摘要:
An image processing device includes an image sequence acquisition section (101), a deformation information calculation section (104) that calculates deformation information about images, a feature area detection section (106) that performs a feature area detection process, an identicalness determination section (109) that performs an identicalness determination process on an ith feature area and an (i+1)th feature area based on the deformation information about an ith image and an (i+1)th image, and a summarization processing section (113) that performs an image summarization process, the deformation information calculation section (104) calculating the deformation information based on an ith deformation estimation target area that includes an area of the ith image other than the ith feature area, and an (i+1)th deformation estimation target area that includes an area of the (i+1)th image other than the (i+1)th feature area.
摘要:
Provided are an image processing apparatus, etc., that can accurately identify abnormalities in a microstructure on a surface of an examination target, such as a mucous membrane, even when contour edges of the examination target are present in an intraluminal image. An image processing apparatus 1 includes a contour edge region extracting unit 110 that extracts a contour edge region of an examination target from an image obtained by capturing inside of a lumen of a living body; an examination region setting unit 120 that sets an examination region in the image so as not to include the contour edge region; and an abnormal structure identifying unit 130 that identifies whether a microstructure of a surface of the examination target is abnormal, based on texture information of the examination region.
摘要:
An image processing device includes an image sequence acquisition section (101), a deformation information calculation section (104) that calculates deformation information about images, a feature area detection section (106) that performs a feature area detection process, an identicalness determination section (109) that performs an identicalness determination process on an ith feature area and an (i+1)th feature area based on the deformation information about an ith image and an (i+1)th image, and a summarization processing section (113) that performs an image summarization process, the deformation information calculation section (104) calculating the deformation information based on an ith deformation estimation target area that includes an area of the ith image other than the ith feature area, and an (i+1)th deformation estimation target area that includes an area of the (i+1)th image other than the (i+1)th feature area.
摘要:
A method for three-dimensional segmentation of a target in multislice images of volumetric data includes determining a center and a spread of the target by a parametric fitting of the volumetric data (201), and determining a three-dimensional volume by non-parametric segmentation of the volumetric data iteratively refining the center and spread of the target in the volumetric data (202).
摘要:
As stereotactic images are digitised, the method consists in the following steps: selecting (400) a target pixel in a target region of interest, generating (401), around the selected pixel, a target window of selected dimensional characteristics and containing the said target region of interest, determining (402) in a second image, based on a predetermined criterion of selection, a set of pixels, generating (403) around each selected pixel a second window of the same dimensional characteristics as the said target window, effecting a correlation processing (404) between the grey levels of the pixels of each second window and the grey levels of the target window pixels, so as to obtain a correlation value for each second window, and identifying the region of interest homologous with the target region of interest based on the analysis of the whole set of correlation values obtained, so as to minimise the risks of pairing errors between homologous regions of interest. Then the element of interest is located from the positions of the two homologous regions.
摘要:
Systems and methods that facilitate the presentation and assessment of selected features in projection and/or reconstructed breast images, such as calcifications that meet selected criteria of size, shape, presence in selected slice images, distribution of pixels that could be indicative of calcification relative to other pixels or of other image features of clinical interest.