81results about How to "Improve diagnostic quality" patented technology

The invention discloses an auxiliary cancer diagnosis method based on digital pathological images. The method comprises the following steps that 1, a section scanner is used for scanning digital pathological sections into images; 2, a digital pathological image database and a digital pathological image label library are built; 3, a digital pathological image automatic diagnosis model and a digital pathological image retrieval model are built; 4, the digital pathological image automatic diagnosis model is adopted for diagnosing an unknown lesion type and digital pathological sections, a diagnosis result is obtained, and meanwhile a plurality of lesion areas are selected; 5, the digital pathological image retrieval model are adopted for searching for similar lesion areas; 6, the diagnosis result, the typical lesion areas and other information are fed back to a doctor for auxiliary diagnosis. The digital pathological image automatic diagnosis model and the digital pathological image retrieval model are combined, previously-diagnosed similar cancer cases are provided for a doctor as references while a computer is used for predicting the lesion type of the digital pathological sections, and the purposes of improving the cancer diagnosis quality and improving the diagnosis capacity of the doctor are achieved.

A system and appertaining method isolates a hardware or user error in a software controlled apparatus e.g., an NMR-apparatus. A diagnostic function is added to an event log that uses a causality model to analyze the event log. A series of events in the event log is evaluated by comparing the events with at least one of a number of root cause related patterns, and a best match of these patterns is used to assign a root cause for the error. Various repair actions may be associated based on a probabilistic model. Additional information may be utilized to modify or improve respective probabilities associated with causes and/or repair actions. This additional information may utilize other automated diagnostic information or may query users for additional information.

A method for diagnostic imaging with reduced contrast agent dose uses a deep learning network (DLN) [114] that has been trained using zero-contrast [100] and low-contrast

images as input to the DLN and full-contrast images [104] as reference ground truth images. Prior to training, the images are pre-processed [106, 110, 118] to co-register and normalize them. The trained DLN [114] is then used to predict a synthesized full-dose contrast agent image [116] from acquired zero-dose and low-dose images.

An X-ray examination apparatus includes an X-ray source, an X-ray detector and an exposure control system. The exposure control system is arranged to control the X-ray source so as to perform a test exposure at a low X-ray dose and to perform an X-ray exposure at a higher X-ray dose. The X-ray detector applies a control signal resulting from the test exposure to the exposure control system and the X-ray source is adjusted on the basis of this control signal. The X-ray exposure produces an X-ray image and the X-ray detector supplies an image signal representing this X-ray image. The exposure control system is arranged to adjust the X-ray detector to a low spatial resolution during the test exposure and to a high spatial resolution during the X-ray exposure. The X-ray detector preferably includes a sensor matrix having sensor elements arranged in columns and rows. The spatial resolution is adjusted by deriving the control signal and the image signal from large and small groups of sensor elements, respectively.

The invention provides a skin image analysis management system which is used for a skin class department of a medical unit and participating in a clinical diagnostic process of a skin class disease. According to the skin image analysis management system, skin image data is obtained and managed, through a skin mirror device, an electronic skin image which has high definition is obtained, a work station is used for rapidly finishing an electronic diagnostic report with the skin image data, a diagnostic result and a diagnostic process are stored in a personal computer (PC) machine and / or a server end, and the skin diagnostic process is enabled to have objective skin image data, a diagnostic report and other objective basis.

The present invention relates to a method of performing dynamic contrast enhanced magnetic resonance imaging of an object (10) with signal separation for water and fat, the method comprising acquiring magnetic resonance datasets in the k-space using Dixon acquisition in a chemical shift encoding space and dynamic time resolution in a dynamic time space, wherein the dataset acquisition is performed employing undersampling, wherein the method further comprises: applying a compressed sensing reconstruction technique in the k-space, the chemical shift encoding space and the dynamic time space, said compressed sensing reconstruction resulting in reconstructed datasets, —performing Dixon reconstruction on the reconstructed datasets and dynamic contrast analysis on the Dixon reconstructed datasets.

A remote access medical image exchange system utilizes a decentralized, i.e., self-organizing, distribution system combined with bid queues to establish a market place which allows for continuously negotiated prices with control (over who reads the images, when they are read and what the fee will be for such a reading) being placed in the hands of the patient/gatekeeper and the diagnostic physician.

The invention relates to an upper body MRI scanner comprising a magnet arrangement for producing a horizontally oriented homogeneous main magnetic field, said magnet arrangement being designed to examine the upper body of a standing patient. An image acquisition unit is provided for continuously creating upper body images of the standing patient. A quality checking unit is designed for automatically determining a quality metric characterizing the quality of the upper body images. An imaging controller connected to the image acquisition unit and the quality checking unit is provided for activating the image acquisition unit and outputting signals for influencing the position and/or behavior of the patient as a function of the characteristic quality metric. An output unit connected to the image acquisition unit is used for displaying and/or storing at least some of the upper body images.

The invention provides a capsule endoscopy image retrieval method based on visual vocabularies and local descriptors. The method concretely comprises the following steps of: building an image library, wherein the image library comprises standard case images and images to be retrieved; converting capsule endoscopy images from an RGB (Red, Green and Blue) color space into an HSI (Hue, Saturation and Intensity) color space, performing quantization processing and extracting a color histogram; extracting an LBP (Local Binary Patterns) texture histogram of the capsule endoscopy images; performing weighing blending on color features and texture features to obtain the visual vocabularies of the images; extracting Sift (Scale invariant feature transform) feature descriptors of the capsule endoscopy images; and performing similarity testing to obtain retrieval results. The method provided by the invention is used for capsule endoscopy image processing; the work intensity of film reading doctors is effectively reduced; and the diagnosis efficiency is improved.

The invention relates to a sensor element (10) comprising an acoustic emission sensor (11) for detecting acoustic emission (41) for the aim of simplifying measurement tasks. The sensor element comprise a second sensor (12) for a second measured variable (42, 45), with the second sensor (12) being different from the acoustic emission (41). Furthermore, the sensor element (10) comprising the acoustic emission sensor (11) for detecting the acoustic emission (41) is provided and comprises an interface (24, 28) for receiving an external sensor signal (15, 16).

The invention relates to the technical field of ultrasonic imaging, in particular to an ultrasonic system and a multi-image imaging method thereof. The ultrasonic system comprises a conventional scanning and processing module and a user interface assembly. The multi-image imaging method is implemented by adopting range customization of a display area, non-image content automatic concealment, single-image zooming and recovering. According to the method, the size of the display area is increased when the multi-image display or image depth is large, the problem that the resolution is lowered under normal conditions is avoided or reduced, and working efficiency and diagnosis quality of a doctor are improved; particularly, on the portable ultrasonic system, the size of the display screen is limited, the size of a display screen is reasonably utilized, and the method is of great significance in image display.

The invention discloses a constant current stimulator and a current stimulator system. The constant current stimulator comprises an MCU, a pulse control circuit, a high voltage generation circuit, a constant current generation control circuit and a 485 bus interface circuit, wherein the 485 bus interface circuit realizes communication between the MCU and a host; controlled by the MCU, the pulse control circuit outputs pulse current with adjustable pulse width, frequency and direction as stimulated current; the constant current generation control circuit receives the control signal of the MCU to determine the amount of the stimulated current and ensures constant stimulated current; and the high voltage generation circuit is electrically connected with the pulse control circuit and applies direct current voltage on the pulse control circuit to generate strong enough stimulus intensity.

The invention is suitable for the technical field of signal processing, and provides a heart sound signal classification method and terminal equipment. The method comprises the steps that heart soundsignals are obtained, the heart sound signals are decomposed and reconstructed, and second heart sound signals of the heart sound signals are extracted; the characteristic frequency of the second heart sound signals is extracted, and the power spectrum density of the second heart sound signals is determined according to the characteristic frequency; the second heart sound signals are classified according to the power spectrum density, and normal heart sound signals and abnormal heart sound signals are obtained. In this way, the normal heart sound signals and the abnormal heart sound signals can be distinguished, a doctor can be assisted in conducting decision and diagnosis, simple, definite and true information is provided for the doctor, the due role of intensive care is played, the diagnosis quality and the level of emergency are improved, the effective treatment time is gained for patients suffering from heart diseases, and the rescue and curative rate for the patients suffering from the heart diseases is increased.

The invention provides a mental disease iconography automatic reporting system. The system is characterized in that a data analysis module obtains measurement data of each brain area of a patient froma brain quantitative post-processing system and analyzes the measurement data; a data comparison module identifies an age group of the patient, extracts the threshold range of each piece of brain area data of the age group from a healthy brain area structure parameter database module, when the measured data is higher than an upper limit value or lower than a lower limit value, the measured data is abnormal data, and when the measured data is within the threshold range, the measured data is normal data; when the abnormal data is received, a report generation module automatically generates a discovery diagnosis report based on the abnormal data and pathological state data of each abnormal brain area in a clinical symptom knowledge base module; when the normal data is received, a discovery-free diagnostic report is automatically generated. The invention further discloses a mental disease iconography automatic reporting method. The system is advantaged in that diagnosis accuracy of mentaldisease patients can be improved, and labor intensity of doctors is reduced.

The invention relates to a micro invasion endoscope of upper urinary tract disease diagnosis and treatment, which is a novel ureter endoscope formed by a terminal 2 of the bendable endoscope body, a rigid endoscope body 1 and operation keys 4 and 5 at the back of an operation handle 3. Most of the endoscope body is rigid structure, so the terminal of the endoscope is the same with the terminal of the traditional and soft ureter endoscope, which can be bended by 180 DEG C towards two opposite direction. The direction and angle of bending movement can be controlled by the operation key 4 at the back of the handle and operated conveniently. The invention has the advantages of the traditional ureter endoscope and soft ureter endoscope, is operated conveniently, no view and operation blind areas and the view is much clearer under the endoscope, which result in large improvement in the upper urinary tract disease diagnosis and treatment. While the operation key 5 can control relative sliding of the bendable endoscope body terminal and rigid endoscope body, so to reach the rigid structure of whole endoscope body during the endoscope entry process and protect the terminal of the soft endoscope body.

The invention relates to a classification method for processing electronic medical record hybrid data based on a crowd network, wherein an existing numerical data processing method can be effectivelyutilized for improving classification efficiency of the hybrid data in the electronic medical record, and improving diagnosis quality and efficiency of a doctor. The method comprises the steps of 1, extracting an original electronic medical record dataset in an original electronic medical record database; 2, performing symbol type data determining on the cleaned electronic medical record dataset,and performing numerical data conversion on the symbol type data; 3, extracting a key characteristic field in the original electronic medical record dataset, and training a classification diagnosis model; and 4, extracting a key characteristic field in the to-be-diagnosed electronic medical record, inputting into the trained model, and outputting a classification result and a disease suffering probability. The method can effectively mine valuable information in the electronic medical record for helping the doctor in quick condition diagnosis, thereby realizing an important theoretical meaningand high application value.

A method for operating a tank leakage diagnosis device, especially of a motor vehicle, volatile fuel (to be degassed) being temporarily stored using an adsorption filter of known absorption capacity or absorption characteristics, and the adsorption filter being regenerated from time to time by purging, using fresh air, to avoid faulty measurements in the tank leakage diagnosis, in particular at elevated fuel degassing. It is provided that the adsorption filter be purged, and, in this context, the volatile fuel removed from the adsorption filter over a predefined time span be integrated, and from that, the loading of the adsorption filter with the volatile fuel, changing during the time span, is ascertained, from the absorption capacity and the absorption characteristics of the adsorption filter, as well as the integrated fuel quantity or the changing loading. The quantity of fuel to be degassed supplied to the adsorption filter from the fuel container in the time span is calculated, and, as a function of the calculated quantity of fuel supplied to the adsorption filter, an intervention is undertaken at the tank leakage diagnosis device.