Medical image analysis method, medical image analysis device, and medical image analysis system
US-2024281969-A1 · Aug 22, 2024 · US
US9436994B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9436994-B2 |
| Application number | US-201013375171-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 13, 2010 |
| Priority date | Jun 2, 2009 |
| Publication date | Sep 6, 2016 |
| Grant date | Sep 6, 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.
An image processing apparatus comprising, boundary extraction means for detecting boundaries of retina layers from a tomogram of an eye to be examined, exudate extraction means for extracting an exudate region from a fundus image of the eye to be examined, registration means for performing registration between the tomogram and the fundus image, and calculating a spatial correspondence between the tomogram and the fundus image, specifying means for specifying a region where an exudate exists in the tomogram using the boundaries of the retina layers, the exudate region, and the spatial correspondence, likelihood calculation means for calculating likelihoods of existence of the exudate in association with the specified region, and tomogram exudate extraction means for extracting an exudate region in the tomogram from the specified region using the likelihoods.
Opening claim text (preview).
The invention claimed is: 1. An image processing apparatus comprising: at least one memory; and at least one processor to perform operations comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; extracting an exudate region from a fundus image of the eye to be examined; specifying a region where an exudate exists in the tomogram using the extracted boundaries of the retina layers and the extracted exudate region; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 2. The apparatus according to claim 1 , wherein the operations further comprise deciding a region in the tomogram corresponding to the exudate region extracted from the fundus image by projecting the extracted exudate region onto the tomogram, and wherein the region where the exudate exists is specified in the tomogram based on the boundaries of the retina layers included in the corresponding region and a surrounding region thereof. 3. An image processing apparatus comprising: at least one memory; and at least one processor to perform operations comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; specifying a region where an exudate exists in the tomogram using a fundus image of the eye to be examined and the extracted boundaries of the retina layers; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 4. The apparatus according to claim 1 , wherein in the calculating, the likelihoods are calculated according to the distances from a reference position, wherein the reference position is decided based on the boundaries of the retina layers in the specified region. 5. The apparatus according to claim 1 , wherein in the calculating, likelihoods of pixels in the specified region are decided by acquiring, from a data server which stores a set of likelihoods of respective pixels that exist between the boundaries of the retina layers in association with the distances between the boundaries of the retina layers, the set of likelihoods according to the distances between the boundaries of the retina layers in the specified region. 6. The apparatus according to claim 1 , wherein in the extracting an exudate region in the specified region of the tomogram, respective pixels which are included in the specified region and have the likelihoods larger than a related threshold are extracted as the exudate region in the tomogram. 7. The apparatus according to claim 1 , wherein in the extracting an exudate region in the specified region of the tomogram, at least one of intensities of pixels and output values of a filter configured to emphasize a region in which intensities are higher than a surrounding region are used, in addition to the likelihoods, and pixels larger than related thresholds in association with the likelihoods and at least one of the intensities and the output values of the filter are extracted as the exudate region in the tomogram. 8. The apparatus according to claim 1 , wherein when a number of coupled pixels is smaller than a coupling threshold or a degree of circularity is lower than a predetermined degree in a coupled region obtained by coupling pixels extracted as an exudate, the coupled region as the exudate region in the tomogram is not extracted. 9. An image processing method comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; extracting an exudate region from a fundus image of the eye to be examined; specifying a region where an exudate exists in the tomogram using the extracted boundaries of the retina layers, and the extracted exudate region; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 10. An image processing method comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; specifying a region where an exudate exists in the tomogram using a fundus image of the eye to be examined and the extracted boundaries of the retina layers; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 11. A non-transitory computer-readable storage medium storing a computer program for making a computer perform operations comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; extracting an exudate region from a fundus image of the eye to be examined; specifying a region where an exudate exists in the tomogram using the extracted boundaries of the retina layers and the extracted exudate region; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 12. A non-transitory computer readable storage medium storing a computer program for making a computer perform operations comprising: extracting boundaries of retina layers from a tomogram of an eye to be examined; specifying a region where an exudate exists in the tomogram using a fundus image of the eye to be examined and the extracted boundaries of the retina layers; calculating, according to distances between the extracted boundaries of the retina layers, likelihoods of existence of the exudate in the specified region of the tomogram; and extracting, according to voxels having intensities higher than a threshold and the calculated likelihoods, an exudate region in the specified region of the tomogram. 13. The apparatus according to claim 1 , wherein the operations further comprise performing registration between the tomogram and the fundus image, and wherein the region where an exudate exists is specified in the tomogram after the registration. 14. The apparatus according to claim 3 , wherein the operations further comprise performing registration between the tomogram and the fundus image, and wherein the region where an exudate exists is specified in the tomogram after the registration. 15. The image processing method according to claim 9 , further comprising performing registration between the tomogram and the fundus image, wherein the region where an exudate exists in the tomogram is specified by the specifying after the performance of the registration. 16. The image processing method according to claim 10 , further comprising performing registration between the tomogram and the fundus image, wherein the region where an exudate exists in
Optical tomography; Optical coherence tomography [OCT] · CPC title
Morphological image processing · CPC title
Eye; Retina; Ophthalmic · CPC title
for optical coherence tomography [OCT] · CPC title
using an image reference approach · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.