Abstract:
A processor encodes a target image to derive at least one first feature amount indicating an image feature for an abnormality of a region of interest included in the target image. In addition, the processor encodes the target image to derive at least one second feature amount indicating an image feature for an image in a case in which the region of interest included in the target image is a normal region.
Abstract:
A region extraction unit extracts first and second shape-invariant regions corresponding to each other from first and second three-dimensional images acquired by an MRI apparatus. A first registration unit acquires a first deformation vector by performing rigid registration between the first and second shape-invariant regions. A second registration unit acquires a second deformation vector by performing non-rigid registration between the first and second three-dimensional images in each shape-invariant region. A magnetic field distortion vector calculation unit calculates a magnetic field distortion vector, which represents relative magnetic field distortion between the first and second three-dimensional images based on the first and second deformation vectors.
Abstract:
A label adding unit adds labels to structures such as a body surface region, a lung region, bronchi, and pulmonary nodules of a human extracted by a structure extraction unit from a three-dimensional image of a chest. An image display control unit displays the three-dimensional image by volume rendering on a display unit. At this time, a label display determination unit determines at least one label to be displayed with the volume rendering image to be displayed based on the opacity during the volume rendering display. A label display control unit displays the determined label with the volume rendering image on the display unit.
Abstract:
A foreground statistic with respect to a distribution of image values in a foreground region and a background statistic with respect to a distribution of image values in a background region are calculated. Image values of a plurality of input images that are captured at different times are corrected based on the foreground statistics and the background statistics which are obtained by processing the input images.
Abstract:
A brain image normalization apparatus, having a processor configured to: detect at least four reference landmarks of a left eye, a right eye, a diencephalon, a fornix, a corpus callosum, a left hippocampus, and a right hippocampus from a brain image including a brain of a subject; perform registration between the detected reference landmarks and reference landmarks corresponding to the detected reference landmarks included in a standard brain image; and normalize the brain image based on a result of the registration.
Abstract:
A liver region extraction unit and a structural element extraction unit extracts the liver region and structural elements, such as the hepatic artery and the hepatic vein, from a three-dimensional image, and a surface data generation unit generates surface data of the liver region and surface data of the structural elements. A pattern adding unit adds a textured pattern to at least one of the surfaces of the liver region and the structural elements, and a data generation unit generate three-dimensional model data by combining the surface data of the liver region and the surface data of the structural elements after the addition of the textured pattern. A three-dimensional model making device makes a three-dimensional model of the liver based on the three-dimensional model data.
Abstract:
A diagnostic endoscopic imaging support apparatus includes a three-dimensional image data obtaining section that obtains three-dimensional image data of a subject, a tubular tissue shape data obtaining section that extracts and obtains tubular tissue shape data representing a shape of a tubular tissue in the subject from the three-dimensional image data obtained by the three-dimensional image data obtaining section, an endoscope route data obtaining section that obtains endoscope route data representing a route of an endoscope inserted into the subject, and a matching section that performs matching between the tubular tissue shape data and the endoscope route data.
Abstract:
A processor acquires a surgical field image of a surgical field containing a target area inside the body and an ultrasound probe; acquire a first three-dimensional image based on an ultrasound image group; derive first positional relationship information indicating a position and orientation of the first three-dimensional image within the surgical field image; derive second positional relationship information indicating a positional relationship between a position within the first three-dimensional image and a position within a second three-dimensional image by performing image analysis on the first three-dimensional image and the second three-dimensional image, the second three-dimensional image having been generated on the basis of a tomographic image group; and generate a composite image with preparation information superimposed onto a corresponding position that corresponds to the target area within the surgical field image on the basis of the first positional relationship information and the second positional relationship information.
Abstract:
A processor of a medical support device is configured to acquire a captured image that is captured by an extracorporeal camera provided outside a body of a subject and in which a medical device whose insertion portion is inserted into the body of the subject and a marker which is provided at a portion of the medical device excluding the insertion portion and is image-recognizable are included in an imaging range; derive position and posture information including at least one of a position or a posture of the medical device in the captured image based on the marker; and execute a control of displaying, on a display unit, a composite image in which medical support information is superimposed at a position specified in the captured image based on the position and posture information.
Abstract:
An initial registration unit performs initial registration between an intraoperative image and simulation information. A positional information obtaining unit obtains positional information indicating a relative positional difference between the intraoperative image after the initial registration and a newly obtained intraoperative image based on an unchanged position which is not changed during surgery included in the intraoperative images. A superimpose display unit registers the simulation information with the new intraoperative image based on the positional information and displays, on a display, the simulation information superimposed on the new intraoperative image.