) generally facing single-molecule localization microscopy may be overcome.

Techniques are provided for estimating an optimal radiation dose for x-ray imaging. A methodology implementing the techniques according to an embodiment includes operating an x-ray sensor at a first gain setting. The method also includes capturing a scouting image at the first gain setting using a scouting image radiation dose. The method further includes employing a radiation dose model to provide a diagnostic image radiation dose based on the scouting image. The diagnostic image radiation dose is greater than the scouting image radiation dose. The method further includes operating the x-ray sensor at a second gain setting. The second gain setting is less than the first gain setting. The method further includes capturing a diagnostic image using the provided diagnostic image radiation dose.

A source emits a pulse to an object to generate a particle, and an imaging detector produces a light flash at an X / Y hit position of the particle. The detector outputs a waveform arising from the particle. An event-driven camera provides a signal from the detector that includes intensity and time-over-threshold signals related to the light flash, time-of-arrival information of the event, and the X and Y hit position of the particle. A photodiode determines a time origin of the pulse from the source. A timing circuit is coupled to the detector and to the photodiode, and determines time-of-flight (TOF) of the particle based on the waveform, and based on the time origin of the pulse. The 3D coordinates are generated based on the X / Y hit position synchronized with the TOF of the particle.

The various embodiments herein provide a system and method for character identification on curved planes The system integrates advanced imaging techniques, standardized character positioning, and a multi-plane OCR module utilizing machine learning to accurately identify characters on non-planar surfaces, such as ship hulls or cylindrical containers. The system includes a surface adaptation module for mapping and adjusting to surface curvatures, ensuring high accuracy across diverse conditions. Real-time processing capabilities offer immediate recognition results, while continuous machine learning-driven improvement enhances the system's effectiveness over time. The system also features a robust communication module for seamless data integration with external applications and a durable housing design to ensure reliable operation in harsh environments. This comprehensive approach provides an efficient and adaptable solution for industries requiring precise OCR on curved surfaces.

The invention relates to a method for performing a dedicated scan (1) using an imaging method (3) of a structure to be examined, in particular the left atrial appendage of a heart, comprising the following method steps: S1) Pre-selecting an area to be examined, wherein the area to be examined includes the structure to be examined, S2) Taking an overview photograph of the area to be examined, S3) Transmitting the overview recording to an evaluation unit (4), S4) Determining the position of the structure to be investigated in the overview image using artificial intelligence and determining preliminary coordinates, wherein the preliminary coordinates define the position of the structure to be investigated in the overview image, S5) Determining final coordinates using artificial intelligence based on preliminary coordinates, wherein the final coordinates define the position of the structure to be examined for the imaging procedure, S6) Transmitting the final coordinates to a control unit of the imaging procedure, S7) Performing a dedicated scan of the structure to be investigated using the transmitted final coordinates via the imaging technique (3). In this way, a method for performing a dedicated scan is provided, which can also detect structures that are difficult to define and with which radiation exposure can be reduced.

The application discloses an X-ray multi-contrast fusion projection tomography reconstruction method based on inter-domain consistent loss, and belongs to the technical fields of deep learning and X-ray multi-contrast imaging. The method comprises the following steps: acquiring a multi-contrast projection and a fusion projection image data set of X-ray grating imaging; constructing an end-to-end fusion projection tomography reconstruction network, wherein the network comprises a back projection layer and a plurality of convolution layers, and a skip connection structure is introduced; integrating the data set into a sinogram to input the network, and adopting a loss function comprising a fusion projection-fusion tomography inter-domain consistent loss and a contrast projection-fusion tomography inter-domain consistent loss to perform self-supervised training; and finally inputting a fusion sinogram projection into the trained network to output a fusion tomography image highly consistent with physical information of the projection domain. The application realizes information consistency of the projection domain and the fusion image of the tomography domain, and improves the comprehensive representation capability of multi-contrast imaging.

A method for providing a prediction of a representation of an examination region that was generated using a medical image technique involving a contrast agent may include receiving a first representation in frequency space of an examination region of an examination object, receiving a second representation in the frequency space of the examination region of the examination object, providing the first representation and the second representation as an input to a predictive machine learning model that is configured to provide, as an output, a prediction of a representation in the frequency space of the examination region with an amount of the contrast agent administered during a medical imaging technique, receiving the output of the predictive machine learning model based on the input, and converting the output of the predictive machine learning model to a representation in real space of the examination region of the examination object.

Techniques are described to utilize machine learning to analyze EBUS ultrasound imagery. Models are trained on annotated samples to identify important vascular landmarks, lymph node stations, and other structures.

Techniques for determining a refined region of interest are described. In an embodiment, the refined region of interest may be associated with a radio frequency (RF) device. In some embodiments, a method may include obtaining, from one or more sensors, sensor data corresponding to a scene associated with at least a portion of a target object, wherein an RF device is associated with the target object; obtaining, from the RF device or a storage device, state information related to the RF device, object information related to the target object, or a combination thereof; and performing an action with respect to the target object based on a region of interest associated with the sensor data, the region of interest corresponding to the RF device and at least a portion of the target object, where the region of interest is based at least in part on the state information, the object information, or a combination thereof.

The utility model relates to the technical field of X-ray imaging, and particularly discloses floor type oral cavity CBCT (cone beam computed tomography) equipment which comprises a floor base and a rotating base rotationally sleeved on the floor base, a supporting mechanism is arranged on the floor base, and a shooting mechanism is arranged on the rotating base; the supporting mechanism comprises a lifting seat arranged at the top of the floor base, and a jaw support assembly and a head support assembly which are distributed on the front side and the rear side of the lifting seat; the shooting mechanism comprises a stand column, a radiation source and a detector, the radiation source and the detector are arranged in the radial direction of the floor base, the radiation source is fixed to the top of the stand column, a connecting piece used for mutual connection is arranged between the radiation source and the detector, and the lifting seat is located between the radiation source and the detector. By adopting the technical scheme provided by the utility model, the technical problems that the radiation source and the detector in the prior art need to be mounted separately, the mounting distance is long, the positioning difficulty of field mounting and later maintenance is increased, and the positioning precision is poor can be solved.

An imaging system and biopsy sample holder with a housing, a hollow cavity within the housing, a vacuum port positioned at an end of the housing and connected to the hollow cavity, a groove in the upper surface of the housing positioned between the ends of the housing, and a plurality of holes positioned in the groove and extending into the hollow cavity are provided. The groove is configured to receive a tissue sample or a biopsy needle for placement of a tissue sample in the groove. The tissue sample is held in place by negative pressure created by applying a vacuum source to the vacuum port. The holder can couple with the specimen stage of many different types of imagers and is well-suited for use with slide-free imaging techniques such as Fluorescence Imitating Brightfield Imaging (FIBI).