Hitachi Medical Corporation

General Electric Company

Ge Medical Systems Global Technology Company, LLC

Yasuo Omi

Osamu Miyazaki

Koichi Hirokawa

Taiga Goto

Tsuyoshi Mitake

Yoshiaki Sugaya

Hasnine Haque

Susumu Yasuda

Masahiko Aoyagi

Shotaro Fuchibe

Ryo Takagi

In accordance with certain embodiments of the present disclosure an apparatus includes: an inference section for performing inference using a learned model. The learned model is generated by multi-channel learning processing of a multi-channel image containing image information on each of three one-channel images (an original image, a histogram-equalized image, and edge-enhanced image), and ground-truth data CD The apparatus also inclides a multi-channel image producing section for producing a multi-channel image containing image information on each of three one-channel images (an original image, a histogram-equalized image, and an edge-enhanced image) of a patient. The inference section inputs the multi-channel image to the learned model, performs the inference, and outputs an output image as output data.

Inference apparatus, medical apparatus, and program

An image processing method for registering first and second images including the same subject is provided. The method includes the repeating the following steps multiple times: a first step including determining feature vectors related to gradients of pixels values at coordinates on the first and second images for each of the coordinates, a second step including calculating for all mutually corresponding coordinates on the first and second images, correlation values each equivalent to a value obtained by an N-th (where N is a natural number) power of an absolute value of an inner product of the feature vectors at the coordinates and determining an evaluation value including an integrated value of the correlation values calculated for each of the coordinates, and a third step including changing the second image in such that the evaluation value becomes larger.

Image processing method and apparatus and program

An image analysis system that analyzes an image of an object's organ having an anatomically symmetric shape includes:

Image analyzing system and method

An image processing method includes identifying a body region in a tomographic image based on pixel values within the tomographic image, extracting a bone muscle region corresponding to essential parts of bones and muscles based on bone muscle pixels having pixel values corresponding to the bones or muscles in the body region, searching boundary points of the bone muscle region from outside a region surrounding the extracted bone muscle region to inside the region, creating a bone-muscle region outer peripheral profile line by joining only boundary points at which each index related to at least one of a length and a slope of a line segment connecting between the adjoining boundary points of the searched boundary points satisfies a predetermined condition, and extracting a visceral fat region comprised of fat pixels having pixel values corresponding to fat in a region lying inside the bone-muscle region outer peripheral profile line.

Image processing method and image processing apparatus, and program

There are provided a function image display method and device capable of performing analysis of biological function information by acquiring from a single image, information obtained from a tomogram and information obtained from a plurality of function images without need of observing the plurality of function images and the tomogram by successively moving the eye line, and easily making judgment about the danger degree of the biological function abnormality. A plurality of function images each displayed by a unique and arbitrary gradation color scale are combined with an arbitrary weight or an image obtained by calculating the inter-function images is displayed or these are combined with the tomogram with an arbitrary weight. Furthermore, an operator can arbitrarily set and modify the range to which weight is applied, the range for displaying the gradation color scale, and the range to be combined.

Function image display method and device

A radiographing apparatus according to an aspect of the present invention is characterized in that an image processing device comprises an acquisition device which acquires projection data of a first energy spectrum and projection data of a second energy spectrum, and a synthetic image generating device which synthesizes a first image on the basis of the projection data of the first energy spectrum, and a second image on the basis of the projection data of the second energy spectrum according to a predetermined synthetic condition, and generating a synthetic image, and a display device displays the generated synthetic image.

Radiographing apparatus and image processing program

An image processing device according to the present invention which includes image creating means for creating each of a smoothened image and a sharpened image with respect to at least a part of image data, and mixed image creating means for mixing the smoothened image and the sharpened image created by the image creating means to create a mixed image, including: analysis quantity calculating means for calculating an analysis quantity on plural pixel values in each matrix that surrounds each pixel of the image data and has any matrix size; control means for controlling the mixing ratio between the smoothened image and the sharpened image in the mixed image creating means in accordance with the analysis quantity calculated by the analysis quantity calculating means; and display means for displaying the mixed image that is controlled by the control means and output from the mixed image generating means.

Image processing device and method

According to the present invention, a Fourier transformation is executed on a time-concentration curve for an inflow artery and a time-concentration curve for each tissue on the basis of a dynamically acquired tomogram. An inverse filter is then calculated from the Fourier-transformed time-concentration curve for the inflow artery. The Fourier-transformed time-concentration curve for each tissue is multiplied by the inverse filter to generate a transfer function for the tissue. The thus generated transfer function for each tissue is used to calculate biological function information. Thus, if biological function information on an organ to be analyzed is to be obtained from a tomogram provided by a computer tomograph, very quantitative biological function information can be obtained at a low contrast rate. In particular, it takes only a minimum calculation time to obtain biological function information.

Growing community of inventors

Tokyo, Japan

Yasuo Omi