CN117437321B - Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging - Google Patents
Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging Download PDFInfo
- Publication number
- CN117437321B CN117437321B CN202311753293.6A CN202311753293A CN117437321B CN 117437321 B CN117437321 B CN 117437321B CN 202311753293 A CN202311753293 A CN 202311753293A CN 117437321 B CN117437321 B CN 117437321B
- Authority
- CN
- China
- Prior art keywords
- interest
- arterial
- region
- artifact
- image
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 78
- 238000003384 imaging method Methods 0.000 title claims abstract description 38
- 238000002372 labelling Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 58
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000010412 perfusion Effects 0.000 claims abstract description 41
- 230000009466 transformation Effects 0.000 claims abstract description 29
- 210000004556 brain Anatomy 0.000 claims abstract description 25
- 238000013210 evaluation model Methods 0.000 claims abstract description 14
- 239000003550 marker Substances 0.000 claims description 22
- 230000036770 blood supply Effects 0.000 claims description 13
- 230000002490 cerebral effect Effects 0.000 claims description 13
- 238000007637 random forest analysis Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 9
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 230000017531 blood circulation Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 210000002551 anterior cerebral artery Anatomy 0.000 description 5
- 210000003388 posterior cerebral artery Anatomy 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- WYTGDNHDOZPMIW-RCBQFDQVSA-N alstonine Natural products C1=CC2=C3C=CC=CC3=NC2=C2N1C[C@H]1[C@H](C)OC=C(C(=O)OC)[C@H]1C2 WYTGDNHDOZPMIW-RCBQFDQVSA-N 0.000 description 2
- 210000004227 basal ganglia Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 210000003657 middle cerebral artery Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000926 neurological effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 206010060965 Arterial stenosis Diseases 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000005013 brain tissue Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003788 cerebral perfusion Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007917 intracranial administration Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000000700 radioactive tracer Substances 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000012764 semi-quantitative analysis Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/008—Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
-
- 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
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
-
- 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
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Abstract
The embodiment of the invention provides a method and a device for automatically evaluating arterial transit artifacts by magnetic resonance spin marking imaging, wherein the method comprises the following steps: acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image; registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix; applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all regions of interest; dividing the region of interest according to the mask to obtain a plurality of arterial navigation artifact regions of interest; extracting features to obtain image features of the region of interest of the arterial navigation artifact; inputting the pre-trained corresponding region-of-interest evaluation model to obtain the evaluation result of each arterial navigation artifact region-of-interest. The automatic evaluation of the arterial navigation artifact is realized, and compared with manual evaluation, the automatic evaluation is higher in efficiency.
Description
Technical Field
The embodiment of the invention relates to the technical field of medical image processing, in particular to a method and a device for automatically evaluating arterial transit artifacts of magnetic resonance spin mark imaging.
Background
Magnetic resonance spin labeling imaging (Arterial Spin Labelling, ASL) uses the blood flow after labeling as an endogenous tracer, a clinically common non-invasive imaging technique to assess perfusion. For assessment of brain perfusion, the most common ASL method is pseudo-continuous marker ASL (pseudo Continuous ASL, pCASL). When the pCASL is used for imaging, firstly, the position of the outer near-center end of an imaging area is selected, all blood flows flowing into the imaging area are marked, after the marking time (Label Duration, LD) is passed, the marking is completed, at the moment, the image acquisition is not carried out, after the marking is carried out, the waiting time Post Labelling Delay, PLD) is passed, the image acquisition is started, and the marked image is obtained after the image acquisition is completed. And for the same imaging area, blood flow marking is not carried out, and the same parameters are used for acquisition, so that an unlabeled image is obtained. Subtracting the marked image from the unmarked image yields a difference map of the two, namely a perfusion weighted image (Perfusion Weighted Image, PWI), noted as ASL-PWI.
The ASL method is very sensitive to arterial arrival times (Arterial Arrival Time, AAT), and if AAT is greater than PLD, at the beginning of the acquisition of the marked image, part of the marked blood flow is still present in the arterial vessel, which results in a bright serpentine or speckle-like intravascular signal on the final ASL-PWI image. These intravascular high signals on ASL-PWI images are arterial transit artifacts (Arterial Transit Artefact, ATA). At present, ATA is evaluated by manual visual inspection, however, manual evaluation depends on experience of doctors, and there may be problems of repeatability such as difference among evaluators, and the overall process efficiency is not high because layers to be evaluated and window width and window levels of images to be manually adjusted need to be manually found and positioned. In view of the foregoing, there is a need for an automated ATA evaluation method.
Disclosure of Invention
The embodiment of the invention provides a method and a device for automatically evaluating arterial transit artifacts of magnetic resonance spin mark imaging, which are used for solving the problems of low repeatability and low efficiency in the conventional manual ATA evaluation.
In a first aspect, an embodiment of the present invention provides a method for automatically evaluating arterial transit artifacts by magnetic resonance spin labeling, including:
acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of an evaluation object;
registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix;
applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all regions of interest;
performing region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial transit artifact regions of the magnetic resonance spin-marker perfusion weighted image;
extracting features of each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest;
and inputting the image characteristics of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of each arterial navigation artifact region of interest of the evaluation object.
In one embodiment, the pre-set region of interest map specific to the arterial navigation artifact is generated by level selection in a first level region of a cerebral blood supply map, the cerebral blood supply map having the same field of view and resolution as the cerebral template image.
In one embodiment, during the layer selection, all layers within a preset range of the upper and lower layers of the nucleus and the nucleus in the cerebral blood supply map are selected.
In one embodiment, the spatial transformation matrix satisfies the following expression:
wherein,representing brain template image, < >>Representing proton density weighted images, ">Representing normalized mutual information function,/->Representing the spatial transformation matrix.
In one embodiment, the image features of the region of interest of each arterial navigation artifact include first order statistical features of the image, gray level co-occurrence matrix features, gray level region size matrix features, gray level travel matrix features, neighborhood gray level difference matrix features, and neighborhood gray level dependency matrix features.
In one embodiment, the region of interest assessment model employs a supervised random forest model that determines model parameters including a number of decision trees, a maximum number of features, and a maximum depth by a grid search method.
In one embodiment, the method further comprises:
when the evaluation object is scanned a plurality of times, a magnetic resonance spin-marker perfusion weighted image and a proton density weighted image of the evaluation object are acquired based on an average of the plurality of scans.
In a second aspect, an embodiment of the present invention provides an automatic assessment apparatus for arterial transit artifact by magnetic resonance spin labeling, including:
the acquisition module is used for acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of the evaluation object;
the registration module is used for registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix;
the processing module is used for applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all the regions of interest;
the segmentation module is used for carrying out region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial transit artifact regions of the magnetic resonance spin-marker perfusion weighted image;
the extraction module is used for extracting characteristics of each arterial navigation artifact region of interest to obtain image characteristics of each arterial navigation artifact region of interest;
the evaluation module is used for inputting the image characteristics of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of each arterial navigation artifact region of interest of the evaluation object.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor and memory;
the memory stores computer-executable instructions;
at least one processor executes computer-executable instructions stored in a memory, causing the at least one processor to perform the method of automatic assessment of arterial traversal artifact for magnetic resonance spin-marker imaging according to any one of the first aspects.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having stored therein computer-executable instructions, which when executed by a processor are configured to implement a method for automatically evaluating arterial traversal artifacts for magnetic resonance spin-marker imaging according to any one of the first aspects.
The embodiment of the invention provides a method and a device for automatically evaluating the arterial transit artifact of a magnetic resonance spin mark imaging, which are used for acquiring a magnetic resonance spin mark perfusion weighted image and a proton density weighted image of an evaluation object; registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix; applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all regions of interest; performing region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial transit artifact regions of the magnetic resonance spin-marker perfusion weighted image; extracting features of each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest; and inputting the image characteristics of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of each arterial navigation artifact region of interest. The automatic evaluation of the arterial transit artifact based on the magnetic resonance spin marking imaging is realized, and compared with the manual evaluation, the automatic evaluation is higher in efficiency.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow chart of an automatic evaluation method for arterial transit artifact by magnetic resonance spin labeling imaging according to an embodiment of the present invention;
FIG. 2 is a diagram of an ATA-dedicated ROI map region according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an automatic evaluation device for arterial transit artifact by magnetic resonance spin labeling according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Specific embodiments of the present invention have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
The invention will be described in further detail below with reference to the drawings by means of specific embodiments. Wherein like elements in different embodiments are numbered alike in association. In the following embodiments, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted, or replaced by other elements, materials, or methods in different situations. In some instances, some operations associated with the present application have not been shown or described in the specification to avoid obscuring the core portions of the present application, and may not be necessary for a person skilled in the art to describe in detail the relevant operations based on the description herein and the general knowledge of one skilled in the art.
Furthermore, the described features, operations, or characteristics of the description may be combined in any suitable manner in various embodiments. Also, various steps or acts in the method descriptions may be interchanged or modified in a manner apparent to those of ordinary skill in the art. Thus, the various orders in the description and drawings are for clarity of description of only certain embodiments, and are not meant to be required orders unless otherwise indicated.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning. The terms "coupled" and "connected," as used herein, are intended to encompass both direct and indirect coupling (coupling), unless otherwise indicated.
The technical terms referred to in the present application will be explained first:
arterial transit artifacts, arterial pass artifacts: chinese translations, which are English (Arterial Transit Artefact, ATA), are various because the mining of the ATA value is still concentrated in the scientific research field;
window width window level: the window width refers to the CT value range displayed by the CT image, the window level refers to the central value in the window width range, and the window width window level is a common term in medical images;
MNI standard space: the standard brain template space of adults established by the montreal nerve institute (Montreal Neurological Institute, MNI) of canada has very wide application in brain image analysis;
cross-validation: in the machine learning process, taking out most samples for model training, leaving small samples for testing by the newly built model, and recording the performance of the model on the small samples, wherein the process is carried out until all samples are forecasted once and only once;
grid search: all combinations of parameters within a range are traversed to optimize the performance of the model.
When performing brain perfusion assessment by the pCASL method, key parameters are to set a Label Duration (LD) and a post-Label latency (Post Labelling Delay, PLD) in addition to a Flip Angle (FA), field of View (FOV), resolution, which are common to general magnetic resonance imaging sequences. Wherein LD is the time of pseudo-continuous radio frequency pulse marking of blood flow, and the size affects the total amount of marked blood flow; PLD is the wait time after the completion of the marking. When the pCASL is used for imaging, the position of the outer side near-center end of the imaging area is selected, all blood flowing into the imaging area is marked, after the LD time, marking is completed, at this time, image acquisition is not performed, and after the PLD time, image acquisition is started, and the marked image is obtained after the image acquisition is completed. And for the same imaging area, blood flow marking is not carried out, and the same parameters are used for acquisition, so that an unlabeled image is obtained. Subtracting the marked image from the unmarked image yields a difference map of the two, namely a perfusion weighted image (Perfusion Weighted Image, PWI), noted as ASL-PWI. Proton density weighted (Proton Density Weighted, PDW) images are also acquired in the same imaging region during ASL scanning for subsequent quantitative analysis of perfusion.
The time required for the labeled blood flow to reach from the label into capillaries of brain tissue in the imaging region is typically referred to as arterial arrival time (Arterial Arrival Time, AAT). Since the ASL method is very sensitive to AAT, if AAT is greater than PLD, at the beginning of the acquisition of the marked image, part of the marked blood flow is still present in the arterial vessel, which results in a bright serpentine or speckle-like intravascular signal on the final ASL-PWI image. These intravascular signals on ASL-PWI images are arterial transit artifacts (Arterial Transit Artefact, ATA). Although ATA can be reduced or even eliminated by providing a larger PLD, a larger PLD not only reduces the signal-to-noise ratio of the image, but also extends the scan time. Therefore, by setting proper PLD, the influence of ATA, signal-to-noise ratio and scanning time can be balanced, and the optimal checking effect can be achieved.
AAT is not the same for different tissues (i.e., blood flows to different tissues at different times), whereas performing blood flow labeling once can only set the same PLD for all imaging areas (only consider the case of a single PLD), so ATA often appears on ASL-PWI images. However, ATA, this "artifact" is actually an intuitive, useful message. ATA generally occurs because arterial stenosis blocks blood flow, or there is a collateral vascular access resulting in a delay in blood flow to the target area, or a slower overall blood flow velocity. Research shows that whether the ASL-PWI has ATA and the distribution of the ATA and the severity of the ATA are related to the perfusion state and collateral blood vessel distribution of the patient, has important significance in the aspects of evaluating the influence caused by the cerebrovascular diseases, predicting the postoperative adverse reaction and the like, and has great research and clinical value in the cerebral perfusion field.
At present, for the evaluation of ATA, an intuitive manual visual scoring method is adopted, and the method comprises the following steps: on ASL-PWI images, two planes, namely a basal ganglia nucleus layer and a basal ganglia nucleus upper layer, are selected to find 20 total areas affected by Anterior Cerebral Artery (ACA), middle Cerebral Artery (MCA) and Posterior Cerebral Artery (PCA) for the left and right hemispheres respectively (the left and right sides have the A1-A2, M1-M6 and P1-P2 areas respectively). For each region, ATA was evaluated using a 4-point method: a score of 0 indicates that no ASL signal could be observed; a score of 1 indicates that ATA can be observed with a lower to average ASL signal in the region; score 2 indicates that ATA can be observed with a higher ASL signal in the region; the 3-division indicates a normal ASL signal without ATA. In view of the stability of the score, the observer can comprehensively consider images of adjacent layers at the time of ATA evaluation. And after the ATA scoring of all 20 areas is completed, obtaining a final ATA evaluation result.
Although ATA evaluation by manual visual observation is more intuitive, there are also many problems, for example, manual evaluation relies on doctor experience, and semi-quantitative analysis may have problems of reproducibility such as inter-evaluator differences; manual evaluation is required to manually find and position a layer to be evaluated, manually adjust window width and window level of an image, then observe, and the whole process is time-consuming and labor-consuming, and efficiency is difficult to improve. The automatic evaluation of ATA not only helps to improve the efficiency of clinical interpretation, but also enhances the repeatability of the evaluation results.
In order to solve at least one of the problems, the application provides an automatic evaluation method for magnetic resonance spin labeling imaging arterial transit artifact based on machine learning, which can automatically, accurately and reliably perform ATA evaluation on an ASL-PWI image. Specific examples will be used to describe in detail the methods provided herein.
Fig. 1 is a flowchart of a method for automatically evaluating arterial transit artifact by magnetic resonance spin labeling imaging according to an embodiment of the present invention. As shown in fig. 1, the method for automatically evaluating arterial transit artifact by using magnetic resonance spin labeling imaging according to the present embodiment may include:
s101, acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of an evaluation object.
In this embodiment, a pseudo-continuous magnetic resonance spin labeling imaging (pCASL) scan may be performed on the evaluation object by the magnetic resonance imaging apparatus, to obtain scanned raw image data. The obtained original image data is exported in a DICOM format, and a marked image, an unmarked image and a Proton Density Weighted (PDW) image can be obtained respectively according to meta information describing scanning parameters of the DICOM file. From the pCASL scanning principle, PDW images, unlabeled images and labeled images are already registered. The unlabeled image is sequentially used to directly subtract the labeled image, so that a magnetic resonance spin labeling perfusion weighted (ASL-PWI) image of the evaluation object can be obtained.
When the evaluation object is scanned a plurality of times, a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of the evaluation object are obtained based on an average value of the plurality of times, so as to further improve the accuracy of the evaluation. Further, if it is not available from the original image data, the unlabeled image is taken as a substitute for the PDW image.
S102, registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix.
The brain template image in this embodiment is predetermined and does not change during the evaluation. In an alternative embodiment, a resolution of 1x1x1mm in the MNI (Montreal Neurological Institute) standard space may be used, for example 3 As a preset brain template image. Furthermore, the neuroradiologist can be also asked to determine the positions of the nucleus layer and the nucleus upper layer in the brain template image, and the positions of the nucleus layer and the nucleus upper layer are respectively marked as z1 and z2.
Registering the proton density weighted image with a preset brain template image to obtain a space transformation matrixThe following expression is satisfied:
wherein,representing brain template image, < >>Representing proton density weighted images, ">Representing normalized mutual information function,/->Representing the spatial transformation matrix.
S103, applying the space transformation matrix to a preset region-of-interest map special for the arterial navigation artifact, and obtaining masks of all the regions of interest.
The preset region of interest (ROI) map specific to arterial navigation artifact (ATA) in this embodiment is generated by manually sketching by a imaging expert with related experience, and the ROI map has the same field of view and resolution as the brain template image. The obtained ATA-dedicated ROI map region is shown in FIG. 2, which shows the correspondence between the brain blood supply map and the ATA-dedicated ROI map region. Note that, fig. 2 only shows the area correspondence relationship of one side, and the other side is identical except for the left-right position change. Fig. 2 is a schematic diagram of an ATA-specific ROI map region according to an embodiment of the present invention. Wherein the left graph is the nucleus layer and the right graph is the nucleus upper layer.
To further increase the reliability of ATA evaluation, the present embodiment also considers the images of the nucleus pulposus layer and the nearby layers of the nucleus pulposus upper layer comprehensively (rather than just observing the two layers). Therefore, when the ATA-dedicated ROI map is prepared, all the layers within the ranges of z1+ -3 mm and z2+ -3 mm are respectively selected as the layers of the corresponding region. That is, in an alternative embodiment, all levels within a predetermined range above and below the level of the nucleus pulposus and the level above the nucleus pulposus in the cerebral blood supply map are selected when the level selection is performed.
The ATA special ROI map reflects the attribution relation of each voxel in the image in the MNI standard space, and the attribution judgment of each voxel of the image in the MNI standard space can be completed by using the map, namely, which ROI area each voxel belongs to is defined. Therefore, by applying the space transformation matrix to the preset region-of-interest map special for the arterial navigation artifact, masks of all the regions-of-interest can be obtained in the space where the magnetic resonance spin-labeling perfusion weighted image is located.
In another alternative embodiment, a deformation field (shaping field) and a transformation matrix (affine matrix) obtained by registering the PDW image and the brain template image may be applied to the ASL-PWI image, and the ASL-PWI image may be registered to the space where the brain template image is located. The space transformation T is applied to the ATA special ROI map, mask (Mask) operation is carried out on the ASL-PWI image, so that the part in the ROI on the ASL-PWI image can be obtained, and the ROI segmentation is completed.
And S104, segmenting the region of interest on the magnetic resonance spin labeling perfusion weighted image according to the mask to obtain a plurality of arterial navigation artifact regions of interest of the magnetic resonance spin labeling perfusion weighted image.
After obtaining the mask of each region of interest, region of interest segmentation can be performed on the ASL-PWI image according to the mask to obtain a plurality of arterial navigation artifact regions of the magnetic resonance spin-labeled perfusion weighted image. In this example, 20 ATA regions of interest were obtained, 10 on each of the left and right sides, specifically including the M1-M6 blood supply region, the A1-A2 region of the anterior cerebral artery (Anterior Cerebral Artery, ACA), and the P1-P2 region of the posterior cerebral artery (Posterior Cerebral Artery, PCA). And performing Mask (Mask) operation on the ASL-PWI image to obtain the part in the ROI on the ASL-PWI image, and completing the ROI segmentation.
S105, extracting features of each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest.
For each segmented arterial navigation artifact ROI, image feature extraction is performed on ASL-PWI images. All features were obtained on ASL-PWI images without filtering. The image features of the region of interest of the arterial navigation artifact in this embodiment include: first order statistical features (First Order Features) of the image; gray Level Co-occurrence Matrix Features, GLCM Features; gray area size matrix Features (Gray Level Size Zone Matrix Features, GLSZM Features); gray scale travel matrix Features (Gray Level Run Length Matrix Features, GLRLM Features); neighborhood gray scale difference matrix Features (Neighbouring Gray Tone Difference Matrix Features, NGTDM Features); neighborhood gray level dependent matrix features (Gray Level Dependence Matrix Features, GLDM Feature).
S106, inputting the image features of the regions of interest of the arterial navigation artifact into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of the regions of interest of the arterial navigation artifact of the evaluation object.
In this embodiment, a supervised Random Forest (Random Forest) model is used for ATA evaluation, and training data is labeled by taking a consensus of at least 2 artificial ATA evaluation results of experienced neuroradiologists as a gold standard when training the model. The dividing ratio of the training set and the test set is 7: and 3, inputting all the extracted features into a random forest model and initializing the random forest model for each ROI which is already segmented, performing 5-fold cross validation on a training set, and determining the optimal parameter combination (the adjusted parameters are the number of decision trees, the maximum feature number and the maximum depth) of the random forest model by adopting a Grid Search method. Model training and testing may be performed, for example, using a scikit-learn tool. That is, in an alternative embodiment, the region of interest assessment model employs a supervised random forest model that determines model parameters including the number of decision trees, the number of maximum features, and the maximum depth by a grid search method. It should be noted that, in this embodiment, there is a corresponding pre-trained evaluation model for each ATA region of interest, that is, there are 20 pre-trained evaluation models in total.
And carrying out ATA evaluation on the corresponding regions of interest by adopting 20 pre-trained evaluation models, so that ATA scores of all the regions of interest can be obtained, and automatic ATA evaluation is completed.
The magnetic resonance spin mark imaging artery passing artifact automatic evaluation method provided by the embodiment obtains a magnetic resonance spin mark perfusion weighted image and a proton density weighted image of an evaluation object; registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix; applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all regions of interest; performing region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial transit artifact regions of the magnetic resonance spin-marker perfusion weighted image; extracting features of each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest; and inputting the image characteristics of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of each arterial navigation artifact region of interest. The automatic evaluation of the arterial transit artifact based on the magnetic resonance spin marking imaging is realized, and compared with the manual evaluation, the automatic evaluation is higher in efficiency.
In summary, according to the automatic evaluation method for the arterial transit artifact by the magnetic resonance spin labeling imaging provided by the application, semi-quantitative scoring is performed on the blood supply region of the intracranial great vessel, and the nucleus layer and the nucleus upper layer are selected for evaluation, wherein the evaluation basis is from the image characteristics in the region. Specifically, for ATA automatic evaluation, an ATA special ROI map is provided, and region of interest segmentation is performed, so that accuracy of ATA evaluation is improved; based on machine learning, the automatic evaluation complexity of ATA is low, the calculation speed is high, and compared with manual evaluation, the automatic evaluation method has more stable performance and more efficient processing speed. The problem of repeatability of manually evaluating ATA is solved, and the problems of time consumption, labor consumption, low efficiency and the like are solved.
Fig. 3 is a schematic structural diagram of an automatic evaluation device for arterial transit artifact by magnetic resonance spin labeling imaging according to an embodiment of the present invention. As shown in fig. 3, the magnetic resonance spin labeling imaging arterial transit artifact automatic assessment device 30 provided in the present embodiment may include:
an acquisition module 301 for acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of the evaluation object;
the registration module 302 is configured to register the proton density weighted image with a preset brain template image to obtain a spatial transformation matrix;
the processing module 303 is configured to apply the spatial transformation matrix to a preset region-of-interest map dedicated to arterial navigation artifact, so as to obtain masks of each region-of-interest;
the segmentation module 304 is configured to segment the region of interest on the magnetic resonance spin-marker perfusion weighted image according to the mask, so as to obtain a plurality of arterial traversal artifact regions of interest of the magnetic resonance spin-marker perfusion weighted image;
the extracting module 305 is configured to perform feature extraction on each arterial navigation artifact region of interest, so as to obtain image features of each arterial navigation artifact region of interest;
and the evaluation module 306 is configured to input the image features of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model, so as to obtain an evaluation result of each arterial navigation artifact region of interest.
The device of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and are not described here again.
In an alternative embodiment, the preset region of interest map specific to the arterial navigation artifact is generated by performing a level selection in a first level region of a cerebral blood supply map, the cerebral blood supply map having the same field of view and resolution as the cerebral template image.
In an alternative embodiment, all layers within a preset range of the upper and lower layers of the nucleus and the nucleus in the cerebral blood supply map are selected when the layer selection is performed.
In an alternative embodiment, the spatial transformation matrix satisfies the following expression:
wherein,representing brain template image, < >>Representing proton density weighted images, ">Representing normalized mutual information function,/->Representing a spatial transformation matrix。
In an alternative embodiment, the image features of each arterial navigation artifact region of interest include first order statistical features of the image, gray level co-occurrence matrix features, gray level region size matrix features, gray level travel matrix features, neighborhood gray level difference matrix features, and neighborhood gray level dependency matrix features.
In an alternative embodiment, the region of interest assessment model employs a supervised random forest model, and the supervised random forest model determines model parameters by a grid search method, where the model parameters include a number of decision trees, a maximum feature number, and a maximum depth.
In an alternative embodiment, the obtaining module 301 is further configured to obtain, when the evaluation object is scanned multiple times, a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of the evaluation object based on an average value of the multiple scans.
An embodiment of the present invention further provides an electronic device, and referring to fig. 4, the embodiment of the present invention is illustrated by taking fig. 4 as an example only, and the present invention is not limited thereto. Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 4, the electronic device 40 provided in this embodiment may include: memory 401, processor 402, and bus 403. Wherein the bus 403 is used to implement the connections between the elements.
The memory 401 stores a computer program, which when executed by the processor 402 can implement the technical solution of any of the above-mentioned method embodiments.
Wherein the memory 401 and the processor 402 are electrically connected directly or indirectly to enable transmission or interaction of data. For example, the elements may be electrically coupled to each other via one or more communication buses or signal lines, such as via bus 403. The memory 401 stores therein a computer program for implementing the automatic assessment method of arterial navigation artifact by magnetic resonance spin-marker imaging, comprising at least one software functional module stored in the memory 401 in the form of software or firmware, and the processor 402 executes various functional applications and data processing by running the software program and module stored in the memory 401.
The Memory 401 may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc. The memory 401 is used for storing a program, and the processor 402 executes the program after receiving an execution instruction. Further, the software programs and modules within the memory 401 described above may also include an operating system, which may include various software components and/or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components.
The processor 402 may be an integrated circuit chip with signal processing capabilities. The processor 402 may be a general-purpose processor, including a central processing unit (Central Processing Unit, abbreviated as CPU), a network processor (Network Processor, abbreviated as NP), and the like. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. It will be appreciated that the configuration of fig. 4 is merely illustrative and may include more or fewer components than shown in fig. 4 or have a different configuration than shown in fig. 4. The components shown in fig. 4 may be implemented in hardware and/or software.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, the computer program being executed by a processor to implement the technical solution of any of the method embodiments described above.
The various embodiments in this disclosure are described in a progressive manner, and identical and similar parts of the various embodiments are all referred to each other, and each embodiment is mainly described as different from other embodiments.
The scope of the present disclosure is not limited to the above-described embodiments, and it is apparent that various modifications and variations can be made to the present disclosure by those skilled in the art without departing from the scope and spirit of the disclosure. Such modifications and variations are intended to be included herein within the scope of the following claims and their equivalents.
Claims (8)
1. A method for automatically evaluating arterial transit artifacts of magnetic resonance spin labeling imaging, comprising:
acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of an evaluation object;
registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix;
applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all regions of interest;
performing region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial transit artifact regions of interest of the magnetic resonance spin-marker perfusion weighted image;
extracting features of each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest, wherein the image features of each arterial navigation artifact region of interest comprise first-order statistical features of images, gray level co-occurrence matrix features, gray region size matrix features, gray level travel matrix features, neighborhood gray level difference matrix features and neighborhood gray level dependency matrix features;
inputting image features of each arterial navigation artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain an evaluation result of each arterial navigation artifact region of interest of the evaluation object, wherein the region of interest evaluation model adopts a supervised random forest model, the supervised random forest model determines model parameters through a grid search method, and the model parameters comprise the number of decision trees, the maximum feature number and the maximum depth.
2. The method of claim 1, wherein the pre-set arterial navigation artifact-specific region of interest map is generated by level selection in a first level region of a cerebral blood supply map, the cerebral blood supply map having the same field of view and resolution as the cerebral template image.
3. The method according to claim 2, wherein, in the level selection, all levels within a preset range of the level of the nucleus pulposus and the level of the nucleus pulposus in the cerebral blood supply map are selected.
4. The method of claim 1, wherein the spatial transformation matrix satisfies the following expression:
wherein,representing brain template image, < >>Representing proton density weighted images, ">Representing normalized mutual information function,/->Representing the spatial transformation matrix.
5. The method according to any one of claims 1-4, further comprising:
when the evaluation object is scanned a plurality of times, a magnetic resonance spin-marker perfusion weighted image and a proton density weighted image of the evaluation object are acquired based on an average of the plurality of scans.
6. An automatic assessment device for arterial transit artifacts of magnetic resonance spin labeling imaging, comprising:
the acquisition module is used for acquiring a magnetic resonance spin labeling perfusion weighted image and a proton density weighted image of the evaluation object;
the registration module is used for registering the proton density weighted image with a preset brain template image to obtain a space transformation matrix;
the processing module is used for applying the space transformation matrix to a preset region-of-interest map special for arterial navigation artifact to obtain masks of all the regions of interest;
the segmentation module is used for carrying out region-of-interest segmentation on the magnetic resonance spin-marker perfusion weighted image according to the mask to obtain a plurality of arterial navigation artifact regions of interest of the magnetic resonance spin-marker perfusion weighted image;
the extraction module is used for carrying out feature extraction on each arterial navigation artifact region of interest to obtain image features of each arterial navigation artifact region of interest, wherein the image features of each arterial navigation artifact region of interest comprise first-order statistics features, gray level co-occurrence matrix features, gray level region size matrix features, gray level travel matrix features, neighborhood gray level difference matrix features and neighborhood gray level dependency matrix features of images;
the evaluation module is used for inputting the image characteristics of each arterial crossing artifact region of interest into a pre-trained corresponding region of interest evaluation model to obtain the evaluation result of each arterial crossing artifact region of interest of the evaluation object, wherein the region of interest evaluation model adopts a supervised random forest model, the supervised random forest model determines model parameters through a grid search method, and the model parameters comprise the number of decision trees, the maximum feature number and the maximum depth.
7. An electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing computer-executable instructions stored in the memory causes the at least one processor to perform the magnetic resonance spin-marker imaging arterial transit artifact automatic assessment method according to any one of claims 1-5.
8. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are for implementing the magnetic resonance spin-marker imaging arterial traversal artifact automatic assessment method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311753293.6A CN117437321B (en) | 2023-12-20 | 2023-12-20 | Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311753293.6A CN117437321B (en) | 2023-12-20 | 2023-12-20 | Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117437321A CN117437321A (en) | 2024-01-23 |
| CN117437321B true CN117437321B (en) | 2024-03-12 |
Family
ID=89553789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311753293.6A Active CN117437321B (en) | 2023-12-20 | 2023-12-20 | Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117437321B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7096188B1 (en) * | 1998-07-02 | 2006-08-22 | Kepner-Tregoe, Inc. | Method and apparatus for problem solving, decision making and storing, analyzing, and retrieving enterprisewide knowledge and conclusive data |
| CN101322648A (en) * | 2008-07-29 | 2008-12-17 | 四川大学华西医院 | NMR imaging equipment stability and method for measuring image-forming index |
| CN110309502A (en) * | 2018-03-20 | 2019-10-08 | 波音公司 | Predicted query for complication system life cycle management is handled |
| CN110554339A (en) * | 2018-05-31 | 2019-12-10 | 通用电气公司 | method and system for coil selection in magnetic resonance imaging to reduce phase wrap artifacts |
| CN113744223A (en) * | 2021-08-26 | 2021-12-03 | 联影智能医疗科技(北京)有限公司 | Blood vessel risk assessment method, computer device, and storage medium |
| CN114140369A (en) * | 2020-08-13 | 2022-03-04 | 武汉联影智融医疗科技有限公司 | Organ segmentation method, device, computer equipment and storage medium |
| CN114565559A (en) * | 2022-01-18 | 2022-05-31 | 首都医科大学附属北京天坛医院 | Semi-automatic measurement method for morphological parameters of intracranial aneurysm |
| CN115760708A (en) * | 2022-10-27 | 2023-03-07 | 沈阳先进医疗设备技术孵化中心有限公司 | Intracranial collateral circulation automatic evaluation method and device, storage medium and computing equipment |
| CN116205915A (en) * | 2023-04-28 | 2023-06-02 | 北京航空航天大学 | Brain age assessment method and system based on mask and electronic equipment |
-
2023
- 2023-12-20 CN CN202311753293.6A patent/CN117437321B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7096188B1 (en) * | 1998-07-02 | 2006-08-22 | Kepner-Tregoe, Inc. | Method and apparatus for problem solving, decision making and storing, analyzing, and retrieving enterprisewide knowledge and conclusive data |
| CN101322648A (en) * | 2008-07-29 | 2008-12-17 | 四川大学华西医院 | NMR imaging equipment stability and method for measuring image-forming index |
| CN110309502A (en) * | 2018-03-20 | 2019-10-08 | 波音公司 | Predicted query for complication system life cycle management is handled |
| CN110554339A (en) * | 2018-05-31 | 2019-12-10 | 通用电气公司 | method and system for coil selection in magnetic resonance imaging to reduce phase wrap artifacts |
| CN114140369A (en) * | 2020-08-13 | 2022-03-04 | 武汉联影智融医疗科技有限公司 | Organ segmentation method, device, computer equipment and storage medium |
| CN113744223A (en) * | 2021-08-26 | 2021-12-03 | 联影智能医疗科技(北京)有限公司 | Blood vessel risk assessment method, computer device, and storage medium |
| CN114565559A (en) * | 2022-01-18 | 2022-05-31 | 首都医科大学附属北京天坛医院 | Semi-automatic measurement method for morphological parameters of intracranial aneurysm |
| CN115760708A (en) * | 2022-10-27 | 2023-03-07 | 沈阳先进医疗设备技术孵化中心有限公司 | Intracranial collateral circulation automatic evaluation method and device, storage medium and computing equipment |
| CN116205915A (en) * | 2023-04-28 | 2023-06-02 | 北京航空航天大学 | Brain age assessment method and system based on mask and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| The utility of arterial spin labelled perfusion-weighted magnetic resonance imaging in measuring the vascularity of high grade gliomas – A prospective study;Gurkirat Chatha .etc;《Elsevier Science》;20230731;第1-9页 * |
| 基于体表光电容积视频信息的无创动脉硬化测量方法研究;赵鹏栋;《万方数据论文库》;20200901;第1-80页 * |
| 影像组学在评估小肝癌与不典型增生结节的价值研究;相悦;《万方数据学位论文库》;20211105;第1-45页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117437321A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Development of a quantitative intracranial vascular features extraction tool on 3 D MRA using semiautomated open‐curve active contour vessel tracing | |
| US9036878B2 (en) | Method for delineation of tissue lesions | |
| EP2374092B1 (en) | A method, apparatus, and computer program product for acquiring medical image data | |
| USRE43225E1 (en) | Method and apparatus for enhancing an image using data optimization and segmentation | |
| US20110245650A1 (en) | Method and System for Plaque Lesion Characterization | |
| US20110158491A1 (en) | Method and system for lesion segmentation | |
| Manniesing et al. | Robust CTA lumen segmentation of the atherosclerotic carotid artery bifurcation in a large patient population | |
| Worth et al. | Precise segmentation of the lateral ventricles and caudate nucleus in MR brain images using anatomically driven histograms | |
| CN110415234A (en) | Brain tumor dividing method based on multi-parameter magnetic resonance imaging | |
| Deshpande et al. | Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature | |
| CN110956634A (en) | Deep learning-based automatic detection method and system for cerebral microhemorrhage | |
| Dong et al. | Identifying carotid plaque composition in MRI with convolutional neural networks | |
| CN117437321B (en) | Automatic evaluation method and device for arterial transit artifact through magnetic resonance spin labeling imaging | |
| CN113113100A (en) | Method and device for making medical image examination report | |
| Cárdenes et al. | Saturn: a software application of tensor utilities for research in neuroimaging | |
| Rushmore et al. | Anatomically curated segmentation of human subcortical structures in high resolution magnetic resonance imaging: An open science approach | |
| Xu et al. | The challenge of cerebral magnetic resonance imaging in neonates: A new method using mathematical morphology for the segmentation of structures including diffuse excessive high signal intensities. | |
| CN114334128A (en) | Tumor evolution process analysis method, system and storage medium based on CT image | |
| JP6432910B2 (en) | Medical image processing apparatus, ultrasonic diagnostic apparatus, and medical image processing method | |
| CN112862731A (en) | Full-automatic blood vessel extraction method of TOF image | |
| Klein et al. | On the Reliability of Diffusion Neuroimaging | |
| US20220398735A1 (en) | Method and system for automated processing, registration, segmentation, analysis, validation, and visualization of structured and unstructured data | |
| M’hiri et al. | Automatic evaluation of vessel diameter variation from 2D X-ray angiography | |
| US20240112786A1 (en) | Image processing apparatus, image processing method, and image processing program | |
| CN116563284B (en) | System for quantitatively describing brain glioma characteristic boundary change evaluation index in MRI |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |