Supervised machine learning technique for reduction of radiation dose in computed tomography imaging
US-2015201895-A1 · Jul 23, 2015 · US
US10064591B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10064591-B2 |
| Application number | US-201515322697-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 9, 2015 |
| Priority date | Jul 9, 2014 |
| Publication date | Sep 4, 2018 |
| Grant date | Sep 4, 2018 |
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.
A novel method for simulating radiation dose reduction that enables previews of low-dose x-ray projection images, low-dose computed tomography images and/or cone-beam CT images. Given an existing projection or set of projections of the patient acquired at a nominal dose, the method provides a means to produce highly accurate preview images that accurately reflect the image quality associated with reduced radiation dose. The low-dose preview image accounts for characteristics of the imaging system, including blur, variations in detector gain and electronic noise, and does so in a manner that yields accurate depiction of the magnitude and correlation of image noise in the preview images. A calibration step may be included to establish the system-specific relationship between the mean and variance in detector signal, and incorporate an accurate model for system blur such that correlations in the resulting LDP images are accurate.
Opening claim text (preview).
We claim: 1. A low-dose x-ray preview image method, comprising: performing, by at least one processor, an initial scan of a patient at a pre-selected amount of x-ray exposure with an x-ray imaging device; creating, by the at least one processor, at least one initial image projection of said patient based on said initial scan; injecting, by the at least one processor, correlated noise into said at least one initial image projection of said initial scan of said patient; reconstructing, by at least one processor, said at least one initial image projection according to an algorithm specific to a task of said patient and based of said detected signal and said injecting of said correlated noise; displaying, by at least one processor, at least one low-dose preview image based on said reconstruction of said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise; and enabling, by at least one processor, a selection of said at least one low-dose preview image based on said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise for at least one subsequent scan. 2. A low-dose x-ray preview image method according to claim 1 , wherein said correlated noise represents a lower amount of x-ray exposure than said initial scan of said patient at said pre-selected amount of x-ray exposure. 3. A low-dose x-ray preview image method according to claim 2 , wherein each of said at least one low-dose preview image represents at least one of a variation of detector blur and a variation of detector gain. 4. A low-dose x-ray preview image method according to claim 1 , wherein each of said at least one initial preview image are injected with a varying amount of said correlated noise. 5. A low-dose x-ray preview image method according to claim 1 , wherein said at least one low-dose preview image is a preview of at least one of a radiographic image, a fluoroscopic image, a tomosynthesis reconstruction, a computed tomography reconstruction, and a cone-beam computed tomography reconstruction. 6. A low-dose x-ray preview image method according to claim 1 , wherein the correlated noise includes at least one of a quantum noise and an electronic noise. 7. A low-dose x-ray preview image method according to claim 1 , wherein said reconstruction includes at least one of a filtered backprojection and a model-based image reconstruction. 8. A low-dose x-ray preview image method according to claim 1 , wherein said reconstruction discards said at least one initial image projection of said patient based on said initial scan. 9. A low-dose x-ray preview image method according to claim 1 , wherein said x-ray imaging device includes at least an emitter and a detector. 10. A low-dose x-ray preview image method according to claim 9 , wherein said detector is a flat panel detector. 11. A low-dose x-ray preview image device, comprising: an x-ray imaging device; at least one storage unit in communication with said x-ray imaging device; at least one data processor in communication with said at least one storage unit and said x-ray imaging device; and at least one display device in communication with said at least one storage unit and said at least one data processor; wherein said at least one processor is configured to: perform an initial scan of a patient at a pre-selected amount of x-ray exposure with said x-ray imaging device; create at least one initial preview image of said patient based on said initial scan; inject correlated noise into said at least one initial image projection of said initial scan of said patient; reconstruct said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise; display, at said at least one display device, an at least one low-dose preview image based on said reconstruction of said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise; and enable, at said at least one display device, a selection of said at least one low-dose preview image based on said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise for at least one subsequent scan. 12. A low-dose x-ray preview image device according to claim 11 , wherein said correlated noise represents a lower amount of x-ray exposure than said initial scan of said patient at said pre-selected amount of x-ray exposure. 13. A low-dose x-ray preview image device according to claim 12 , wherein each of said at least one low-dose preview image represents at least one of a variation of detector blur and a variation of detector gain. 14. A low-dose x-ray preview image device according to claim 11 , wherein each of said at least one initial image projection are injected with a varying amount of said correlated noise. 15. A low-dose x-ray preview image device according to claim 11 , wherein said at least one low-dose preview image is a preview of at least one of a radiographic image, a fluoroscopic image, a tomosynthesis reconstruction, a computed tomography reconstruction, and a cone-beam computed tomography reconstruction. 16. A low-dose x-ray preview image device according to claim 11 , wherein the correlated noise includes at least quantum noise and an electronic noise. 17. A low-dose x-ray preview image device according to claim 11 , wherein said reconstruction includes at least one of a filtered backprojection and a model-based image reconstruction. 18. A low-dose x-ray preview image device according to claim 11 , wherein said reconstruction discards said at least one initial image projection of said patient based on said initial scan. 19. A low-dose x-ray preview image device according to claim 11 , wherein said low-dose x-ray image projection device includes at least an emitter and detector. 20. A low-dose x-ray image projection device according to claim 19 , wherein said detector is a flat panel detector. 21. A non-transitory computer readable medium comprising software, which when executed by a computer, causes the computer to: perform, by at least one processor, an initial scan of a patient at a pre-selected amount of x-ray exposure with an x-ray imaging device; create, by the at least one processor, at least one initial image projection of said patient based on said initial scan; inject, by the at least one processor, correlated noise into said at least one initial image projection of said initial scan of said patient; reconstruct, by at least one processor, said at least one initial image projection according to an algorithm specific to a task of said patient and based said detected signal and said injecting of said correlated noise; display, by at least one processor, at least one low-dose preview image based on said reconstruction of said at least one initial image projection according to an algorithm specific to a task of said patient and based on said detected signal and said injecting of said correlated noise; and enable, by at least one processor, a selection of said at least one low-dose preview image based on said at least one initial image projec
Tomographic reconstruction from projections · CPC title
Inverse problem, i.e. transformations from projection space into object space · CPC title
Image preprocessing, e.g. calibration, positioning of sources or scatter correction · CPC title
Devices using data or image processing specially adapted for radiation diagnosis · CPC title
Displaying means of special interest · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.