211 results about "Imaging modalities" patented technology

The invention relates to the technical field of image detection and quality assessment, and discloses an image-based cable stranded wire quality assessment method and system, and the method comprises the steps: obtaining an illumination reflection image set of a cable stranded wire through employing a multi-angle annular illumination imaging mode; constructing a multi-angle reflection image sequence; generating a defect suppression highlight image; carrying out image enhancement and three-dimensional normal estimation; and outputting a quality grade evaluation result. In the prior art, fine scratches, burrs and distortion defects are difficult to accurately identify under the condition of strong reflection interference, and particularly, high-resolution quality evaluation cannot be realized under the conditions of complex surface structure of a cable stranded wire and non-uniform illumination response. According to the method, the multi-angle illumination model and the angle domain sparse unmixing mechanism are constructed, and the defect enhancement driven by the normal disturbance and the multi-modal fusion classification are combined, so that the precise positioning and grade evaluation of the tiny defect area are realized, and the precision of the quality detection of the stranded cable is improved.

A platform for characterizing biomolecules, biological tissue sections, viruses, or other particles of interest in a non-invasive, high-throughput, cost-effective, and label-free manner. The platform includes a merged set of imaging modalities including and capable of interferometric microscopy and wide-field or confocal microscopy (such as, for example, a wide-field super-resolution surface enhanced Raman spectroscopy, SERS), although some aspects may be employed with data sets only received from wide-field or confocal microscopy. Related devices, systems, methods, techniques, and variations to the same are also provided.

A real-time artificial intelligence (AI) framework is provided for the automated analysis of radiological images and detection of disease, such as extracapsular extension (ECE) in prostate cancer. The system includes a dual deep learning architecture comprising a first convolutional neural network (CNN) for identifying diagnostically relevant image slices from three-dimensional MRI data, and a second CNN for classifying disease presence based on those slices. A preprocessing pipeline standardizes and harmonizes image input, and cropping algorithms isolate the region of interest for enhanced model performance. This framework enables scalable, high-accuracy diagnosis across various imaging modalities including but not limited to MRI, CT, PET, ultrasound, and diverse disease types, improving clinical decision-making and supporting integration into real-time radiology workflows.

Methods and systems for identifying a region of interest in breast tissue utilize artificial intelligence to confirm that a target lesion identified during imaging the breast tissue using a first imaging modality (e.g. x-ray imaging) has been identified using a second imaging modality (e.g. ultrasound imaging). A computing system operating a lesion matching engine utilizes a machine learning classifier algorithm trained on cases of x-ray images and corresponding ultrasound images in which lesions were identified for further analysis. The lesion matching engine analyzes a target lesion identified with x-ray imaging and a potential lesion identified with ultrasound imaging to determine a likelihood that the target lesion is the same as the potential lesion. A confidence level indicator for the lesion match is presented on a display of a computing device to aid a healthcare provider in locating a lesion in breast tissue.

The invention discloses a human body peripheral blood vessel photoacoustic three-dimensional imaging device and an imaging method thereof, and belongs to the field of blood vessel imaging. Through high resolution and functional monitoring capability of photoacoustic imaging, detailed blood vessel structure and blood flow dynamic information are provided, and early recognition and treatment effect evaluation of common lesions such as diabetic foot and peripheral artery diseases are promoted; meanwhile, a mechanical system is adopted, so that the detection front end with relatively high quality can be borne, and stable operation is realized, and a relatively good photoacoustic imaging result is obtained; the system has a highly stable accurate scanning imaging mode, and is convenient for multiple imaging modes of clinical application; through the arrangement of the imaging water tank and the lifting structure of the imaging water tank, switching of imaging modes in a limited space can be ensured, so that the device can be suitable for the layout of a portal type three-dimensional moving device. The system is expected to promote the portability of equipment, reduce the research and development cost of the equipment, be widely applied to clinical practice and community medical treatment, and improve the disease management level.

The invention relates to the technical field of multi-modal ophthalmology image analysis, and particularly discloses a multi-modal ophthalmology image analysis method, model and system based on optimal transmission image diffusion and a medium thereof.The method at least comprises the steps that S100, the distance between fundus color photo and OCT image modals is explicitly calculated through an optimal transmission algorithm, and the distance between fundus color photo and OCT image modals is calculated; carrying out collaborative evolution on the features in a continuous time domain in combination with a graph neural network and a Sheng differential equation model; and step S200, applying self-attention and cross attention in parallel, reserving modal specificity with low-layer fine granularity, and progressively fusing the color photo texture and the OCT depth structure in a high layer to realize cross-layer long-range dependent depth semantic fusion. The method not only promotes the leading-edge development of multi-modal medical image analysis, but also provides important scientific basis and technical support for constructing a high-precision and high-robustness intelligent ophthalmology diagnosis system.

An example semiconductor workpiece imaging system includes an imaging device. The example semiconductor workpiece imaging system includes a workpiece holder operable to receive a semiconductor workpiece. The example semiconductor workpiece imaging system includes a fiducial structure having one or more fiducial markers. The one or more fiducial markers and at least a portion of the semiconductor workpiece are detectable in a plurality of different image modalities.

Methods, systems, and devices for evaluating function of a heart are provided. The methods can include use of one or more imaging modalities to assess diastolic function. The methods, systems, and devices can employ various features of a cardiac volume curve to assess cardiac function. The methods, systems, and devices can be used to guide diagnosis, therapy, and / or training for sick or well patients. Methods, systems, and devices for assessing likelihood of hospital readmission for a heart failure patient are also provided.

Disclosed systems, apparatuses, and methods enable remotely controlling robotic-assisted medical systems, such as robotic-assisted surgery systems. Disclosed approaches facilitate deployment and improve the safety of robotic-assisted procedures.

The present disclosure provides to process a series of intravascular images, such as intravascular ultrasound (IVUS) images, to align the frames of the series of images longitudinally and angularly with respect to an extravascular image. In some examples, vessel fiducials are identified in each image modality and longitudinal and angular offsets are identified based on the location and angular orientation of the vessel fiducials. An aligned series of images can be generated by shifting and rotating frames of the series of images based on the identified offsets.

The invention belongs to the field of laparoscopes, and particularly relates to an integrated multi-modal image fusion laparoscope system which comprises a laparoscope body, a multi-modal image acquisition module, an image fusion processing module, a display control module and an energy supply module. The laparoscope body is integrally designed, and a plurality of image acquisition probes are arranged at the front end of the laparoscope body and used for acquiring image information in different modes; corresponding optical conduction and signal transmission lines are integrated in the lens body, so that acquired image information can be stably and efficiently transmitted to a rear-end module; the multi-mode image acquisition module comprises a white light imaging unit, a fluorescence imaging unit, an ultrasonic imaging unit and a photoacoustic imaging unit which are respectively used for acquiring image data of different modes. The system is reasonable in design, provides comprehensive operation area information for doctors by integrating various image modalities and realizing efficient fusion, improves the operation precision and operation efficiency, and is high in expandability.

A computer-implemented method for machine-learning a function configured to take as input a plurality of aligned images of a same patient and each of a different modality among a predetermined set of medical-imaging modalities, and to calculate a fused image. The method includes obtaining a dataset including, for each patient of a plurality of patients and for each modality of a respective at least part of the predetermined set, a respective image, the respective images for a patient being aligned; and training the function based on the dataset. This forms an improved solution for medical imaging.

The invention discloses a bioelectrical impedance tumor identification method based on multi-modal fusion. The method comprises the following steps: S1, acquiring electrical impedance signal data and tissue slice image data of a tumor sample; the tissue slice image data are pathological slice images corresponding to tumor tissues; s2, inputting the electrical impedance signal data and the tissue slice image data into a multi-modal feature coding module for asymmetric feature coding; s3, performing splicing and weighted fusion on the global semantic feature vector and the image semantic feature vector to form a multi-modal feature vector; and S4, inputting the multi-modal feature vector into a decoding network for classification prediction, and outputting a tumor identification result. According to the method, an asymmetric coding structure and a weighted fusion mechanism are constructed by fusing the electric signal modality and the image modality, so that the utilization efficiency and the feature discrimination capability of multi-modal information can be effectively improved, and the accuracy and the reliability of tumor recognition are remarkably improved.

The present invention provides a flexible, light-weighted and efficient multistream fusion encoder which can be easily integrated into multistream convolutional neural networks to perform segmentation and classification tasks on MRI images registered with different modalities. The encoder allows fusion of extracted feature maps in multiple streams on a layer-by-layer basis and generates the output of each stream by adding the corresponding convolutional output with an adaptively weighted fusion map computed from outputs of all streams. Adaptive weighting of fusion maps at each layer allows flexibility in highlighting different image modalities according to their relative influence on the segmentation / classification performance. The fusion encoder can also play an important role in the segmentation-classification workflow in biopsy and focal therapy planning.

The application relates to an online monitoring device and method for microelectrodes, and belongs to the technical field of special machining.The online monitoring device is composed of a coaxial holographic imaging module, an LED backlight imaging module, a motion control module, an image acquisition card, a laser power controller and an LED brightness controller.The LED backlight imaging module is used for positioning the microelectrode image; the coaxial holographic imaging module is used for holographic interference imaging of the microelectrode; based on a holographic reconstruction algorithm, electrode profile information is obtained, and the electrode loss degree is judged.The coaxial holographic imaging module and the LED backlight imaging module switch the positions of the reflecting mirrors through the motion control module to realize control of different imaging modes; the collected images are input into a PC through the image acquisition card, image algorithm analysis is carried out, and the microelectrode loss degree is judged.The application realizes online monitoring of the microelectrode loss.

A magnetic tolerant, multi-mode imaging device includes an elongated probe adapted for insertion into an imaging region of a first imaging modality, and an imaging sensor in rotational communication with the elongated probe, where the imaging sensor is responsive to a second imaging modality. A control circuit is configured for activating the first imaging modality and the second imaging modality for imaging over a region of interest, and an imaging circuit aligns images received from the first and second imaging modalities for registration in a common frame of reference to render a combined image.

A method and system (100) for augmented interpretation of shear wave elastography between first and second imaging modalities comprises performing an elastography measurement via a second imaging modality (20), different from a first imaging modality (10), to obtain at least one second imaging modality elastography value (32, 60) of a region of interest (33). At least one corresponding first imaging modality elastography value (36, 38, 62) is predicted based on the obtained second imaging modality elastography value. A graphical user interface or smart report dashboard (50) is generated that shows (i) a fibrosis level (521) of the region of interest, wherein the fibrosis level is determined as a function of (i)(a) the at least one second imaging modality elastography value (32) and / or (i)(b) the predicted at least one corresponding first imaging modality elastography value (36, 38).

A method is provided for generating and / or displaying a dynamic tooth chart In some cases, the method can include receiving dataset(s) associated with a patient. Each dataset comprises data corresponding to an imaging modality of a plurality of imaging modalities and provides information on a dentition of the patient. The datasets are processed to generate, for each dataset, one or more tooth portions. Each tooth portion comprises an image of one or more teeth of the patient. The one or more tooth portions are arranged into a dental chart. A visualization of the dental chart of the patient is generated and provided to a user device for presentation in a user interface. In some cases, a method can include determining one or more chart annotations can by performing a shape analysis, a teeth arrangement analysis, and / or a material analysis on 3D dental model(s) and / or 2D images of the patient's jaw.

A deployment system for accurate placement of localization tags within biological tissue is disclosed. The system comprises a catheter hub with sheath, a stylet, and a loader. The catheter hub provides an interface for system components, while the flexible sheath allows navigation to target sites. The stylet, operable in multiple positions, guides the sheath and assists in tag deployment. The loader houses the localization tag and acts as a safety spacer during deployment. The system is compatible with endoscopes and various imaging modalities, offering improved accuracy and efficiency over traditional wire localization techniques. The localization tags may be passive or active, with potential for advanced functionalities such as biosensing or drug delivery. This minimally invasive system finds applications in tumor marking, lymph node localization, and targeted therapy delivery across multiple medical specialties.

The invention discloses a multi-modal tampering information detection and positioning method based on mitigation of modal misleading. The method comprises the steps of S1, image tampering region identification, S2, non-tampering region and text interactive learning, S3, LLM knowledge supplementation, and S4, tampering identification and positioning. After a tampered area and a non-tampered area of an image are recognized, an LLM generates explanation of text modal background knowledge, and the consistency of the text modal and the background knowledge and the consistency of the image modal and the background knowledge are compared to serve as the basis of multi-modal tampering information detection and positioning, so that the modal misleading of multi-modal tampering information detection and positioning is relieved.

The present disclosure provides to generate ground truth data for training a machine learning (ML) model to infer pressure information (e.g., a pressure curve, a pressure ratio, or the like) for a cardiac artery from border segmentations generated from images of the cardiac artery. The ground truth data can comprise vessel and / or lumen segmentations for several cardiac arteries and associated pressure information for the cardiac arteries. The vessel and / or lumen segmentations can be generated from images from different image modalities (e.g., IVUS, angiographic, CT, etc.). Further, some of the associated pressure information can be based on measured pressure information (e.g., using a pressure sensing catheter) while other associated pressure information can be derived from the vessel and / or lumen border segmentations using numerical analysis techniques (e.g., CFD, or the like).

Provided herein is an intravascular endoscope with an improved balloon design. The endoscope comprises an anterior balloon with a camera, light source, and working channel port for visualization and therapeutic access. One or more posterior balloons are positioned inferior to, at the same level as, or superior to the anterior balloon. Inflation of the one or more posterior balloons pushes the anterior balloon against the blood vessel wall while maintaining a channel for blood flow past the anterior balloon. The endoscope enables real-time, direct visualization of the interior of blood vessels for diagnosis and treatment of vascular diseases while preserving critical blood flow. Additional imaging modalities, such as ultraviolet and infrared, can be incorporated to enhance tissue characterization. Visual markers on devices inserted through the working channel improve visibility and guidance under endoscopic imaging. The endoscope is compatible with arteries and veins throughout the body and provides advantages over traditional imaging techniques for managing vascular disease.

The application discloses a skin disease case retrieval method and device, a medium and a product, and relates to the technical field of medical image understanding and multi-modal knowledge fusion. The method encodes and maps multi-modal data of each skin disease case, obtains labeled features of the multi-modal data, projects the labeled features to a shared latent space, and obtains labeled features of the multi-modal data in the shared latent space; based on the labeled features, a Top-k node selection mechanism based on correlation scores is used to construct a single-modal knowledge graph of each image modality and a cross-modal knowledge graph between any two modalities, and then a modality-level representation and a cross-modal embedded representation are obtained, and a case database is obtained by splicing; the similarity between the feature vector of a skin disease query case and the feature vectors in the case database is determined, the feature vector with the highest similarity in the case database is output, and a retrieval result of the skin disease query case is obtained. The application can improve the accuracy and clinical applicability of cross-modal medical image retrieval.

The application discloses a long-distance rail recognition and obstacle detection method and system, a long-focus optical system is combined with a super-high-speed industrial camera on a hardware level to build a high-frame-rate and long-distance optical detection system, a region of interest for obstacle detection is demarcated by recognizing and visually segmenting left and right rail lines on a software level, and a target detection-based track obstacle intrusion detection algorithm and other advanced visual tasks are executed, and finally high-frame-rate recognition and detection of long-distance rails and track obstacles are realized. The Schmidt-Cassegrain optical system with a focal length of 2000mm is combined with a super-high-speed industrial camera with a resolution of 1920*1080 and 3000 frames per second to build a long-distance high-frame-rate optical detection platform and erect on a driving position of a train, railway conditions within a range of 6km are detected in real time, and serious accidents caused by a too long braking distance of the train due to high-speed driving can be prevented. Compared with traditional train driver eye observation and laser radar scanning imaging modes, a long-distance optical observation platform and a rear-end real-time detection system can realize a longer detection distance, better detection and recognition robustness and a higher frame rate.

The present disclosure provides a scheme to process a series of intravascular images, such as intravascular ultrasound (IVUS) images, to align frames of the series of images with extravascular images in longitudinal and angular directions. In some examples, vessel fiducials are identified in each image modality, and longitudinal and angular offsets are identified based on the position and angular orientation of the vessel fiducials. By shifting and rotating the frames of the series of images based on the identified offset, an aligned series of images may be generated.

The invention discloses an application of a tumor-associated macrophage targeting nanoprobe in ultrasensitive magnetic resonance molecular imaging of in-vivo in-situ lung cancer. The tumor-associated macrophage targeting nanoprobe prepared by the method provided by the invention is loaded with water-insoluble supramolecular celopphane, so that Xe'molecular cage 'celopphane can be uniformly dispersed in water and a biological system, and is used for in-vivo hyperpolarized 129Xe magnetic resonance imaging. According to the nanoprobe, mannose modification is carried out on the surface of the nanoprobe, so that the nanoprobe can effectively target tumor-related macrophages in a tumor area, and targeted detection of in-situ lung cancer tumors is realized; the surface of the nanoprobe is subjected to near-infrared fluorescence molecular modification, so that fluorescence / magnetic resonance bimodal detection of solid tumors can be realized. In combination with the advantage that local drug concentration can be improved by pulmonary drug delivery, a strong 129Xe magnetic resonance signal of the developed probe can be directly detected in vivo, and in-vivo 129Xe magnetic resonance molecular imaging is realized on an in-situ lung cancer model mouse through a direct sampling imaging mode.

The application provides a chest plain CT image lung artery and vein automatic extraction method, and relates to the technical field of CT image processing. The method first acquires lung airway, lung blood vessel and lung external artery and vein data, and performs data preprocessing and unifies layer thickness; then, based on the reconstructed CT scan image, lung blood vessel skeletonization is performed; and a lung internal artery and vein growth algorithm is used to classify the lung blood vessel skeleton; then, the lung artery and vein are reconstructed according to the artery and vein marked by the lung blood vessel skeleton; finally, the classified lung blood vessel is evaluated according to the blood vessel skeleton of the marked lung internal artery and vein and the blood vessel voxel point after the lung internal artery and vein reconstruction. The method uses multiple features to classify the lung internal artery and vein, does not require the imaging mode of the input data, is an automatic algorithm, does not require manual parameter adjustment or seed point setting, has strong generalization ability, and proposes two new evaluation methods, so that the classification effect of the lung artery and vein is checked and evaluated from multiple angles.

The application discloses a kind of imaging type ultra-small curvature flat convex lens or flat concave lens positive and negative face detection device and method, the detection method of the present application, the distinction of plane and curved surface is realized by imaging method, imaging method includes transmission imaging method, right-angle reflection imaging method and acute-angle reflection imaging method.The imaging type ultra-small curvature flat convex lens or flat concave lens positive and negative face detection method of the present application is simple, easy to operate, and the distinction of curved surface, plane can be realized by specific imaging mode, high efficiency, and accuracy is 100%;The imaging type ultra-small curvature flat convex lens or flat concave lens positive and negative face detection device of the present application is simple in structure, convenient to use, after the optical system of the specific structure of the present application, imaging light spot can be obtained using area array camera, and whether curved surface is upward or plane is upward can be accurately judged by the size of two light spots.

The present disclosure provides a system and method for automated monitoring, quantification, and control of plant health from micro and macro scales using optical sensing and imaging modalities, environmental sensing, data analysis, image processing, and machine learning. Intelligent feedback control of plant health employed in the system reacts in real-time to changes in plant health to enable precision agriculture applications like intelligent irrigation or determination of optimal fertigation parameters. In turn, the system results in improved agricultural outcomes such as increased fruit production or unique flavor profiles. The system further provides a means for automated and non-invasive testing of novel treatments for disease or adverse conditions, or to improve crop yields.

An intraoperative guidance approach for an image guided surgical robot performs intraoperative image registration and guidance based on a surgical target. A surgical imaging modality, such as US (ultrasound) or PA (photoacoustic), establishes a frame of reference based on a preoperative base imaging modality such as CT (computed tomography) or MRI (magnetic resonance imaging). A position reference of a surgical target, such as a tumor or neural structure, is established by the surgical imaging modality from the base imaging modality, computed based on a dense scan of the surgical region. Successive scans in the surgical image modality provide real-time guidance for a robotically actuated surgical instrument or probe based on the surgical target. An iteration of successive scans allows intramodal servoing concurrent with surgical instrument actuation towards a moving surgical target when a fixed surgical position in the frame of reference cannot be assured.