CN105139030A - Method for sorting hepatic vessels - Google Patents
Method for sorting hepatic vessels Download PDFInfo
- Publication number
- CN105139030A CN105139030A CN201510506303.5A CN201510506303A CN105139030A CN 105139030 A CN105139030 A CN 105139030A CN 201510506303 A CN201510506303 A CN 201510506303A CN 105139030 A CN105139030 A CN 105139030A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- vessel
- blood
- image
- propping
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002440 hepatic effect Effects 0.000 title claims abstract description 10
- 210000004185 liver Anatomy 0.000 claims abstract description 44
- 210000004204 blood vessel Anatomy 0.000 claims description 247
- 230000002792 vascular Effects 0.000 claims description 94
- 241000415078 Anemone hepatica Species 0.000 claims description 47
- 210000003240 portal vein Anatomy 0.000 claims description 29
- 230000011218 segmentation Effects 0.000 description 13
- 230000007547 defect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 210000001367 artery Anatomy 0.000 description 4
- 210000003462 vein Anatomy 0.000 description 4
- 210000003484 anatomy Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 210000001835 viscera Anatomy 0.000 description 3
- 206010019695 Hepatic neoplasm Diseases 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 208000014018 liver neoplasm Diseases 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 231100000768 Toxicity label Toxicity 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 210000005166 vasculature Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
Abstract
The invention provides a method for sorting hepatic vessels. The method for sorting hepatic vessels comprises redistricting a plurality of branches of a vessel according to the types of hepatic vessels; receiving the sorting indication of a user for the vessel types of the plurality of branches of a vessel; and updating three dimensional vessel images according to the sorting of updated vessel types of the plurality of branches of a vessel. The method for sorting hepatic vessels can improve the accuracy for sorting vessels in the three dimensional vessel images of liver organs so as to improve the practical medical reference application value of the three dimensional vessel images. The method for sorting hepatic vessels can be used for three dimensional modeling image processing in the medical field.
Description
Technical field
The present invention relates to medical image processing technology field, particularly relate to a kind of sorting technique of liver vessel.
Background technology
Along with improving constantly of medical technique level, in order to obtain the lesion locations of patient more accurately, adopt in prior art and English full name: the ComputedTomography Chinese of general abdominal CT(carried out to human body: CT scan) strengthen three phase dynamic scans, obtain three phase images of arterial phase, Portal venous phase and balance period, and then adopt three-dimensional reconstruction to arteria hepatica, portal vein and vena hepatica blood vessel imaging, analyze the distributed architecture of three in liver and variation, for liver subsection, the resection of liver neoplasm has important directive significance.
If the CT picture quality provided is better, use arterial phase image can create out artery vascular pattern, use portal vein phase image can create portal vein model, balance phase image creation goes out vena hepatica model.But, due to medical imaging self and the factor such as the position of individual patient liver neoplasm and the variation of blood vessel, cause actual CT picture quality not high, therefore, use three-dimensional reconstruction to arteria hepatica, when portal vein and vena hepatica blood vessel carry out imaging, the three-dimensional blood-vessel image obtained often there will be arteria hepatica, portal vein and vena hepatica overlap, and the phenomenon that other non-vascular tissues mix, medical personnel can only according to arteria hepatica under normal circumstances, the difference of vena hepatica and pylic anatomical structure, determine their root, and then according to the thickness of blood vessel, connective and out of shapely sort out arteria hepatica, vena hepatica and portal vein, medical personnel are needed to spend more energy, and said method of sampling also often can lose multivessel details perhaps.
Summary of the invention
Embodiments of the invention provide a kind of sorting technique of liver vessel, by repartitioning multiple blood vessel section of propping up respectively according to liver vessel type, and receive user the classification of the vascular group of multiple blood vessel section of propping up is indicated, the accuracy of the three-dimensional blood-vessel image medium vessels classification to liver organ can be improved, thus improve the practical medical of three-dimensional blood-vessel image with reference to using value.
For achieving the above object, embodiments of the invention adopt following technical scheme:
Obtain the three-dimensional blood-vessel image of liver organ;
According to arteria hepatica in three-dimensional blood-vessel image, portal vein, vena hepatica vascular group marks different colors respectively to distinguish;
Respectively according to arteria hepatica, portal vein, often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group;
Receive the classification instruction of the vascular group to multiple blood vessel section of propping up of user's input;
Vascular group classification after upgrading according to multiple blood vessel section of propping up, upgrades three-dimensional blood-vessel image.
The liver vessel sorting technique that the embodiment of the present invention provides, after the three-dimensional blood-vessel image obtaining liver organ, again carry out the blood vessel section of propping up to often kind of vascular group respectively according to liver vessel type to divide, receive the instruction of the classification to the vascular group belonging to multiple blood vessel section of propping up of user's input, for specialized medical personnel user provides manual intervention means, secondary classification is carried out to vascular group, himself abundant professional knowledge can be utilized can to correct the defect that existing three-dimensional modeling algorithm and source data cause, thus improve the accuracy of liver vessel classification.
Simultaneously, this programme divides multiple blood vessel section of propping up respectively again according to three kinds of large vascular groups, this considers, three-dimensional modeling overall accuracy is higher on the one hand, defect mistake appears at the little branch vessel section of propping up aspect usually, therefore again divided by large vascular group, convenient classification little branch vessel, checks.
The three-dimensional blood-vessel image of vascular group classifying, updating after embodiment of the present invention scheme also upgrades according to multiple blood vessel section of propping up, thus also have updated the classification of liver three trunk, the practical medical that improve three-dimensional blood-vessel image with reference to using value, thus is convenient to medical personnel and is carried out preoperative estimating and accurate judgement in art.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The sorting technique schematic diagram of a kind of liver vessel that Fig. 1 provides for the embodiment of the present invention one;
The three-dimensional model that Fig. 2 provides for the embodiment of the present invention one creates schematic diagram;
The three-dimensional blood-vessel image bearing calibration schematic diagram that Fig. 3 provides for the embodiment of the present invention two;
Fig. 4 organizes sweep-out method schematic diagram for the non-vascular of the three-dimensional blood-vessel image that the embodiment of the present invention three provides;
The disconnection blood vessel incorrect link location method schematic diagram that Fig. 5 provides for the embodiment of the present invention four;
The mapping schematic diagram of three-dimensional blood-vessel image on two-dimensional CT image that Fig. 6 provides for the embodiment of the present invention two.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Embodiment one,
Embodiments of the invention provide a kind of sorting technique of liver vessel, and with reference to Fig. 1, the method comprises the following steps:
The three-dimensional blood-vessel image of step 100, acquisition liver organ.
Wherein, three-dimensional blood-vessel image carries out modeling according to one group of one group of two-dimensional CT image being in the same period to obtain.Than as described in the background art, use arterial phase image can create out artery vascular pattern, use portal vein phase image can create portal vein model, balance phase image creation goes out vena hepatica model.
Concrete, the three-dimensional blood-vessel image obtaining liver organ in step 100 is specifically comprised as shown in Figure 2,
100a, according to algorithm of region growing, blood vessel segmentation is carried out to each two-dimentional blood-vessel image in one group of two-dimensional CT image, obtain the blood vessel segmentation sequence of each two-dimentional blood-vessel image.
Wherein, algorithm of region growing (English full name: regiongrowing) is that the set of pixels with similar quality is formed region altogether.First in the region needing segmentation, a Seed Points (x is chosen, y) as growing point, then according to predefined rule, the similar pixel in field around Seed Points is merged in the region belonging to Seed Points pixel, these new pixels are proceeded said process as new sub pixel, until the pixel do not satisfied condition is included, such region has just generated.After blood vessel segmentation being carried out to each two-dimentional blood-vessel image by algorithm of region growing, each two-dimentional blood-vessel image can be divided into multiple region, thus, obtain the blood vessel segmentation sequence of each two-dimentional blood-vessel image.As shown in Figure 2,
100b, carry out three-dimensional reconstruction according to marching cube (English full name: MarchingCubes, be called for short MC) the blood vessel segmentation sequence of algorithm to all two-dimentional blood-vessel images, obtain three-dimensional blood-vessel image.
Example, the if desired image of three-dimensional reconstruction arterial phase, then according to marching cubes algorithm, carry out three-dimensional reconstruction to the blood vessel segmentation sequence of all CT images of arterial phase, obtain the three-dimensional blood-vessel image of the liver vessel of arterial phase; If desired the image of three-dimensional reconstruction venous phase, then according to marching cubes algorithm, carry out three-dimensional reconstruction to the blood vessel segmentation sequence of all CT images of venous phase, obtain the three-dimensional blood-vessel image of the liver vessel of venous phase; If desired the image of three-dimensional reconstruction Portal venous phase, then according to marching cubes algorithm, carry out three-dimensional reconstruction to the blood vessel segmentation sequence of all CT images of Portal venous phase, obtain the three-dimensional blood-vessel image of the liver vessel of Portal venous phase.
Step 102, obtain arteria hepatica in described three-dimensional blood-vessel image respectively, portal vein, hepatic venous 3-D view.
Particularly, on the three-dimensional blood-vessel image that modeling is good, according to more existing blood vessel recognizers, can distinguish arteria hepatica, portal vein, the blood vessel of vena hepatica three major types type, each vascular group generally includes many blood vessels.Obtain arteria hepatica in three-dimensional blood-vessel image respectively, portal vein, hepatic venous three-dimensional picture, and distinguished.In order to differentiation clearly, the blood vessel of these three kinds large kinds can divide and wears different colors to distinguish.
Such as, arteria hepatica red-label, vena hepatica Green Marker, portal vein blue markings.
Step 104, respectively according to described arteria hepatica, portal vein, often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group.
Based on the technology of current Computerized three-dimensional modeling, the modeling of overall three-dimensional blood-vessel image, such as in locus, the aspect accuracys such as volume reach to a certain degree, but often occur that some are judged by accident at little vessel branch place.Therefore again divide according to large vascular group, obtain multiple blood vessel section of propping up, wherein, arteria hepatica, portal vein, arteria hepatica have multiple blood vessel section of propping up respectively.
Particularly, be multiple blood vessel sections of propping up by the vessel segmentation of often kind of vascular group, thus be convenient to observe the little blood vessel section of propping up.The plurality of blood vessel section of propping up shows respectively, and painted with affiliated large vascular group is identical.For convenience of paired observation, improve interactive, three-dimensional blood-vessel image and multiple blood vessel section of propping up are presented in same interface respectively.Such as, three-dimensional blood-vessel image is presented on the left of interface, and right side arranges three different switching push buttons, and the multiple blood vessels of each button to a kind of vascular group prop up segment limit face.After choosing one of them vascular group button, the multiple blood vessel sections of propping up under this vascular group ready-portioned that just display is corresponding, each blood vessel section of propping up is in a square frame.Each blood vessel section of propping up keeps its locus in whole three-dimensional blood-vessel image.
Further, if sorted many to the blood vessel section of propping up, according to its locus, trend or the Consideration of individual patient lesion degree will become a lot of and complicated, be not easy divide, easily misjudge on the contrary, and if very few to the segmentation of the blood vessel section of propping up, easily ignore details again, do not reach the object correcting classification.
Therefore according to the locus of liver vessel, doctor is to the degree of concern of the important blood vessels section of propping up, in conjunction with anatomy principle, in practical operation, 4 to 8 blood vessel sections of propping up are divided into each large vascular group kind, the object that three-dimensional modeling is corrected can be met, meet reference needs medically, simultaneously, for doctor, the workload reclassified is also less, and the probability of error in judgement also reduces.
The classification instruction of the vascular group to described multiple blood vessel section of propping up of step 106, reception user input.
Highly professional due to medical domain, the individual difference of patient is also larger, medical imaging does not have absolute accuracy, therefore when real world applications, if can correct three-dimensional model by the abundant professional standing and experience of medical personnel simultaneously, modeling object more accurately can be reached.
In embodiment of the present invention step, doctor or other medical personnel can judge by the vessel branch to three-dimensional blood-vessel image again by professional experiences and knowledge, thus are classified in correct vascular group classification.
Particularly, such as the hepatic venous blood vessel section of propping up a potential range vena hepatica blood vessel is very near, and vein is due to blood flow reason, not necessarily when scanning imagery can often open in two-dimensional CT image and can observe, due to reasons such as backoff algorithms, vena hepatica may be included into, and actual should assign to portal vein classification in.
In embodiment of the present invention scheme, for this situation, can set property to multiple blood vessel section of propping up, this property value at least comprises this vascular group described in blood vessel section of propping up, user changes the property value of this blood vessel section of propping up after can choosing this blood vessel section of propping up, so complete the vascular group classification instruction to this blood vessel section of propping up.
Property value can occur by choosing click right after the blood vessel section of propping up, user is selected by drop-down list, under the mode that also can pull by pinning left mouse button carrying out after choosing the blood vessel section of propping up is referred to corresponding vascular group button, and then property value also changes thereupon.
After the property value of the blood vessel section of propping up changes, its correspondence painted also changes into color corresponding to the vascular group classification after renewal.
Step 108, upgrade according to the described multiple blood vessel section of propping up after vascular group classification, upgrade described three-dimensional blood-vessel image.
After the classification of user to the blood vessel section of propping up changes, the painted of the blood vessel section of propping up changes, this blood vessel section of propping up changes in three-dimensional blood-vessel image interface simultaneously simultaneously, and painted becoming upgrades color corresponding to the rear vascular group of classification, facilitates user's Real Time Observation to judge.
Back-end data also changes thereupon simultaneously, is upgraded by whole three-dimensional blood-vessel image model, thus is convenient to the operation that user carries out other on this basis, such as simulate excision, and segmentation observation waits surgical adjunct.
The liver vessel sorting technique that the embodiment of the present invention provides, after the three-dimensional blood-vessel image obtaining liver organ, again carry out the blood vessel section of propping up to often kind of vascular group respectively according to liver vessel type to divide, receive the instruction of the classification to the vascular group belonging to multiple blood vessel section of propping up of user's input, for specialized medical personnel user provides manual intervention means, secondary classification is carried out to vascular group, himself abundant professional knowledge can be utilized can to correct the defect that existing three-dimensional modeling algorithm and source data cause, thus improve the accuracy of liver vessel classification.
Simultaneously, this programme divides multiple blood vessel section of propping up respectively again according to three kinds of large vascular groups, this considers, three-dimensional modeling overall accuracy is higher on the one hand, defect mistake appears at the little branch vessel section of propping up aspect usually, therefore again divided by large vascular group, convenient classification little branch vessel, checks.
The three-dimensional blood-vessel image of vascular group classifying, updating after embodiment of the present invention scheme also upgrades according to multiple blood vessel section of propping up, thus also have updated the classification of liver three trunk, the practical medical that improve three-dimensional blood-vessel image with reference to using value, thus is convenient to medical personnel and is carried out preoperative estimating and accurate judgement in art.
Embodiment two
The embodiment of the present invention two is the improvement to the sorting technique of liver vessel on embodiment one basis.
Particularly, in step 104, respectively according to described arteria hepatica, portal vein, before often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group, also comprises step 103, described three-dimensional blood-vessel image is carried out two dimensional image map correction.
During owing to carrying out blood vessel segmentation to each two-dimentional blood-vessel image according to algorithm of region growing in embodiment one step 100a, sometimes the similar pixel point not belonging to angiosomes is also referred to angiosomes, therefore, three-dimensional blood-vessel image is mapped at each two-dimentional blood-vessel image, inaccurate position adjusts, and makes the three-dimensional blood-vessel image after rebuilding more accurate, with the vascular system of realistic internal organs, and then continue to perform step 103a-103d, as shown in Figure 3.
Step 103a, the mapped profile line obtained on the two-dimensional CT image of described three-dimensional blood-vessel image corresponding sequence in described one group of two-dimensional CT image.
Wherein, one group of two-dimensional CT image refers to the 2-D data source for creating the same first phase that the three-dimensional blood-vessel image model of liver uses.Mapped by three-dimensional for liver blood-vessel image model, object is in order to comparison generates the 2-D data of three-dimensional blood-vessel image and the difference in original 2-D data source.Because three-dimensional blood-vessel image is volume data, and two-dimensional CT image by multiple images of same first phase according to series arrangement, also can be understood as, the time series characteristic three-dimensional data of two-dimensional CT image showed.Thus an individual data items can map back on multiple two dimensional images of this group, often opens the mapping that two dimensional image all can have this individual data items in principle, but due to reasons such as imagings, not often open on two-dimensional CT image to observe object organ-tissue.
Can comprise for the mapped profile line obtained in step 103a on the two-dimensional CT image of described three-dimensional blood-vessel image corresponding sequence in described one group of two-dimensional CT image:
1031a, obtain three-dimensional blood-vessel image vessel boundary line corresponding in each two-dimensional CT image.
Obtain because three-dimensional blood-vessel image all carries out three-dimensional reconstruction by multiple two-dimensional CT image, therefore, three-dimensional blood-vessel image can have corresponding data-mapping on the two-dimensional CT image of corresponding sequence, blood vessel in each two-dimentional blood-vessel image has corresponding stereoscopic three-dimensional vasculature part at three-dimensional blood-vessel image, each three-dimensional blood vessel has respective vessel boundary line, as shown in Figure 6, three-dimensional blood-vessel image maps back two-dimensional CT image, represents mapped profile line in figure in the mode of closed curve.
1032a, obtain the positional information of vessel boundary line corresponding to each two-dimensional CT image medium vessels tissue of sequence corresponding to three-dimensional blood-vessel image.
Due to the image that three-dimensional blood-vessel image is a 3 D stereo, therefore, three-dimensional blood-vessel image medium vessels has respective positional information.In concrete realization, this positional information can be locus coordinate.Therefore, the vessel profile line of three-dimensional blood-vessel image in the two-dimentional blood-vessel image of correspondence has respective locus coordinate, obtains the locus coordinate of the three-dimensional blood-vessel image vessel boundary line corresponding with each two-dimentional vascular tissue image.
The position relative information of the vessel boundary line that 1033a, basis are corresponding with each two-dimentional blood-vessel image, draws and obtains the vessel map outline line of three-dimensional blood-vessel image on each two-dimentional blood-vessel image.
Step 103b, judge whether whether described mapped profile line overlap with the border of the two-dimensional CT image medium vessels tissue of the corresponding sequence in described one group of two-dimensional CT image.
Namely more three-dimensional blood-vessel image maps back the difference of the data area of the two-dimensional CT image of corresponding sequence and the data area of original two dimensional CT image.
The border of each two-dimentional blood-vessel image medium vessels tissue can calculate according to borderline region algorithm.Closed curve is as shown in Figure 6 the mapped profile line that three-dimensional blood-vessel image maps back the two-dimensional CT image of a certain corresponding sequence.
The mapped profile line judging to compare three-dimensional modeling data on this two-dimensional CT image whether vascular tissue original structure border with whether overlap.
Determination methods can by means of computerized algorithm, and comparing the positional information of mapped profile line of three-dimensional modeling data and the positional information of organizational boundary, particularly, can be the comparison of co-ordinate position information.
And, also can be the artificial observation of user.
If step 103c does not overlap, adjust the overlapping margins of described mapped profile line and the two-dimensional CT image medium vessels tissue of described corresponding sequence.
Particularly, method of adjustment can be the comparative result of computing machine according to both positional informations, is extended out by mapped profile line or zooms to place of organizational boundary, changing the scope of mapped profile line.
Or, also can by the method for manual intervention.According to the operation of user, obtain calibration command,
According to calibration command, namely certain any mobile message on mapped profile line, is adjusted to specified location in user by this position of mapped profile line.
Repeat said process, by the overlapping margins of mapped profile line adjustment with corresponding two-dimentional blood-vessel image medium vessels tissue.
Step 103d, the two-dimensional CT image data again three-dimensional modeling corresponding according to the mapped profile line after described adjustment, obtain the three-dimensional blood-vessel image after correcting.
Concrete, just mean that the scope of two dimensional source data there occurs change after mapped profile line is adjusted, thus the data area of two-dimensional CT image corresponding to the mapped profile line after adjustment re-starts marching cubes algorithm carries out three-dimensional modeling, obtain the three-dimensional blood-vessel image after correcting.
It should be noted that, above-mentioned be map back a corresponding sequence two-dimensional CT image on map outline line adjustment carry out the citing of three-dimensional blood-vessel image correction, the change of the mapped profile line in each two-dimensional CT image all can cause the change of two dimensional source data area, thus again after modeling, three-dimensional blood vessel model is corrected.Namely, can choose multiple two-dimensional CT image, observe the mapped profile line of three-dimensional model, distribution adjusts, thus more accurate three-dimensional blood-vessel image is corrected.
Embodiment of the present invention scheme adds the step of three-dimensional blood-vessel image being carried out two dimensional image map correction on embodiment one scheme basis, on the beneficial effect basis that embodiment one is brought, the accuracy of three-dimensional modeling can be improved further, thus provide foundation more accurately for the division of next step blood vessel section of propping up, and finally affect the classification results of three major types blood vessel in liver.
Embodiment three
The embodiment of the present invention is the improvement on the basis that embodiment one or embodiment one and embodiment two combine.
Particularly, in embodiment one step 104, respectively according to described arteria hepatica, portal vein, before often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group, or after carrying out two dimensional image map correction in embodiment two step 103, by described three-dimensional blood-vessel image, also comprise another aligning step 105 to three-dimensional blood-vessel image, the non-vascular tissue removed in described three-dimensional blood-vessel image.
Because the embodiment of the present invention is mainly for the 3-D view of blood vessel, therefore, the non-vascular in three-dimensional blood-vessel image can be organized and first remove, to obtain three-dimensional blood-vessel image comparatively accurately.
For the non-vascular tissue how removed in three-dimensional blood-vessel image, as shown in Figure 4, specifically comprise:
The mark instructions of 105a, reception user.
Wherein, mark instructions is used to indicate by the non-vascular tissue mark in three-dimensional blood-vessel image out.Wherein, mark instructions can be that user clicks the mouse, and also can be the instruction code relevant to mark that user inputs.
105b, according to mark instructions, mark the non-vascular tissue in three-dimensional blood-vessel image.
The clear instruction of 105c, reception user.
Wherein, clear instruction is used to indicate and is removed by the non-vascular tissue marked in three-dimensional blood-vessel image.
105d, according to clear instruction, remove the non-vascular tissue in three-dimensional blood-vessel image.
Example, the medical personnel of user's particularly specialty can out of shape according to the anatomical structure of internal organs and blood vessel, confirm obvious non-vascular tissue, these non-vascular being organized, by clicking the mouse, marking these non-vascular tissues, as drawn closed curve, these non-vascular tissues are drawn a circle to approve out, further, the non-vascular tissue for delineation region is removed, and obtains three-dimensional blood-vessel image comparatively accurately.
Thus the embodiment of the present invention is owing to adding the step removing non-vascular tissue in three-dimensional blood-vessel image, unnecessary non-targeted object can be removed, thus make three-dimensional blood-vessel image more accurate, prevent from follow-uply unnecessary tissue being put under when dividing the blood vessel section of propping up, that causes the blood vessel section of propping up to divide is inaccurate, and then reduces the accuracy of liver vessel classification.
The embodiment of the present invention carries out improving on the basis that embodiment one or embodiment one and two combine, and therefore has the beneficial effect of embodiment one and embodiment two simultaneously concurrently, do not repeat them here.
Embodiment four
The embodiment of the present invention is on above-described embodiment one basis, or embodiment one is on the basis that embodiment two is combined, or on the basis of embodiment one, three combination, or the improvement that the basis of embodiment one, two, three combination is done.
Particularly, in embodiment one step 104, respectively according to described arteria hepatica, portal vein, before often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group, or in embodiment two step 103, after described three-dimensional blood-vessel image is carried out two dimensional image map correction, or before embodiment two step 103, or in embodiment three step 105, before removing the non-vascular tissue in described three-dimensional blood-vessel image, or after embodiment three step 105, also comprise another aligning step 107 to three-dimensional blood-vessel image, disconnect described three-dimensional blood-vessel image medium vessels connection error position.
In embodiments of the present invention, due to the optimization that step 107 is to above-described embodiment effect, implementation step arrangement does not have strict order restriction, as long as the accuracy improving three-dimensional blood-vessel image can be reached, and then improves the object of liver vessel classification accuracy.
In three-dimensional modeling, often might not open in two-dimensional ct source images can observe due to all histoorgans, some vein scan images can be flickering, therefore the blood vessel in three-dimensional blood-vessel image is not full communicating yet, there will be several branch, the embodiment of the present invention utilizes these disconnected branches to carry out the classification of artery, vein and portal vein, sorted vessel branch maintains the anatomical location of original blood vessel, can find out that three is in the distributed architecture of internal organs, variation situation and the neighbouring relationship with focus clearly.In a practical situation, due to the reason of algorithm in three-dimensional blood vessel modeling process, may to the erroneous judgement of organizational boundary in two-dimensional ct source images, or many-sided factor such as the uncertainty of backoff algorithm, user, before classifying or after classification or in assorting process, according to anatomical knowledge, finds that some arteries, vein and portal vein are mutually mixed in together, therefore, with regard to needing, the position of these connection errors is removed.
Concrete, as shown in Figure 5, step 107, disconnect described three-dimensional blood-vessel image medium vessels connection error position and comprise:
Second mark instructions of step 107a, reception user.
Wherein, the second mark instructions is used for the position of three-dimensional blood-vessel image medium vessels connection error to mark.Second mark instructions can be that user clicks the mouse, and also can be the instruction code relevant to mark that user inputs.
Step 107b, according to the second mark instructions, mark the position of three-dimensional blood-vessel image medium vessels connection error.
Second clear instruction of step 107c, reception user.
Wherein, the second clear instruction is used to indicate and is removed the position of the blood vessel connection error marked in three-dimensional blood-vessel image.
Step 108d, according to the second clear instruction, remove the position of three-dimensional blood-vessel image medium vessels connection error.
Thus realize the disconnection of blood vessel incorrect link position.
Example, user determines the position having blood vessel malunion true in three-dimensional blood-vessel image according to anatomical knowledge, by clicking the mouse, identify by spheroid cutter or other shapes, obtain the volume coordinate of the position identified, in the data centralization storing three-dimensional blood-vessel image data, the coordinate figure of this part is emptied, be so just disconnected incorrect link position.And then the three-dimensional blood-vessel image removing blood vessel connection error is classified, for follow-up medical surgery provides reference accurately.
On the basis of above-described embodiment one, two, three, the embodiment of the present invention adds the treatment step disconnecting described three-dimensional blood-vessel image medium vessels connection error position, also improve the modeling accuracy of three-dimensional blood-vessel image, if blood vessel connection error, the blood vessel section of propping up likely is caused to divide mistake when dividing, thus classification error when causing the blood vessel section of propping up to reclassify, and then cause the classification results of final liver three trunk type inaccurate.Thus the increase step that the present embodiment provides also can improve the accuracy that the Subsequent vessel section of propping up divides and blood vessel is classified.
The embodiment of the present invention carries out improving obtaining on the basis that embodiment one or embodiment one and two combine, and therefore has the beneficial effect of embodiment one, embodiment two, embodiment three simultaneously concurrently, do not repeat them here.
To sum up, the above embodiment of the present invention provides the method for multiple liver vessel classification, first after the three-dimensional blood-vessel image obtaining liver organ, again carry out the blood vessel section of propping up to often kind of vascular group respectively according to liver vessel type to divide, receive the instruction of the classification to the vascular group belonging to multiple blood vessel section of propping up of user's input, for specialized medical personnel user provides manual intervention means, secondary classification is carried out to vascular group, himself abundant professional knowledge can be utilized can to correct the defect that existing three-dimensional modeling algorithm and source data cause, thus improve the accuracy of liver vessel classification.
Simultaneously, this programme divides multiple blood vessel section of propping up respectively again according to three kinds of large vascular groups, this considers, three-dimensional modeling overall accuracy is higher on the one hand, defect mistake appears at the little branch vessel section of propping up aspect usually, therefore again divided by large vascular group, convenient classification little branch vessel, checks.
The three-dimensional blood-vessel image of vascular group classifying, updating after embodiment of the present invention scheme also upgrades according to multiple blood vessel section of propping up, thus also have updated the classification of liver three trunk, the practical medical that improve three-dimensional blood-vessel image with reference to using value, thus is convenient to medical personnel and is carried out preoperative estimating and accurate judgement in art.
And, also comprised before the division carrying out the blood vessel section of propping up and two dimensional image map correction is carried out to three-dimensional blood-vessel image, whether overlapped with the boundary line of two-dimentional blood-vessel image medium vessels tissue by the mapped profile line on the two-dimensional CT image of corresponding sequence of more three-dimensional blood-vessel image, if do not overlap, then vessel map outline line is adjusted, thus change the 2-D data category that Three-dimension Reconstruction Model uses, make the vascular tissue's source data closer to reality, the effect that three-dimensional blood-vessel image carries out correcting is served after rebuilding, make three-dimensional blood-vessel image more accurate, with realistic liver vessel, be convenient to medical personnel and Accurate classification is carried out to the blood vessel in liver, and then be convenient to medical personnel and carry out preoperative estimating and accurate judgement in art.
And, before the division carrying out the blood vessel section of propping up or after three-dimensional blood-vessel image carries out two dimensional image map correction, also comprise and the non-vascular tissue in three-dimensional blood-vessel image is removed, thus some non-essential tissue parts can be deleted, optimize three-dimensional blood-vessel image, also can improve the accuracy of the blood-vessel image of three-dimensional modeling, the accuracy of final blood vessel classification results can be improved.
And, before the division carrying out the blood vessel section of propping up, or after three-dimensional blood-vessel image carries out two dimensional image map correction, or afterwards, or before the non-vascular tissue in three-dimensional blood-vessel image is removed, or afterwards, also comprise the errors present disconnecting three-dimensional blood-vessel image medium vessels and connect, thus can correct the three-dimensional modeling position of mistake, also optimize three-dimensional blood-vessel image, thus improve the accuracy of blood vessel classification results.
No matter above-mentioned be that the two dimensional image of three-dimensional blood-vessel image maps, the removing of non-vascular tissue, or the disconnection of blood vessel incorrect link position, the aligning step to three-dimensional blood vessel model can be considered as, can select to be suitable for according to the concrete defect problem of 3-dimensional image model, are all the accuracys in order to improve three-dimensional blood-vessel image model, thus establish the basis that liver vessel correctly classifies.
One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that programmed instruction is relevant, aforesaid program can be stored in a computer read/write memory medium, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: ROM, RAM, magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (10)
1. a method for liver vessel classification, is characterized in that, comprising:
Obtain the three-dimensional blood-vessel image of liver organ;
Obtain arteria hepatica in described three-dimensional blood-vessel image respectively, portal vein, hepatic venous 3-D view;
Respectively according to described arteria hepatica, portal vein, often kind of vascular group is all divided into multiple blood vessel section of propping up by vena hepatica vascular group;
Receive the classification instruction of the vascular group to described multiple blood vessel section of propping up of user's input;
Vascular group classification after upgrading according to described multiple blood vessel section of propping up, upgrades described three-dimensional blood-vessel image.
2. method according to claim 1, is characterized in that,
Described three-dimensional blood-vessel image and described multiple blood vessel section of propping up are presented in same interface respectively.
3. method according to claim 1, is characterized in that, described respectively according to described arteria hepatica, and portal vein, vena hepatica vascular group also comprises before often kind of vascular group is all divided into multiple blood vessel section of propping up:
Described three-dimensional blood-vessel image is carried out two dimensional image map correction.
4. method according to claim 3, is characterized in that, describedly described three-dimensional blood-vessel image is carried out two dimensional image map correction comprises:
Obtain the mapped profile line on the two-dimensional CT image of described three-dimensional blood-vessel image corresponding sequence in described one group of two-dimensional CT image;
Judge whether whether described mapped profile line overlap with the border of the two-dimensional CT image medium vessels tissue of the corresponding sequence in described one group of two-dimensional CT image;
If do not overlap, adjust the overlapping margins of described mapped profile line and the two-dimensional CT image medium vessels tissue of described corresponding sequence;
The two-dimensional CT image data again three-dimensional modeling corresponding according to the mapped profile line after described adjustment, obtains the three-dimensional blood-vessel image after correcting.
5. method according to claim 1, is characterized in that, described respectively according to described arteria hepatica, and portal vein, vena hepatica vascular group also comprises before often kind of vascular group is all divided into multiple blood vessel section of propping up:
Remove the non-vascular tissue in described three-dimensional blood-vessel image.
6. method according to claim 5, is characterized in that, the non-vascular tissue in the described three-dimensional blood-vessel image of described removing comprises:
Receive the mark instructions of user;
According to described mark instructions, mark the described non-vascular tissue in described three-dimensional blood-vessel image;
Receive the clear instruction of described user;
According to described clear instruction, remove the non-vascular tissue in described three-dimensional blood-vessel image.
7. method according to claim 1, is characterized in that, described respectively according to described arteria hepatica, and portal vein, vena hepatica vascular group also comprises before often kind of vascular group is all divided into multiple blood vessel section of propping up:
Disconnect described three-dimensional blood-vessel image medium vessels connection error position.
8. method according to claim 7, is characterized in that, the described three-dimensional blood-vessel image medium vessels connection error position of described disconnection comprises:
Receive second mark instructions of described user;
According to described second mark instructions, mark the position of described three-dimensional blood-vessel image medium vessels connection error;
Receive second clear instruction of described user;
According to described second clear instruction, remove the position of described second three-dimensional blood-vessel image medium vessels connection error.
9. method according to claim 1, it is characterized in that, described respectively according to described arteria hepatica, portal vein, often kind of vascular group is all divided into multiple blood vessel section of propping up and specifically comprises by vena hepatica vascular group: respectively according to described arteria hepatica, portal vein, often kind of vascular group is all divided into 4 to 8 blood vessel sections of propping up by vena hepatica vascular group.
10. according to the method in claim 2 or 3, it is characterized in that, the classification instruction of the vascular group to described multiple blood vessel section of propping up of described reception user input comprises:
Described multiple blood vessel section of propping up has property value, and described property value at least comprises the vascular group belonging to described each blood vessel section of propping up;
The lastest imformation receiving the property value to described multiple blood vessel section of propping up of user's input indicates the classification of the vascular group of described multiple blood vessel section of propping up to obtain.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510506303.5A CN105139030A (en) | 2015-08-18 | 2015-08-18 | Method for sorting hepatic vessels |
| PCT/CN2016/074386 WO2017028519A1 (en) | 2015-08-18 | 2016-02-23 | Hepatic vascular classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510506303.5A CN105139030A (en) | 2015-08-18 | 2015-08-18 | Method for sorting hepatic vessels |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105139030A true CN105139030A (en) | 2015-12-09 |
Family
ID=54724373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510506303.5A Pending CN105139030A (en) | 2015-08-18 | 2015-08-18 | Method for sorting hepatic vessels |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105139030A (en) |
| WO (1) | WO2017028519A1 (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017028519A1 (en) * | 2015-08-18 | 2017-02-23 | 青岛海信医疗设备股份有限公司 | Hepatic vascular classification method |
| CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
| CN106897564A (en) * | 2017-02-28 | 2017-06-27 | 成都金盘电子科大多媒体技术有限公司 | A kind of medical record image modeling system based on medical image |
| CN107784038A (en) * | 2016-08-31 | 2018-03-09 | 法乐第(北京)网络科技有限公司 | A kind of mask method of sensing data |
| CN108937978A (en) * | 2018-04-20 | 2018-12-07 | 重庆大学 | A kind of Layering manifestation method of blood flow complete alternation imaging algorithm |
| CN109758136A (en) * | 2019-02-28 | 2019-05-17 | 四川大学华西医院 | Hepatic vein pressure gradient measurement method based on portal vein blood vessel feature |
| CN109949322A (en) * | 2019-03-27 | 2019-06-28 | 中山大学 | A kind of cerebrovascular image partition method based on magnetic resonance T1 enhancing image |
| CN111311583A (en) * | 2020-02-24 | 2020-06-19 | 广州柏视医疗科技有限公司 | Method and system for naming pulmonary trachea and blood vessel in segmented mode |
| CN111666972A (en) * | 2020-04-28 | 2020-09-15 | 清华大学 | Liver case image classification method and system based on deep neural network |
| CN112489051A (en) * | 2020-11-13 | 2021-03-12 | 深圳市旭东数字医学影像技术有限公司 | Liver cutting method and system based on blood vessels and lesion areas |
| CN112826535A (en) * | 2020-12-31 | 2021-05-25 | 青岛海信医疗设备股份有限公司 | Method, device and equipment for automatically positioning blood vessel in ultrasonic imaging |
| CN113096066A (en) * | 2021-02-26 | 2021-07-09 | 杭州臻合健康科技有限公司 | Intelligent hepatic portal vein based typing method |
| CN113763331A (en) * | 2021-08-17 | 2021-12-07 | 北京医准智能科技有限公司 | Coronary artery dominant type determination method, device, storage medium, and electronic apparatus |
| CN115760961A (en) * | 2021-09-01 | 2023-03-07 | 数坤(北京)网络科技股份有限公司 | Blood vessel image processing method, device, server and post-processing image generation system |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112842371A (en) * | 2021-01-29 | 2021-05-28 | 上海商汤智能科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN117635950B (en) * | 2024-01-04 | 2024-04-09 | 广东欧谱曼迪科技股份有限公司 | Method, device, electronic equipment and storage medium for vessel segmentation correction processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101203890A (en) * | 2005-06-24 | 2008-06-18 | 美国医软科技公司 | Methods for interactive liver disease diagnosis |
| CN102048550A (en) * | 2009-11-02 | 2011-05-11 | 上海交通大学医学院附属仁济医院 | Method for automatically generating liver 3D (three-dimensional) image and accurately positioning liver vascular domination region |
| CN102117378A (en) * | 2009-12-31 | 2011-07-06 | 苏州瑞派宁科技有限公司 | Hepatic tumor comprehensive surgical planning analogy method and system thereof based on three-dimensional multimode images |
| CN102938027A (en) * | 2012-11-30 | 2013-02-20 | 河北大学 | Realization method of computer-assisted liver transplantation operation planning system |
| CN104463860A (en) * | 2014-12-01 | 2015-03-25 | 冯炳和 | Method for segmenting liver |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8612890B2 (en) * | 2007-12-14 | 2013-12-17 | Koninklijke Philips N.V. | Labeling a segmented object |
| EP2335189B1 (en) * | 2008-09-23 | 2020-05-27 | Edda Technology, Inc. | Methods for interactive labeling of tubular structures in medical imaging |
| CN105139030A (en) * | 2015-08-18 | 2015-12-09 | 青岛海信医疗设备股份有限公司 | Method for sorting hepatic vessels |
-
2015
- 2015-08-18 CN CN201510506303.5A patent/CN105139030A/en active Pending
-
2016
- 2016-02-23 WO PCT/CN2016/074386 patent/WO2017028519A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101203890A (en) * | 2005-06-24 | 2008-06-18 | 美国医软科技公司 | Methods for interactive liver disease diagnosis |
| CN102048550A (en) * | 2009-11-02 | 2011-05-11 | 上海交通大学医学院附属仁济医院 | Method for automatically generating liver 3D (three-dimensional) image and accurately positioning liver vascular domination region |
| CN102117378A (en) * | 2009-12-31 | 2011-07-06 | 苏州瑞派宁科技有限公司 | Hepatic tumor comprehensive surgical planning analogy method and system thereof based on three-dimensional multimode images |
| CN102938027A (en) * | 2012-11-30 | 2013-02-20 | 河北大学 | Realization method of computer-assisted liver transplantation operation planning system |
| CN104463860A (en) * | 2014-12-01 | 2015-03-25 | 冯炳和 | Method for segmenting liver |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017028519A1 (en) * | 2015-08-18 | 2017-02-23 | 青岛海信医疗设备股份有限公司 | Hepatic vascular classification method |
| CN107784038A (en) * | 2016-08-31 | 2018-03-09 | 法乐第(北京)网络科技有限公司 | A kind of mask method of sensing data |
| CN107784038B (en) * | 2016-08-31 | 2021-03-19 | 法法汽车(中国)有限公司 | Sensor data labeling method |
| CN106780728B (en) * | 2017-02-28 | 2020-05-01 | 成都金盘电子科大多媒体技术有限公司 | Medical image-based single organ splitting method and system |
| CN106780728A (en) * | 2017-02-28 | 2017-05-31 | 成都金盘电子科大多媒体技术有限公司 | A kind of single organ method for splitting and system based on medical image |
| CN106897564B (en) * | 2017-02-28 | 2019-12-03 | 成都金盘电子科大多媒体技术有限公司 | A kind of medical record image modeling system based on medical image |
| CN106897564A (en) * | 2017-02-28 | 2017-06-27 | 成都金盘电子科大多媒体技术有限公司 | A kind of medical record image modeling system based on medical image |
| CN108937978A (en) * | 2018-04-20 | 2018-12-07 | 重庆大学 | A kind of Layering manifestation method of blood flow complete alternation imaging algorithm |
| CN109758136A (en) * | 2019-02-28 | 2019-05-17 | 四川大学华西医院 | Hepatic vein pressure gradient measurement method based on portal vein blood vessel feature |
| CN109949322A (en) * | 2019-03-27 | 2019-06-28 | 中山大学 | A kind of cerebrovascular image partition method based on magnetic resonance T1 enhancing image |
| CN111311583A (en) * | 2020-02-24 | 2020-06-19 | 广州柏视医疗科技有限公司 | Method and system for naming pulmonary trachea and blood vessel in segmented mode |
| CN111666972A (en) * | 2020-04-28 | 2020-09-15 | 清华大学 | Liver case image classification method and system based on deep neural network |
| CN112489051A (en) * | 2020-11-13 | 2021-03-12 | 深圳市旭东数字医学影像技术有限公司 | Liver cutting method and system based on blood vessels and lesion areas |
| CN112489051B (en) * | 2020-11-13 | 2024-04-05 | 深圳市旭东数字医学影像技术有限公司 | Liver cutting method and system based on blood vessels and lesion areas |
| CN112826535A (en) * | 2020-12-31 | 2021-05-25 | 青岛海信医疗设备股份有限公司 | Method, device and equipment for automatically positioning blood vessel in ultrasonic imaging |
| CN113096066A (en) * | 2021-02-26 | 2021-07-09 | 杭州臻合健康科技有限公司 | Intelligent hepatic portal vein based typing method |
| CN113763331A (en) * | 2021-08-17 | 2021-12-07 | 北京医准智能科技有限公司 | Coronary artery dominant type determination method, device, storage medium, and electronic apparatus |
| CN115760961A (en) * | 2021-09-01 | 2023-03-07 | 数坤(北京)网络科技股份有限公司 | Blood vessel image processing method, device, server and post-processing image generation system |
| CN115760961B (en) * | 2021-09-01 | 2023-08-29 | 数坤(北京)网络科技股份有限公司 | Vascular image processing method, vascular image processing device, server and post-processing image generation system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017028519A1 (en) | 2017-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139030A (en) | Method for sorting hepatic vessels | |
| CN107358595B (en) | Method and system for lobe segmentation and preoperative surgical planning | |
| CN107808156A (en) | Area-of-interest exacting method | |
| KR20130100758A (en) | 3d virtual liver surgery planning system | |
| US20110052026A1 (en) | Method and Apparatus for Determining Angulation of C-Arm Image Acquisition System for Aortic Valve Implantation | |
| CN102968783B (en) | Automatically the method and system of skeleton are split from abdomen image data | |
| JP2008521461A (en) | Method for measuring tubular organs using knowledge structure mapping | |
| JPWO2011152094A1 (en) | Medical device and method for controlling medical device | |
| CN103049638A (en) | Semi-automated preoperative resection planning | |
| CN105956395A (en) | Medical image processing method, device and system | |
| CN103810752A (en) | Liver segmenting method based on medical image and liver segmenting system thereof | |
| CN113693725A (en) | Needle insertion path planning method, device, equipment and storage medium | |
| CN106952264B (en) | Method and device for cutting three-dimensional medical target | |
| CN112331311B (en) | Method and device for fusion display of video and preoperative model in laparoscopic surgery | |
| CN106469445A (en) | A kind of calibration steps of 3-D view, device and system | |
| EP4241248A1 (en) | System and method for annotation of anatomical tree structures in 3d images | |
| CN105513055A (en) | Method and apparatus for segmenting tissue in CTA image | |
| WO2021081771A1 (en) | Vrds ai medical image-based analysis method for heart coronary artery, and related devices | |
| CN115938542A (en) | Image-guided ablation path optimization method based on three-dimensional topological analysis | |
| CN107464243A (en) | A kind of localization method of aorta petal, device and equipment | |
| CN113628346A (en) | Method for freely browsing VB (visual basic) and method and system for marking | |
| CN115908225A (en) | Tubular organ labeling method, tubular organ labeling result correction method and tubular organ labeling result correction system | |
| CN105574862A (en) | Semi-automatic liver segmenting method | |
| US11380060B2 (en) | System and method for linking a segmentation graph to volumetric data | |
| CN111161241B (en) | Liver image identification method, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Yongjian Inventor after: Liu Rong Inventor after: Liu Lili Inventor after: Wang Fei Inventor before: Liu Lili Inventor before: Chen Yongjian |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151209 |