44 results about "Diagnostic quality" patented technology

An implantable biocompatible lead that is also compatible with a magnetic resonance imaging scanner for the purpose of diagnostic quality imaging is described. The implantable electrical lead comprises a plurality of coiled insulated conducting wires wound in a first direction forming a first structure of an outer layer of conductors of a first total length with a first number of turns per unit length and a plurality of coiled insulated conducting wires wound in a second direction forming a second structure of an inner layer of conductors of a second total length with a second number of turns per unit length. The first and the second structures are separated by a distance with a layer of dielectric material. The distance and dielectric material are chosen based on the field strength of the MRI scanner. The lead may further comprise a conducting layer formed by coating a material consisting of medium conducting particles in physical contact with each other and a mechanically flexible, biocompatible layer forming an external layer of lead and in contact with body tissue or body fluids.

An antenna module, that is compatible with a magnetic resonance imaging scanner for the purpose of diagnostic quality imaging, is adapted to be implanted inside an animal. The antenna module comprises an electrically non-conducting, biocompatible, and electromagnetically transparent enclosure with inductive antenna wires looping around an inside surface. An electronic module is enclosed in an electromagnetic shield inside the enclosure to minimize the electromagnetic interference from the magnetic resonance imaging scanner.

Systems and methods are provided for processing a medical image to automatically identify the anatomy and view (or pose) from the medical image and automatically assess the diagnostic quality of the medical image. In one aspect a method for automated decision support for medical imaging includes obtaining image data, extracting feature data from the image data, and automatically performing anatomy identification, view identification and / or determining a diagnostic quality of the image data, using the extracted feature data.

Systems and methods are provided for processing a medical image to automatically identify the anatomy and view (or pose) from the medical image and automatically assess the diagnostic quality of the medical image. In one aspect a method for automated decision support for medical imaging includes obtaining image data, extracting feature data from the image data, and automatically performing anatomy identification, view identification and / or determining a diagnostic quality of the image data, using the extracted feature data.

An antenna module, that is compatible with a magnetic resonance imaging scanner for the purpose of diagnostic quality imaging, is adapted to be implanted inside an animal. The antenna module comprises an electrically non-conducting, biocompatible, and electromagnetically transparent enclosure with inductive antenna wires looping around an inside surface. An electronic module is enclosed in an electromagnetic shield inside the enclosure to minimize the electromagnetic interference from the magnetic resonance imaging scanner.

An implantable biocompatible lead that is also compatible with a magnetic resonance imaging scanner for the purpose of diagnostic quality imaging is described. The implantable electrical lead comprises a plurality of coiled insulated conducting wires wound in a first direction forming a first structure of an outer layer of conductors of a first total length with a first number of turns per unit length and a plurality of coiled insulated conducting wires wound in a second direction forming a second structure of an inner layer of conductors of a second total length with a second number of turns per unit length. The first and the second structures are separated by a distance with a layer of dielectric material. The distance and dielectric material are chosen based on the field strength of the MRI scanner. The lead may further comprise a conducting layer formed by coating a material consisting of medium conducting particles in physical contact with each other and a mechanically flexible, biocompatible layer forming an external layer of lead and in contact with body tissue or body fluids.

A system and method of medical imaging is designed to reduce a patient's X-ray exposure during scanning. The system automatically generates a default noise index from a received set of scan parameter values that specifies a desired tube current of an X-ray source to use during the scanning of a patient. The default noise index can then be overridden to select a preferred noise index based upon a desired diagnostic quality for a particular volume of interest (VOI) and a diagnostic objective.

For training data pairs comprising training text (a radiological report) and training images (radiological images associated with the radiological report), a first encoder network determines word embeddings for the training text. A concept is generated from the operation of layers of the first encoder network, which is regularized by a first loss between the generated concept and a labeled concept for the training text. A second encoder network determines features for the training image. A heatmap is generated from the operation of layers of the second encoder network, which is regularized by a second loss between the generated heatmap and a labeled heatmap for the training image. A categorical cross entropy loss is calculated between a diagnostic quality category (classified by an error encoder) and a labeled diagnostic quality category for the training data pair. A total loss function comprising the first, second, and categorical cross entropy losses is minimized.

Embodiments of the subject invention relate to a method and apparatus for obtaining an electrocardiogram (ECG) signal. Embodiments can separate a true ECG signal from one or more signals due to electric fields caused by moving electrical charges. In a specific embodiment, an ECG signal can be separated from one or more electric fields caused by blood flow. An embodiment pertains to a joint MRI and diagnostic ECG system. In an embodiment, the joint diagnostic quality ECG can add information to a MRI cardiac study. This additional information can be useful for MR guided intervention treatments, such as locating tissue that created bad electrical arrhythmia. In an embodiment, the subject method and apparatus can be utilized to obtain an ECG for patient located in a magnetic field of 1.5 T or higher, such as in MRI systems with 1.5 T or higher magnetic fields. Embodiments of the invention can use flow encoding with a changing magnetic field, with dense electrical sensors and inversion of the EEG data, utilizing this information to extract the flow related signals. Further, inversion to the source distribution of the flow related signals can be accomplished.

A method for correcting Positron Emission Tomography (PET) data includes adjusting a tube current generated by the CT imaging system to a second tube current value that is less than a first tube current value used to generate diagnostic quality CT images, and imaging the patient with the CT imaging system set at the second tube current value. The method also includes generating a plurality of computed tomography (CT) projection data from the CT imaging system and preprocessing the CT projection data to generate preprocessed CT projection data. The method further includes filtering the preprocessed CT projection data to reduce electronic noise to generate filtered CT projection data, and performing a minus logarithmic operation on the filtered CT projection data to generate the corrected PET data.

The invention discloses a smart medical service system based on big data. The smart medical service system is composed of a medical data collection device, a wireless communication device, a cloud server, a storage device, a user terminal system and a medical terminal system. The medical data collection device is configured to input user identity information and collect various physiological and pathological data of users; the cloud server is used for realizing user data mining, evaluating the user health states and diagnostic quality, and generating disease diagnosis and treatment plans automatically; the user terminal system is configured to receive server data and perform an online medical assistance service; and the medical terminal system is used for carrying out online professional evaluation and consultation on users having pathological features by doctors. Therefore, the collected user data can be stored into the server and users can check the own pathological data through mobile phones; and online medical assistance services are provided.

This multipurpose, modular system provides diagnostic-quality, wireless, multichannel monitoring in diverse settings, including interventional procedures guided by X-ray and MRI, with variable electromagnetic interference (EMI) and eliminates the need for multiple detachments / reattachments of patient cables when the patient is moved from one room / procedure to another. The system includes: 1) multiple filterbanks (filtering procedures) for recording both diagnostic-quality (broad-band) signals in the absence of EMI and narrow-band signals in the presence of EMI, with subsequent reconstruction of diagnostic-quality signals from the narrow-band signals; 2) filtering of EMI, using a priori and adaptive criteria about differences between the EMI and physiological signals' characteristics; 3) filtering of the magneto-hydrodynamic effect, using physiological measurements at different distances from the magnet (i.e., at different strengths of magnetic field) and changes in blood flow and blood pressure; and 4) multiple wireless transmitters for increasing reliability and speed (throughput) of the wireless data transmission.

The invention discloses a to-be-corrected medical data identification method, device and equipment, and a storage medium, relates to the technical field of artificial intelligence such as AI medical treatment, big data and natural language processing, and can be applied to an auxiliary diagnosis decision scene. According to the specific implementation scheme, the method comprises the steps of obtaining medical data, and converting the medical data into medical structured data; performing quality control examination on the medical structured data to generate at least one quality control examination result; generating an error probability of the medical data according to the at least one quality control examination result; and under the condition that the error probability is greater than apreset threshold, taking the medical data as to-be-corrected medical data. Therefore, by identifying the medical data, the medical data to be corrected is determined, so that the medical data is corrected in time, and the writing quality and the diagnosis quality of the electronic medical record are improved.

A method for the reduction of motion artifacts in a helical CT reconstruction, the method including the steps of: (a) reconstructing from the raw CT data an initial estimate of the 3D attenuation distribution of the object of interest; (b) estimating a pose parameter set of the object for each projection angle; (c) undertaking a motion corrected reconstruction from the measured projections, accounting for the pose changes estimated in (b); (d) iterating steps (b)-(c) until some convergence criterion is met; and (e) making a final reconstruction of diagnostic quality using the pose estimates obtained in the previous steps.

A compact, mobile, dedicated SPECT brain imager that can be easily moved to the patient to provide in-situ imaging, especially when the patient cannot be moved to the Nuclear Medicine imaging center. As a result of the widespread availability of single photon labeled biomarkers, the SPECT brain imager can be used in many locations, including remote locations away from medical centers. The SPECT imager improves the detection of gamma emission from the patient's head and neck area with a large field of view. Two identical lightweight gamma imaging detector heads are mounted to a rotating gantry and precisely mechanically co-registered to each other at 180 degrees. A unique imaging algorithm combines the co-registered images from the detector heads and provides several SPECT tomographic reconstructions of the imaged object thereby improving the diagnostic quality especially in the case of imaging requiring higher spatial resolution and sensitivity at the same time.

A method for correcting Positron Emission Tomography (PET) data includes adjusting a tube current generated by the CT imaging system to a second tube current value that is less than a first tube current value used to generate diagnostic quality CT images, and imaging the patient with the CT imaging system set at the second tube current value. The method also includes generating a plurality of computed tomography (CT) projection data from the CT imaging system and preprocessing the CT projection data to generate preprocessed CT projection data. The method further includes filtering the preprocessed CT projection data to reduce electronic noise to generate filtered CT projection data, and performing a minus logarithmic operation on the filtered CT projection data to generate the corrected PET data.

Projection data acquired with an x-ray CT system is filtered using a bilateral filter to reduce image noise and enable the acquisition at lower x-ray dose without the loss of image diagnostic quality. The bilateral filtering is performed before image reconstruction by producing a noise equivalent data set from the acquired projection data and then converting the bilateral filtered values back to a projection data set suitable for image reconstruction.

An interactive method for allowing a user to obtain image data for diagnostic purposes from a server having access to stored data, comprising: connecting a user's computer to the server over a communication network; receiving from the server image reconstruction software for the user's computer; requesting specific image data for transmission from the server to the user's computer; progressively transmitting the requested specific image data over the network from the server to user's computer; and repeatedly reconstructing diagnostic quality images, from the progressively received image data, at different quality levels, using the reconstruction software on the user's computer.

The invention discloses a control method, a control system and a control device of auto-exposure of C-arm X-ray machines. The device collects images according to the setting exposure parameter, analyzes images, adjusts the exposure parameter and collects images again. Through such a rapid and continuous process of collection and adjustment, the control device of auto-exposure of C-arm X-ray machine realizes auto-exposure control, eases the burden of doctors and reduces the surgical risk by automatically outputting and locking the optimal exposure parameter in a short time. the control device of auto-exposure of C-arm X-ray machine also realizes consistency of the diagnostic images of different body parts of patients in different body sizes; in addition to meeting the diagnosis quality demand of images, the device also minimizes the radiation level of rays and reduces the radiation risk of doctors and patients.

The invention provides a system for deducing scanning sequence phase on the basis of DICOM image information, wherein the system includes an image information management module used for transmitting the DICOM image of a patient to an image data extraction module; the image data extraction module can extract a sequence, containing a phase data, in the DICOM image sequence on the basis of inspectionarea data, spatial position data and scanning time data, and then divide the sequence into N DICOM image groups, the images in each of the DICOM image group comprising the same phase data. An image data naming module sets the name of each DICOM image group according to the clinical meanings of the phase on the basis of the sequences of the inspection area data, spatial position data and scanningtime data; a data sending module searches a DICOM image group matched with an AI diagnosis model on the basis of the inspection number of the patient and the name of the DICOM image group and sends the DICOM image group to the AI diagnosis model. The invention further provides a method for deducing scanning sequence phase on the basis of DICOM image information. The system and method are used forimproving diagnosis quality and increasing report writing efficiency.

This multipurpose, modular system provides diagnostic-quality, wireless, multichannel monitoring in diverse settings, including interventional procedures guided by X-ray and MRI, with variable electromagnetic interference (EMI) and eliminates the need for multiple detachments / reattachments of patient cables when the patient is moved from one room / procedure to another. The system includes: 1) multiple filterbanks (filtering procedures) for recording both diagnostic-quality (broad-band) signals in the absence of EMI and narrow-band signals in the presence of EMI, with subsequent reconstruction of diagnostic-quality signals from the narrow-band signals; 2) filtering of EMI, using a priori and adaptive criteria about differences between the EMI and physiological signals' characteristics; 3) filtering of the magneto-hydrodynamic effect, using physiological measurements at different distances from the magnet (i.e., at different strengths of magnetic field) and changes in blood flow and blood pressure; and 4) multiple wireless transmitters for increasing reliability and speed (throughput) of the wireless data transmission.

The present invention provides a method for improving diagnostic quality in echocardiography, especially for patients having an elevated heart rate.

Methods and systems are provided for medical imaging systems. In one embodiment, a method for a medical imaging system comprises acquiring emission data during a positron emission tomography (PET) scan of a patient, reconstructing a series of live PET images while acquiring the emission data, and tracking motion of the patient during the acquiring based on the series of live PET images. In this way, patient motion during the scan may be identified and compensated for via scan acquisition and / or data processing adjustments, thereby producing a diagnostic PET image with reduced motion artifacts and increased diagnostic quality.

Methods and systems are provided for medical imaging systems. In one embodiment, a method for a medical imaging system comprises acquiring emission data during a positron emission tomography (PET) scan of a patient, reconstructing a series of live PET images while acquiring the emission data, tracking motion of the patient during the acquiring by determining a per-voxel variation for selected voxels in a current live PET image of the series of live PET images, and outputting an indication of patient motion based on the per-voxel variation for the selected voxels in each live PET image. In this way, patient motion during the scan may be identified and compensated for via scan acquisition and / or data processing adjustments, thereby producing a diagnostic PET image with reduced motion artifacts and increased diagnostic quality.

A system and a method are provided that may be used to determine the suitability of a client for use in medical diagnosis. Multimedia content may be presented on the client and used to elicit responses from a user indicative of the suitability of the client for use in medical diagnosis. The elicited responses may be used to determine the suitability of the client for medical diagnosis.

Methods and systems are provided for de-noising medical images using deep neural networks. In one embodiment, a method comprises receiving a medical image acquired by an imaging system, the medical image comprising colored noise; mapping the medical image to a de-noised medical image using a trained convolutional neural network (CNN); and displaying the de-noised medical image via a display device. The deep neural network may thereby reduce colored noise in the acquired noisy medical image, increasing a clarity and diagnostic quality of the image.

The present invention discloses an endoscopic vagina examination device. The endoscopic vagina examination device comprises a hard tube endoscope, a control host, a monitor and a limiting vagina expander matched with the hard tube endoscope, the control host comprises an image processing system and a light source system, the image processing system and the light source system are both connected with the hard tube endoscope, and an upper end of the control host is provided with an operation panel. The endoscopic vagina examination device solves a problem that the prior colposcopes have more observation blind spots, realizes omnibearing observation, realizes essential breakthrough compared with the colposcopy examination products in the prior art, facilitates operation of medical staff, cangreatly improve examination efficiency, improves an examination effect, helps the medical staff quickly and safely obtain fully prepared examination data, effectively shortens examination time and promotes comfort levels of examinees, built-in parts are all passive products, and the endoscopic vagina examination device avoids cross infection that probably produces, strengthens examination safety simultaneously and promotes diagnostic quality comprehensively.

The invention relates to a multi-path b-ultrasonic image diagnostic system with an intelligent image interpreting device. The system comprises image analog signals, video and audio alerting signals which need to be corrected and alerting signals. The image analog signals are obtained and sent by 1-N path ultrasonic detection sensors to different examined operating parts of a human body, the image analog signals are processed by b-ultrasonic image imaging devices corresponding to the 1-N path to generate recognizable video and audio signals, the recognizable video and audio signals are sent to b-ultrasonic image imaging long-range displays corresponding to the 1-N path to alert respectively, meanwhile, the recognizable video and audio signals are sent to the intelligent image interpreting device to be processed and fed back to the b-ultrasonic image imaging devices corresponding to the 1-N path to generate the video and audio alerting signals which correspond to the 1-N path and need to be corrected, finally, through b-ultrasonic image imaging long-range and short-range displays corresponding to the 1-N path, the alerting signals correcting the images of the examined operating parts movably detected by the ultrasonic detection sensors are generated. The system has the advantages that the operability of a usage method is high, the misdiagnosis rate of the multi-path b-ultrasonic image diagnostic system is low, and the quality and efficiency of diagnoses are high.