CN107292878A - A kind of method for assessing virtual coloscope visualization technique using visualization area - Google Patents
A kind of method for assessing virtual coloscope visualization technique using visualization area Download PDFInfo
- Publication number
- CN107292878A CN107292878A CN201710543458.5A CN201710543458A CN107292878A CN 107292878 A CN107292878 A CN 107292878A CN 201710543458 A CN201710543458 A CN 201710543458A CN 107292878 A CN107292878 A CN 107292878A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- colon
- model
- dimensional colon
- visualization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/50—Lighting effects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30028—Colon; Small intestine
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present invention relates to a kind of method for assessing virtual coloscope visualization technique using visualization area, this method includes：Obtain the sectioning image of Clinical CT colon；Sectioning image is handled to complete the segmentation of colon；According to the colon after segmentation, three dimensional colon model is created；Extract three dimensional colon model center line, and along center line by three dimensional colon model be divided into left and right two half parts three dimensional colon model；The visualization area of the three dimensional colon model of two half parts of left and right is gathered respectively；The all surface product of the visualization area and the three dimensional colon model is compared, virtual coloscope visualization technique is estimated according to comparative result.It is compared by the visualization area of present invention collection three dimensional colon model and all surface product of three dimensional colon model, can more accurately assesses visualization technique, obtained result is more accurate, greatly reduces error.
Description
Technical field
The invention belongs to clinical medicine colon field, more particularly to one kind can using visualization area assessment virtual coloscope
Method depending on changing technology.
Background technology
Virtual coloscope generally uses fly-through visualization techniques, for the detection thinking of simulated optical Sigmoidoscope,
The three-dimensional center line that this technology is calculated using virtual camera (the general visual angle using 90-120 degree) edge, surface rendering
Situation inside technology, true reappearance Colon and rectum, the direction of observation can be since rectum (antegrade), or from caecum
Start to observe (retrograde).
Visualization technique is assessed by the observation of Fly-through technologies and Fly-over technologies, but adopted in the prior art
Means assess visualization technique, and the result that it is assessed is mostly inaccurate, there is error.
The content of the invention
The technical problems to be solved by the invention are：The means used in the prior art are estimated to visualization technique,
The result that it is assessed is mostly undesirable, inaccurate, there is error.
It is visual using visualization area assessment virtual coloscope the invention provides one kind to solve technical problem above
The method of change technology, this method includes：
S1, obtains the sectioning image of Clinical CT colon；
S2, is handled the sectioning image to complete the segmentation of colon；
S3, according to the colon after segmentation, creates three dimensional colon model；
S4, extracts the center line of the three dimensional colon model, and divides equally the three dimensional colon model along the center line
Into the three dimensional colon model of the half part of left and right two；
S5, gathers the visualization area of the three dimensional colon model of two half parts of the left and right respectively；
S6, all surface of visualization area and the three dimensional colon model is accumulated and is compared, according to comparing knot
Fruit is estimated to virtual coloscope visualization technique.
Beneficial effects of the present invention：By by the visualization area and three dimensional colon mould of above-mentioned collection three dimensional colon model
The all surface product of type is compared, and can more accurately assess visualization technique, obtained result is more accurate, subtracts significantly
Error is lacked.
Further, the S4 includes：
S41, by the three dimensional colon model partition into equal length multiple three dimensional colon model loops；
S42, extracts the center line of each three dimensional colon model loop；
S43, the center line by each three dimensional colon model loop along each three dimensional colon model loop is divided equally
Into the three dimensional colon model loop of the half part of left and right two；
S44, the three-dimensional of whole left-half is connected into by the three dimensional colon model loop of each left-half
Colon models, while the three dimensional colon model loop of each right half part is connected into the three-dimensional of whole right half part
Colon models.
Above-mentioned further beneficial effect：By by three dimensional colon model partition into the multiple three dimensional colon models of equal length
Ring, each three dimensional colon model loop is divided into along its corresponding center line the three dimensional colon model of two half parts of left and right
Ring.The colon subsequently observed can so be caused more fully and completely, while being also convenient for observing and calculating colic surface
Product.
Further, the S5 includes：The three dimensional colon model of respectively two half parts of the left and right configures a void
Intend camera, the Softcam gathers the three dimensional colon mould of two half parts of the left and right along the path of the center line respectively
The visualization area of type.
Further, the S6 includes：Calculate all surface of the visualization area and the three dimensional colon model
Long-pending ratio, is estimated according to the ratio to virtual coloscope visualization technique.
Above-mentioned further beneficial effect：The ratio accumulated by all surface of calculation visualization area and three dimensional colon model
Value, it can be determined that go out the quality of virtual coloscope visualization technique.
Further, the S3 includes：The contour surface of the three dimensional colon tissue after segmentation is obtained, by the equivalence
Face carries out surface rendering, obtains the three dimensional colon tissue model.
Further, extracting the center line of the three dimensional colon model includes：Algorithm based on gradient vector extracts institute
State the center line of three dimensional colon model.
Further, the S2 includes：
The sectioning image is handled according to level set and bayesian theory to complete the segmentation of three dimensional colon tissue.
Further, the three dimensional colon model table area is divided into the triangle of multiple standard areas, according to described
Triangle is total to determine that all surface of the three dimensional colon model is accumulated with triangle standard area.
Further, the number of the triangle observed according to Fly-over technologies and the index plane of the triangle
Product determines the visualization area.
Above-mentioned further beneficial effect：By the triangle that three dimensional colon model table area is divided into multiple standard areas
Shape, so calculates the number of triangle, it is possible to directly obtain the area of triangle, and the result so also obtained was both accurate or square
Just.
Brief description of the drawings
Fig. 1 is a kind of flow using the method for visualizing area assessment virtual coloscope visualization technique of the invention
Figure；
Fig. 2 observes the schematic diagram of colon for the present invention using Fly-over technologies and Fly-through technologies.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
Embodiment 1
As shown in figure 1, the present embodiment 1 is a kind of side that virtual coloscope visualization technique is assessed using visualization area
Method, this method includes：
S1, obtains the sectioning image of Clinical CT colon；
S2, is handled the sectioning image to complete the segmentation of colon；
S3, according to the colon after segmentation, creates three dimensional colon model；
S4, extracts the center line of the three dimensional colon model, and divides equally the three dimensional colon model along the center line
Into the three dimensional colon model of the half part of left and right two；
S5, gathers the visualization area of the three dimensional colon model of two half parts of the left and right respectively；
S6, all surface of visualization area and the three dimensional colon model is accumulated and is compared, according to comparing knot
Fruit is estimated to virtual coloscope visualization technique.
It should be noted that in the present embodiment 1 first, scan and gather by using arbitrary CT scanner it is general from
Chest is to the section of colon image of belly, and the section of colon picture number typically gathered is 400-500, wherein, belong to one
Patient's colon C T data are typically stored under same catalogue, can be specialty medical digital image transfer protocol (DICOM,
Digital Imaging and Communications in Medicine, or the standard slice map such as conventional JPEG, BMP
Picture.The section of colon image of these collections is input in computer, pictures different in sectioning image are told by computer
Element, can learn which is partly to belong to colon and non-colon, pixel it is deep belong to colon, pixel is shallow to be belonged to
Non- colon.The sectioning image of these different pixels is split again, that is, the partial segmentation that colon will be belonged to
Out.Wherein, the segmentation of colon is to be based on level set (Level Sets), the Gaussian Profile of colon, non-colon group
The Gaussian Profile knitted and the method according to bayesian theory (Bayesian Theory) or use 3D region growth etc.,
The method that pixel undetermined is classified as colon or non-colon, so as to complete colon's segmentation.Such as：Level set
Carry out three dimensional colon sectioning image segmentation.Whole colon's pixels (primary sources) and other non-colon's pixels (
Two class data) all meet Gaussian Profile.Specifically, it can be described by equation below (1)-(3)：
Wherein, X=(x, y, z) is three bit space positions of pixel, and H (a) is unit step function, i.e.,
I (X) is the intensity of the pixel, for the different tissue of two classes, i.e. colon (i=1) and non-colon (i
=2), μ and σ are such average and variance respectively.π is such prior probability, i.e.,
, can be according to following formula (4) for the classification of a pixel undetermined:
I (X)=arg (maxI=1,2(πi(PiI(X)))), (4)
The probability that wherein P is obtained by Gaussian Profile, then according to bayesian theory, the prior probability π * of the pixel undetermined
P, the affiliated class of the larger posterior probability of acquisition big that class, the i.e. pixel undetermined.
Then, the colon cut out is subjected to three-dimensional rendering into three dimensional colon model, then extracts the three dimensional colon
The center line of model, and along the center line by the three dimensional colon model be divided into left and right two half parts three dimensional colon model, its
In, the central line pick-up of threedimensional model is the automatic algorithms based on gradient vector flow (Gradient Vector Flow-GVF),
Such as：The central line pick-up of threedimensional model is carried out by three dimensions shortest path, i.e., from three dimensional colon position (caecum) to
(rectum end/anus, its process is end position：It is empty in 3-D view for the shortest path C (s) between 2 points (A and B)
Between, cost function U is three-dimensional space position P (x, y, z) function, then shortest path, i.e., three-dimensional center line T is in locus
P can be defined as：
The minimum value of above-mentioned integration is minimum cost function, i.e. three-dimensional center line.
The solution of equation (5) is a nonlinear partial differential equation
Wherein:F (P)=1/U (P).
Then, the visualization area of the three dimensional colon model of the above-mentioned half part of left and right two being mentioned to is gathered respectively, is passed through
Fly-over technologies are acquired, and are finally accumulated all surface of the visualization area of collection and strange three dimensional colon model and are carried out
Compare, the visual performance of Fly-over technologies is determined according to comparative result.
By by all surface of the visualization area of above-mentioned collection three dimensional colon model and three dimensional colon model accumulate into
Row compares, and can more accurately assess visualization technique, obtained result is more accurate, greatly reduces error.
Alternatively, the S4 includes：
S41, by the three dimensional colon model partition into equal length multiple three dimensional colon model loops；
S42, extracts the center line of each three dimensional colon model loop；
S43, the center line by each three dimensional colon model loop along each three dimensional colon model loop is divided equally
Into the three dimensional colon model loop of the half part of left and right two；
S44, the three-dimensional of whole left-half is connected into by the three dimensional colon model loop of each left-half
Colon models, while the three dimensional colon model loop of each right half part is connected into the three-dimensional of whole right half part
Colon models.
It should be noted that, being into length by the above-mentioned three dimensional colon model partition that is mentioned in the present embodiment 1 first
Equal multiple three dimensional colon model loops, then the center line of each three dimensional colon model loop is extracted, then by each three dimensional colon
Model loop is divided into the three dimensional colon model loop of two half parts of left and right along center line corresponding with the ring, then by each left-half
Three dimensional colon model loop connect into the three dimensional colon model of whole left-half, while the three-dimensional of each right half part is tied
Intestines model loop connects into the three dimensional colon model of whole right half part.
, will be every by three dimensional colon model partition into the multiple three dimensional colon model loops of equal length by technology alternatively
The individual three dimensional colon model loop is divided into the three dimensional colon model loop of two half parts of left and right along its corresponding center line.So may be used
To cause the colon subsequently observed more fully and completely, while being also convenient for observing and calculating colon area.
Alternatively, the S5 includes：The three dimensional colon model of respectively two half parts of the left and right configures one virtually
Camera, the Softcam gathers the three dimensional colon model of two half parts of the left and right along the path of the center line respectively
Visualization area.
It should be noted that being the three dimensional colon mould in the above-mentioned half part of left and right two being mentioned in the present embodiment 1
A Softcam is respectively configured in type, and then the two Softcams are respectively along two half portions of path collection left and right of center line
The visualization area of the three dimensional colon model divided.
Alternatively, the S6 includes：The all surface for calculating the visualization area and the three dimensional colon model is accumulated
Ratio, virtual coloscope visualization technique is estimated according to the ratio.
, can be with it should be noted that the ratio that all surface for passing through calculation visualization area and three dimensional colon model is accumulated
Judge the quality of virtual coloscope visualization technique.
Alternatively, the S3 includes：The contour surface of the three dimensional colon tissue after segmentation is obtained, by the contour surface
Surface rendering is carried out, the three dimensional colon tissue model is obtained.
It should be noted that split the contour surface (iso-surface) of dimensional colon image later to create threedimensional model,
Then surface rendering is carried out.Render will above addition bitmap texture or procedural texture, illumination, bump mapping and
Relative to the position of other objects.Obtained result is exactly the complete image that consumer or observer can see.
Alternatively, extracting the center line of the three dimensional colon model includes：Algorithm based on gradient vector extracts described
The center line of three dimensional colon model.
Alternatively, the S2 includes：
The sectioning image is handled according to level set and bayesian theory to complete the segmentation of three dimensional colon tissue.
Alternatively, the three dimensional colon model table area is divided into the triangle of multiple standard areas, according to described three
The angular total all surface product that the three dimensional colon model is determined with triangle standard area.Such as：Triangle
Standard area is 1, and total triangle number is N；Then the total triangle numbers of the standard area 1* of all surface product=triangle are N.
Alternatively, the number of the triangle observed according to Fly-over technologies and the standard area of the triangle
Determine the visualization area.
It should be noted that the triangle by the way that three dimensional colon model table area to be divided into multiple standard areas, so
Calculate the number of triangle, it is possible to be directly observed the area of triangle, the result so also obtained was both accurately also convenient for.Than
Such as：The number that the triangle is obtained under the visualization of Fly-over technologies is N1, then visualizes the index plane of area=triangle
Product 1*N1, if obtain institute in the case where the area number that Fly-through technologies are observed is the visualization of 300, Fly-over technologies
The number for stating triangle is 490, and triangle sum is 500, then it is known that what Fly-over technologies visualization technique was observed
Colon is more preferable.
As shown in Fig. 2 light color system for visualization area, dark color system the area that cannot be observed, in clinical test
In show：
First group：Fly-through is unidirectionally detected, using the detection from anus to caecum, and visualization area ratio only has
79%.
Second group：The two-way detections of Fly-through, from anus to caecum, then return anus, although two-way from caecum
Fly-through visualization areas are than being lifted to 93%, but detection time is twice.
3rd group：Fly-over is unidirectionally detected, from anus to caecum, Fly-over visualization areas ratio up to 99.7%,
It is substantially prevented from missing inspection.
In summary, the present embodiment 1 is generally compared with virtual coloscope using Fly-through visualization techniques, Fly-
Over this patents have following technology and commercial advantage：
The computational methods of offer do not have geometric distortion；
There is no angle of visual field limitation, can maximize the colon surface observed；
There is no perspective distortion, the polyp of colon on the inside of intestinal wall fold will not be missed；
Expert is simulated, in order to adapt to human colorectal steering, adjust automatically camera angle in detection process；
Maximum visual colon inner surface, in favor of finding the lesion behind fold；
The maximum free degree adjusts the height of camera.
In this manual, identical embodiment or example are necessarily directed to the schematic representation of above-mentioned term.
Moreover, specific features, structure, material or the feature of description can be in any one or more embodiments or example with suitable
Mode is combined.In addition, in the case of not conflicting, those skilled in the art can be by the difference described in this specification
The feature of embodiment or example and non-be the same as Example or example is combined and combined.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (9)
1. a kind of method for assessing virtual coloscope visualization technique using visualization area, it is characterised in that this method includes：
S1, obtains the sectioning image of Clinical CT colon；
S2, is handled the sectioning image to complete the segmentation of colon；
S3, according to the colon after segmentation, creates three dimensional colon model；
S4, extracts the center line of the three dimensional colon model, and the three dimensional colon model is divided into a left side along the center line
The three dimensional colon model of right two half parts；
S5, gathers the visualization area of the three dimensional colon model of two half parts of the left and right respectively；
S6, all surface product of the visualization area and the three dimensional colon model is compared, according to comparative result pair
Virtual coloscope visualization technique is estimated.
2. according to the method described in claim 1, it is characterised in that the S4 includes：
S41, by the three dimensional colon model partition into equal length multiple three dimensional colon model loops；
S42, extracts the center line of each three dimensional colon model loop；
S43, the center line by each three dimensional colon model loop along each three dimensional colon model loop is divided into a left side
The three dimensional colon model loop of right two half parts；
S44, the three dimensional colon of whole left-half is connected into by the three dimensional colon model loop of each left-half
Model, while the three dimensional colon model loop of each right half part is connected into the three dimensional colon of whole right half part
Model.
3. method according to claim 1 or 2, it is characterised in that the S5 includes：Respectively described or so two half portions
The three dimensional colon model divided configures a Softcam, and the Softcam gathers institute along the path of the center line respectively
State the visualization area of the three dimensional colon model of two half parts of left and right.
4. method according to claim 1 or 2, it is characterised in that the S6 includes：Calculate it is described visualization area with
The ratio of all surface product of the three dimensional colon model, is commented virtual coloscope visualization technique according to the ratio
Estimate.
5. method according to claim 1 or 2, it is characterised in that the S3 includes：Obtain the three-dimensional after segmentation
The contour surface of colon, carries out surface rendering by the contour surface, obtains the three dimensional colon tissue model.
6. method according to claim 1 or 2, it is characterised in that extracting the center line of the three dimensional colon model includes：
Algorithm based on gradient vector extracts the center line of the three dimensional colon model.
7. method according to claim 1 or 2, it is characterised in that the S2 includes：
The sectioning image is handled according to level set and bayesian theory to complete the segmentation of three dimensional colon tissue.
8. method according to claim 4, it is characterised in that the three dimensional colon model table area is divided into multiple marks
The triangle of quasi- area, the three dimensional colon model is determined with triangle standard area according to the triangle is total
All surface is accumulated.
9. method according to claim 8, it is characterised in that the triangle observed according to F l y-over technologies
The standard area of number and the triangle determine the visualization area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710543458.5A CN107292878A (en) | 2017-07-05 | 2017-07-05 | A kind of method for assessing virtual coloscope visualization technique using visualization area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710543458.5A CN107292878A (en) | 2017-07-05 | 2017-07-05 | A kind of method for assessing virtual coloscope visualization technique using visualization area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107292878A true CN107292878A (en) | 2017-10-24 |
Family
ID=60100307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710543458.5A Pending CN107292878A (en) | 2017-07-05 | 2017-07-05 | A kind of method for assessing virtual coloscope visualization technique using visualization area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107292878A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8014561B2 (en) * | 2006-09-07 | 2011-09-06 | University Of Louisville Research Foundation, Inc. | Virtual fly over of complex tubular anatomical structures |
| CN102184567A (en) * | 2011-05-04 | 2011-09-14 | 北京师范大学 | Method for constructing three-dimensional blood vessel model based on ball B-spline curve |
| CN102289811A (en) * | 2011-08-17 | 2011-12-21 | 深圳市旭东数字医学影像技术有限公司 | Semi-automatic sequence image segmentation method and system |
| CN103300820A (en) * | 2012-03-13 | 2013-09-18 | 西门子公司 | Method and system for non-invasive functional assessment of coronary artery stenosis |
| US9401047B2 (en) * | 2010-04-15 | 2016-07-26 | Siemens Medical Solutions, Usa, Inc. | Enhanced visualization of medical image data |
-
2017
- 2017-07-05 CN CN201710543458.5A patent/CN107292878A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8014561B2 (en) * | 2006-09-07 | 2011-09-06 | University Of Louisville Research Foundation, Inc. | Virtual fly over of complex tubular anatomical structures |
| US9401047B2 (en) * | 2010-04-15 | 2016-07-26 | Siemens Medical Solutions, Usa, Inc. | Enhanced visualization of medical image data |
| CN102184567A (en) * | 2011-05-04 | 2011-09-14 | 北京师范大学 | Method for constructing three-dimensional blood vessel model based on ball B-spline curve |
| CN102289811A (en) * | 2011-08-17 | 2011-12-21 | 深圳市旭东数字医学影像技术有限公司 | Semi-automatic sequence image segmentation method and system |
| CN103300820A (en) * | 2012-03-13 | 2013-09-18 | 西门子公司 | Method and system for non-invasive functional assessment of coronary artery stenosis |
Non-Patent Citations (4)
| Title |
|---|
| ALY FARAG 等: "Adaptive Segmentation of Multi-modal 3D Data", 《MICCA 2004》 * |
| DONGQING CHEN 等: "On clinical validation of Fly-Over visualization technique for virtual colonoscopy", 《2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)》 * |
| HASSOUNA 等: "Differential Fly-Throughs (DFT): A General", 《MICCAI 2005》 * |
| M. SABRY HASSOUNA 等: "Virtual Fly-Over: A New Visualization Technique for Virtual Colonoscopy", 《INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2006》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2827742C (en) | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery | |
| CN104883946B (en) | Image processing apparatus, electronic equipment, endoscope apparatus and image processing method | |
| Robben et al. | Simultaneous segmentation and anatomical labeling of the cerebral vasculature | |
| Roy et al. | Detection and Quantification of Brain Tumor from MRI of Brain and it’s Symmetric Analysis | |
| CN106447708A (en) | OCT eye fundus image data registration method | |
| Joshi et al. | Depth discontinuity-based cup segmentation from multiview color retinal images | |
| WO2009103046A2 (en) | Medical image reporting system and method | |
| US20210406596A1 (en) | Convolutional neural networks for efficient tissue segmentation | |
| CN106650794A (en) | Method and system for eliminating highlight of image affected by highlight reflection on object surface | |
| CN104574374B (en) | The automatic division method that retina serous pigmentary epithelial layer is detached from | |
| CN108090954A (en) | Abdominal cavity environmental map based on characteristics of image rebuilds the method with laparoscope positioning | |
| CN110415216A (en) | CNV automatic testing method based on SD-OCT and OCTA retinal images | |
| Bogunović et al. | Geodesic graph cut based retinal fluid segmentation in optical coherence tomography | |
| CN108648228A (en) | A kind of binocular infrared human body dimension measurement method and system | |
| Yao et al. | Employing topographical height map in colonic polyp measurement and false positive reduction | |
| CN111091605B (en) | Rib visualization method, identification method and computer-readable storage medium | |
| EP2506212B1 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN115619790B (en) | Hybrid perspective method, system and equipment based on binocular positioning | |
| CN112435281A (en) | Multispectral fundus image analysis method and system based on counterstudy | |
| CN107292878A (en) | A kind of method for assessing virtual coloscope visualization technique using visualization area | |
| Choe et al. | 2-D registration and 3-D shape inference of the retinal fundus from fluorescein images | |
| CN113610908B (en) | Depth estimation method for multi-baseline fusion in monocular endoscopic surgery | |
| CN114617527A (en) | Laparoscope three-dimensional imaging method and system | |
| CN112651400A (en) | Stereoscopic endoscope auxiliary detection method, system, device and storage medium | |
| Choe et al. | 3-d shape reconstruction of retinal fundus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |
|
| RJ01 | Rejection of invention patent application after publication |