759results about "Radiation diagnostic image/data processing" patented technology

Methods of predicting fracture risk of a patient include: obtaining an image of a bone of the patient; determining one or more bone structure parameters; predicting a fracture line with the bone structure parameter; predicting a fracture load at which a fracture will happen; estimating body habitus of the patient; calculating a peak impact force on the bone when the patient falls; and predicting a fracture risk by calculating the ratio between the peak impact force and the fracture load. Inventive methods also includes determining the effect of a candidate agent on any subject's risk of fracture.

The invention provides a method for detecting an X-ray mammary gland lesion image based on feature pyramid network under transfer learning. The method comprises the steps: 1, establishing a source domain data set and a target domain data set; 2, establishing a deformable convolution residual network layer by a deformable convolution and extended residual network module; 3, establishing a multi-scale feature extraction sub-network based on a feature pyramid structure through a feature map up-sampling and feature fusion method in combination with a deformable convolution residual network layer;4, establishing a deformable pooling sub-network sensitive to the focus position; 5, establishing a post-processing network layer to optimize a prediction result and a loss function; and 6, migratingthe training model to a small sample molybdenum target X-ray mammary gland focus detection task so as to improve the detection precision of the network model on the focus in the small sample image. According to the method, a transfer learning strategy is combined to realize focus image processing in a small sample medical image.

In some embodiments, a planning station can receive image data associated with an image(s) of an area of interest within a body of a patient and display the image(s) on a display device. A user can make a selection of a first interventional tool and a second interventional tool about which information is stored in a memory of the planning station. The planning station can execute a simulation viewable on the display device of a treatment plan for disposing the first and second interventional tools in the body of the patient and applying thermal energy from the first and second interventional tools to the body of the patient. The planning station can generate a thermal model of the thermal effect collectively produced on tissue of the patient by the first interventional tool and the second interventional tools and display the thermal model on the display device.

A method for adjusting a field of view for exposure of an X-ray system is provided. The method comprises: capturing an image of a patient on an examining table of the system by an image sensor, wherein the image sensor is placed at a predetermined position in the system; displaying the captured image on a display for selection of a region of interest or a point of interest by a user on the image; automatically determining a target position of an X-ray source in response to the selection of the region of interest or the point of interest on the image, wherein a desired field of view for exposure covering the region of interest or the point of interest is obtained when the X-ray source is located at the target position; and automatically locating the X-ray source at the target position in response to the determination of the target position.

A medical image display system is shown. The medical image display system includes, a fringe scanning type capturing apparatus or a Fourier transformation type capturing apparatus; an image processing section; a display section; and a control section. The capturing apparatus includes, an X-ray source; a first grating and a second grating; a subject table; and an X-ray detector. The image processing section generates a plurality of reconstructed images for diagnosis based on an image signal of a subject captured with the capturing apparatus. The display section displays at least two of the plurality of reconstructed images. The control section detects an abnormal candidate on each of the plurality of reconstructed images and controls display order of the plurality of reconstructed images displayed on the display section based on a result of detecting.

A multi energy, such as dual-energy (“DE”), x-ray imaging system data acquisition and image reconstruction system and method enables optimizing the image contrast of a sample. Using the DE x-ray imaging system and its associated user interface applications, an operator performs a low energy (“LE”) and high energy (“HE”) x-ray scan of the same volume of interest of the sample. The system creates a low-energy reconstructed tomographic volume data set from the set of low-energy projections and a high-energy tomographic volume data set from the set of high-energy projections. This enables the operator to control the image contrast of selected slices, and apply the information associated with optimizing the contrast of the selected slice to all slices in the low-energy and high-energy tomographic data sets. This creates a combined volume data set from the LE and HE volume data sets with optimized image contrast throughout.

Apparatus and methods are described for use with an input angiogram image of a device inserted inside a portion of subject's body, the angiogram image being acquired in the presence of contrast agent. At least one processor (11) includes background-image-generation functionality (13) configured to generate a background image in which a relative value is assigned to a first pixel with respect to a second pixel, at least partially based upon relative values of surroundings of the first pixel and the surroundings of the second pixel in the input image. Cleaned-image-generation functionality (14) generates a cleaned image in which visibility of the radiopaque portions of the device is increased relative to the input image, by dividing the input image by the background image. Output-generation functionality (15) drives a display (16) to display an output based upon the cleaned image. Other applications are also described.

A method and apparatus for automated reconstruction of a 3D computed tomography (CT) volume from a small number of X-ray images is disclosed. A sparse 3D volume is generated from a small number of x-ray images using a tomographic reconstruction algorithm. A final reconstructed 3D CT volume is generated from the sparse 3D volume using a trained deep neural network. A 3D segmentation mask can also be generated from the sparse 3D volume using the trained deep neural network.

Systems and methods for attenuation compensation in nuclear medicine imaging based on emission data are provided. One method includes acquiring emission data at a plurality of energy windows for a person having administered thereto a radiopharmaceutical comprising at least one radioactive isotope. The method also includes performing a preliminary reconstruction of the acquired emission data to create one or more preliminary images of a peak energy window and a scatter energy window and determining a body outline of the person from at least one of the reconstructed preliminary image of the peak energy window or of the scatter energy window. The method further includes identifying a heart contour and segmenting at least the left lung. The method additionally includes defining an attenuation map based on the body outline and segmented left lung and reconstructing an image of a region of interest of the person using an iterative joint estimation reconstruction.

A non-invasive imaging system, including an imaging scanner suitable to generate an imaging signal from a tissue region of a subject under observation, the tissue region having at least one substructure; a signal processing system in communication with the imaging scanner to receive the imaging signal from the imaging scanner; and a data storage unit in communication with the signal processing system, wherein the data storage unit stores an anatomical atlas comprising data encoding spatial information of the at least one substructure in the tissue region, and a pathological atlas corresponding to an abnormality of the tissue region, wherein the signal processing system is adapted to automatically identify, using the imaging signal, the anatomical atlas, and the pathological atlas, a presence of the abnormality or a precursor abnormality in the subject under observation.

The present application provides an image segmentation system, method and apparatus, and a computer readable storage medium. The method comprises: obtaining image data, wherein the image data comprises at least one rib; determining a rib region, wherein the rib region comprises at least a portion of ribs; randomly selecting a rib in the ribs as a target rib; processing the target rib by using a classifier trained through a machine learning method, and obtaining a rib probability map; determining a starting point of the target rib; carrying out model tracking on the target rib based on the ribprobability map and the starting point; and based on a model tracking result, segmenting the target rib to obtain segmented ribs. According to the technical scheme of the present application, model tracking is carried out based on the machine learning method, so that the robustness of the model tracking algorithm is improved and that the ribs can be successfully segmented in the image is ensured.

The invention relates to the technical field of medical equipment, in particular to a medical diagnosis auxiliary system. The medical diagnosis auxiliary system can comprise medical imaging equipment,a sensor and augmented reality equipment, wherein the medical imaging equipment is used for acquiring three-dimensional image data of a diagnosed object; the sensor is used for acquiring registrationparameters of the diagnosed object; the augmented reality equipment comprises a registration unit, a camera shooting unit and an image processing unit; the registration unit is used for generating aregistration model according to the three-dimensional image data and the registration parameters; the camera shooting unit is used for acquiring current image data of the diagnosed object in real time; the image processing unit is used for generating visual image data of the diagnosed object according to the three-dimensional image data and the registration model; and the image processing unit canfuse the visual image data with the current image data to generate augmented reality images. By the system, three-dimensional images corresponding to organs in the body of a patient can be provided in real time on the basis of the perspective of an observer, thus, the observer can clearly position the positional relation of the internal organs and the body surface, and therefore, the diagnosis accuracy of the patient and the treatment effect are improved effectively.

What is disclosed is a system and method for determining a subject's respiratory pattern from a video of that subject. One embodiment involves receiving a video comprising N≧2 time-sequential image frames of a region of interest (ROI) of a subject where a signal corresponding to the subject's respiratory function can be registered by at least one imaging channel of a video imaging device. The ROI comprises P pixels. Time-series signals of duration N are generated from pixels isolated in the ROI. Features are extracted from the time-series signals and formed into P-number of M-dimensional vectors. The feature vectors are clustered into K clusters. The time-series signals corresponding to pixels represented by the feature vectors in each cluster are averaged along a temporal direction to obtain a representative signal for each cluster. One of the clusters is selected. A respiratory pattern is determined for the subject based on the representative signal.

A nuclear medicine (NM) multi-head imaging system is provided that includes a gantry, plural detector units mounted to the gantry, and at least one processor operably coupled to at least one of the detector units. The detector units are mounted to the gantry. Each detector unit defines a detector unit position and corresponding view oriented toward a center of the bore. Each detector unit is configured to acquire imaging information over a sweep range corresponding to the corresponding view. The at least one processor is configured to, for each detector unit, determine plural angular positions along the sweep range corresponding to boundaries of the object to be imaged, generate a representation of each angular position for each detector unit position, generate a model based on the angular positions using the representation, and determine scan parameters to be used to image the object using the model.

Method and/or apparatus embodiments for 3-D cephalometric analysis of a patient according to the application can display reconstructed volume image data from a computed tomographic scan of a patient's head including segmented dentition elements having an initial arrangement from one or more 2D/3D views; can compute and display a plurality of cephalometric parameters for the patient according to the reconstructed volume image data; then use the patient specific cephalometric parameters and population biometry data, to identify one or more maxillofacial/dental abnormalities; and compose patient specific treatment plans to correct selected dentition abnormalities using maxillofacial/dental structure, which can be composed in a final tooth arrangement in a final virtual CT volume. One or more aligners can be generated to incrementally move dentition from the initial arrangement to the final tooth arrangement.

A system for indicating an area of interest on an image, including a source of image data, an image processing unit, a user interface, and a destination, which may be a display. The image data may be ultrasound, X-ray, magnetic resonance imaging, nuclear magnetic resonance imaging, magnetic resonance tomography, computed tomography or surgical image data. The image processing unit may be configured to receive the image data from the source and combine it with a desired overlay pattern selected from a plurality of overlay patterns for indicating an area of interest on the image, which is then displayed on the display. The overlay pattern may include a key with coordinates or labels. Properties of the overlay pattern and the image data may be adjusted independently or automatically.