Dynamic tomosynthesis system and ventilation and perfusion imaging systems and methods employing same
US-2024423577-A1 · Dec 26, 2024 · US
US9307948B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9307948-B2 |
| Application number | US-201414481741-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 9, 2014 |
| Priority date | Mar 13, 2012 |
| Publication date | Apr 12, 2016 |
| Grant date | Apr 12, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
The filtering unit calculates an evaluation matrix by performing filtering on each pixel position of an image representing a hollow structure using a second order partial differential of a function representing a hollow sphere. The evaluation unit calculates an evaluation value of at least one or more of point-like structureness, line-like structureness, and plane-like structureness at the pixel position based on the calculated evaluation matrix.
Opening claim text (preview).
What is claimed is: 1. An image processing apparatus, comprising: a filter that is configured to calculate a Hessian matrix on each pixel position of an image representing a hollow structure by convoluting a filter kernel representing a second order partial differential of a function representing a hollow sphere; and an evaluation unit that is configured to calculate an evaluation value of at least one or more of hollow-point-like structureness, hollow-line-like structureness, and hollow-plane-like structureness at the pixel position based on the calculated Hessian matrix. 2. An image processing apparatus, comprising: a filter that is configured to calculate an evaluation Hessian matrix by performing filtering on each pixel position of an image representing a hollow structure using by convoluting a filter kernel representing a second order partial differential of a function representing a hollow sphere; and a direction discrimination unit that is configured to calculate eigenvalues and eigenvectors by performing eigenvalue analysis on the calculated Hessian matrix and discriminates, based on directions of the calculated eigenvectors, a principal axis direction of a hollow-line-like structure or a normal direction of a hollow-plane-like structure. 3. The image processing apparatus as claimed in claim 1 , wherein the function representing the hollow sphere is expressed by Formula (3) given below: f ( r ) = δ ( r - R ) r = x 2 + y 2 + z 2 } ( 3 ) where, x, y, z are three-dimensional coordinates in real space and R is the radius of the hollow sphere. 4. The image processing apparatus as claimed in claim 1 , wherein the filter calculates respectively, with respect to functions representing the hollow sphere in a plurality of sizes, Hessian matrixes by using filters representing a second order partial differential of the function representing each hollow sphere. 5. The image processing apparatus as claimed in claim 1 , wherein the filter calculates the Hessian matrix in Fourier space. 6. The image processing apparatus as claimed in claim 1 , wherein the image is a medical image, and the hollow structure is a bronchus. 7. An image processing method performed by a computer having a processor and a memory, comprising: calculating a Hessian matrix by performing filtering on each pixel position of an image representing a hollow structure by convoluting a filter kernel representing a second order partial differential of a function representing a hollow sphere; and calculating an evaluation value of at least one or more of hollow-point-like structureness, hollow-line-like structureness, and hollow-plane-like structureness at the pixel position based on the calculated Hessian matrix. 8. A non-transitory computer readable recording medium on which is recorded an image processing program that causes a computer to function as, comprising: a filter that is configured to calculate a Hessian matrix on each pixel position of an image representing a hollow structure by convoluting a filter kernel representing a second order partial differential of a function representing a hollow sphere; and an evaluation unit that is configured to calculate an evaluation value of at least one or more of hollow-point-like structureness, hollow-line-like structureness, and hollow-plane-like structureness at the pixel position based on the calculated Hessian matrix. 9. The image processing apparatus as claimed in claim 2 , wherein the function representing the hollow sphere is expressed by Formula (3) given below: f ( r ) = δ ( r - R ) r = x 2 + y 2 + z 2 } ( 3 )
Computed x-ray tomography [CT] · CPC title
Lung · CPC title
for diagnosis of bone · CPC title
for diagnosis of blood vessels, e.g. by angiography · CPC title
Transmission computed tomography [CT] · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.