CN106897993B - Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map - Google Patents
Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map Download PDFInfo
- Publication number
- CN106897993B CN106897993B CN201710020265.1A CN201710020265A CN106897993B CN 106897993 B CN106897993 B CN 106897993B CN 201710020265 A CN201710020265 A CN 201710020265A CN 106897993 B CN106897993 B CN 106897993B
- Authority
- CN
- China
- Prior art keywords
- map
- subject
- space
- magnetic susceptibility
- probability map
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- 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
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a kind of construction methods based on quantitative susceptibility imaging human brain gray matter core group probability map, comprising the following steps: acquires data using MR imaging apparatus;By the quantitative magnetic susceptibility image registration of subject into normed space, that is, space MNI;Brain deep layer kankar group region is sketched out on the magnetic susceptibility figure of normed space after registration by hand, and makes different probability map according to different overlap proportion;In the magnetic susceptibility image for evaluation, automatic segmentation result and the measurement of goldstandard the progress similarity and coverage value delineated by hand to different probability map, the final probability map of the map construction of overlap proportion when similarity being taken to reach peak value.The automatic segmentation that the probability map that the present invention constructs rolls into a ball brain deep layer kankar can be to avoid the artificial difference for delineating introducing by hand, and core group segmentation result accuracy is higher, is better than existing AAL and JH map;And the method than delineating by hand saves the time, improves the efficiency of image analysis work.
Description
Technical field
The invention belongs to mr imaging technique fields, are based especially on the human brain deep layer kankar of quantitative susceptibility imaging
The construction method of the probability map of group.
Background technique
3 D stereo brain map can be analyzed for brain imaging data and provide useful anatomical reference, and subject and brain template are passed through
Between autoregistration, brain map can effectively will subject brain be divided into corresponding region of interest.The structure and function of human brain is multiple
There are its specificity in miscellaneous multiplicity, every part.Spatial normalization can reduce the difference of brain anatomy between individual, therefore it is
An important step in human brain atlas research.Currently, the big brain map that MR investigation is widely used is derived from t1 weighted image,
Such as Talairach and Tournoux map, automatic anatomical landmarks (AAL) map based on Colin27 template.
With the development of High field strenghth MRI technology, quantitative susceptibility imaging provides a kind of novel contrast mechanism,
It obtains local magnetic field variation characteristic using the phase information that general mr imaging technique is given up, then passes through complicated field to source
Inversion Calculation can directly obtain quantitative magnetic susceptibility distribution map.The contrast mechanism of brain magnetic susceptibility image is mainly derived from iron-containing
Deep kankar group and the white matter containing myelin, its contrast is very good for deep nuclei.Johns is come from recently
The research team of Hopkins university has made the big brain map (JH map) based on quantitative magnetic susceptibility figure, but its map
It is the brain based on single-subject, cannot sufficiently reflects the diversity of the anatomical structure of a large amount of Normal brains.
Summary of the invention
It is fixed that the one kind proposed the purpose of the present invention is to solve automatic segmentation brain deep layer kankar clique problem is based on
Amount susceptibility imaging technology creates a kind of construction method of automatic segmentation measurement map of deep layer kankar group, and this method uses one group
The high-resolution of subject quantifies magnetic susceptibility image creation one new probability brain deep layer kankar group segmentation map, the map
It can be used as a useful template to carry out the identification of brain deep layer core group automatically and carry out the group analysis measurement of big data.
The object of the present invention is achieved like this:
A kind of construction method for rolling into a ball probability map based on quantitative susceptibility imaging human brain deep layer kankar, this method include
Step in detail below:
Step 1: recruiting a collection of Healthy subjects, randomly select a portion subject as map and make object, remaining quilt
Study the object that map evaluation is examined for the later period;
Step 2: acquiring data using MR imaging apparatus and data are rebuild to obtain quantitative magnetic susceptibility image;
Step 3: by the quantitative magnetic susceptibility image registration of all subjects into normed space, that is, space MNI;
Step 4: on the magnetic susceptibility figure of the normed space after all maps production object subject registration, sketching out by hand big
Brain deep layer kankar rolls into a ball region, and makes different probability map according to different overlap proportion;
Step 5: in the magnetic susceptibility image for the normed space after map evaluation object subject registration, being studied by two
Person delineates to obtain brain deep layer kankar group region by hand;
Step 6: the different probability map obtained using step 4 to the magnetic susceptibility image being tested for map evaluation object into
The automatic segmentation of row, and marked the core group i.e. gold that obtained core group delineates by hand with two researchers in step 5 is divided automatically
Standard, carries out the measurement of similarity and coverage value, final general of the map construction of overlap proportion when similarity being taken to reach peak value
Rate map.
It is specific to wrap described in step 3 by the quantitative magnetic susceptibility image registration of subject into normed space in method of the invention
Include following steps:
Step a1: subject sagittal plain high-resolution T1 structure picture is redeveloped into cross-section position, and removes scalp, cranium, is extracted
Brain tissue part;
Step a2: scalp, cranium are removed to the mould figure of subject, extract brain tissue part;
Step a3: the T1 structure picture of subject is registrated with the mould figure of subject using linear registration Algorithm, is tested
T1 figure in mould map space;
Step a4: it is used what step a3 was obtained in linear registration Algorithm and normed space by the T1 figure in die trial map space
ICBM T1 figure be registrated, obtain subject T1 structure chart in normed space and turn from by die trial map space to normed space
The matrix changed;
Step a5: the transition matrix obtained using step a4 is transformed to the magnetic susceptibility figure of subject in normed space, is obtained
The magnetic susceptibility image of subject in normed space.
In method of the invention, described in step 6 in the magnetic susceptibility image for evaluation, different probability map is divided automatically
The core group i.e. goldstandard that the core group cut delineates by hand with two researchers, carries out the survey of similarity and coverage value
Amount, using following evaluation parameter:
Kappa coefficient:
Dice coefficient:
Coverage rate:
Wherein, similarity Dice coefficient refers to that the number of pixels of correct segmentation result accounts for entire cut zone (comprising by hand
Segmentation and all areas divided automatically of map) ratio, value model very sensitive to the difference of two area sizes and position
Enclosing indicates completely the same for [0,1], 1.Since TN number of pixels is infinity relative to target core group number of pixels, to make
Kappa coefficient is equal with Dice coefficient, and some studies pointed out that a kind of special cases that Dice coefficient is Kappa coefficient.Covering
Rate refers to the ratio that the number of pixels being correctly partitioned into accounts for manual segmentation result and map segmentation result jointly comprises region.
The probability map that the present invention makes can delineate introducing to the automatic segmentation that brain deep layer kankar is rolled into a ball to avoid manual
Artificial difference, core roll into a ball segmentation result accuracy it is higher, be better than existing AAL map and JH map;In addition, the present invention makes
Probability map than by hand delineate region of interest conventional method save the time, can effectively improve image analysis work effect
Rate.
Detailed description of the invention
Fig. 1 is flow chart of the present invention;
Fig. 2 is the flow chart of present invention building probability map embodiment;
Fig. 3 is present invention evaluation schematic illustration;
Each core group in the Basal ganglia region that Fig. 4 is divided automatically for the different probability map of production of the embodiment of the present invention
Dice coefficient and coverage rate distribution trend curve graph;
Each core group in the basis cranii and cerebellum that Fig. 5 is divided automatically for the different probability map of production of the embodiment of the present invention
Dice coefficient and coverage rate distribution trend curve graph.
Specific embodiment
In conjunction with following specific embodiments and attached drawing, invention is further described in detail.Implement process of the invention, item
Part, experimental program method etc., in addition to what is specifically mentioned below, are among the general principles and common general knowledge in the art, this
There are no special restrictions to content for invention.
The present invention quantifies the construction method that susceptibility imaging human brain deep layer kankar rolls into a ball probability map, based on to brain
On the basis of the extraordinary quantitative magnetic susceptibility figure of deep nuclei contrast, the method for taking optimal probability using more people, production it is general
Forthright map.This method can be improved the efficiency of image analysis work to a certain extent.
The present invention is introduced individually below to the initial data collected by being registrated, delineating, evaluate, and obtains optimum probability
The specific implementation process of map.Wherein, data source is in 3T MR imaging apparatus system (Siemens MAGNETOM Trio a
Tim 3T), quantitative susceptibility imaging scanning sequence is three-dimensional more echo gradient echo (Gradient echo, GRE) sequences, tool
Swept-volume parameter is as follows: the repetition time (TR)=60ms, the first echo time (TE1)=6.8ms, and echo sounding (Δ TE)=
6.8ms, number of echoes=8, flip angle (FA)=15 °, the visual field (FOV)=240 × 180mm2, voxel size=0.625mm ×
0.625mm × 2mm, the number of plies=96.To reduce the sampling time, parallel sampling is used in phase-encoding direction (subject left and right directions)
Technology, accelerated factor 2.T1 weights high resolution structure picture and prepares fast gradient echo using three-dimensional magnetization
(Magnetization-Prepared Rapid Gradient Echo, MPRAGE) sequence, design parameter are as follows: median sagittal
Bit scan, TR=2530ms, reversing time (TI)=1100ms, FA=7 °, TE=2.34ms, FOV=256 × 256mm2, body
Plain size=1mm × 1mm × 1mm, the number of plies=192.
The present embodiment has recruited 15 Healthy subjects (7 women, 8 males, average age 24.3 ± 1.0 years old), at random
Choosing wherein 10 (each 5 of men and women) subjects is used as map to make object, remaining 5 subjects examine map validity as the later period
Object.
By the collected complex data of gradin-echo by phase-fitting, phase unwrapping around, remove ambient field, based on shape
The dipole inversion algorithm (Morphology Enabled Dipole Inversion, MEDI) of state and etc. reconstruct cranium
The cross-section position magnetic susceptibility figure of brain.
The flow chart of map production of the present invention is shown in Fig. 1-2, comprising: arrives the quantitative magnetic susceptibility image registration of subject
In normed space (space MNI), after registration brain deep layer kankar group is sketched out on the magnetic susceptibility figure of normed space by hand
Region, the measurement that similarity and coverage value are carried out to the probability map for the different situations delineated, take similarity to reach peak
The map of overlap proportion when value makes final probability map.Detailed process is as follows:
1) using scanner carry three-dimensional the poster processing soft will be tested sagittal plain high-resolution T1 structure picture be redeveloped into it is cross-section
Bit image (T1 MPRAGE figure), the image resolution ratio after the present embodiment reconstruction are as follows: 1mm × 1mm × 1mm;Then FSL is used
5.0.9 the BET software in kit (Brain Extraction Tool) removes scalp, cranium, extracts brain tissue part.
2) the mould figure (GreRawMag figure) that subject three-dimensional GRE sequence is obtained, also using in FSL 5.0.9 kit
BET software removes scalp, cranium, extracts brain tissue part.
3) using the rigid body translation algorithm in the linear registration Algorithm of FLIRT in FSL 5.0.9 kit by head clearing and
The cross-section bitmap being tested after skull be registrated to after skull by die trial map space, obtain by the T1 in die trial map space
Scheme (Mag T1 figure).
It 4) will be by using 12 parameter affine transform methods in the linear registration Algorithm of FLIRT in FSL 5.0.9 kit
The Mag T1 figure of examination is registrated in the normed space (MNI) of ICBM T1 figure, obtains the T1 being tested in the space MNI figure (MNI T1
Figure) and by die trial map space to the transition matrix in the space MNI.
5) transition matrix is applied on the QSM figure of subject, is transformed in normed space, obtain the quilt of normed space
Try QSM figure (MNI QSM figure).
6) on the normed space QSM figure of the above-mentioned single-subject obtained by pretreatment, You Yiwei researcher is utilized
3.2 software of ITK-SNAP sketch out manually six bilateral deep-brain kankars group ROI (caudate nucleus: CN, shell core: PU, globus pallidus:
GP, black substance: SN, rubrum: RN, dentate nucleus: DN), to obtain each subject in the deep grey matter segmentation figure of MNI coordinate system
(Deep Gray Matter Parcellation Map, DGMPM).
7) DGMPM of all maps production object subject is schemed, by every one kind ROI according to overlap proportion from 10%-
100% incremented by successively 10% mode saves as a probability map respectively, is selected later using corresponding map evaluation method
The map of optimum superposing ratio is as final probability map.
The map evaluation method is specific as follows:
Utilize 3.2 software of ITK-SNAP in the normed space QSM figure of 5 subjects for evaluation by two researchers
Deep nuclei ROI is sketched out manually, in this, as the goldstandard of the evaluation map accuracy of separation.
The quantitatively evaluating of the segmentation result accuracy of each ROI is carried out using principle shown in Fig. 3.Assuming that researcher
It is T that segmentation, which obtains the pixel of target core group, by hand, and probability map of the present invention, AAL map, Johns Hopkins (JH) map obtain
The pixel of the target core group arrived is R, the overlapping region of researcher's target image that segmentation and map are divided automatically by hand
Number of pixels is true positives (TP), and manual segmentation result and inclusion region number of pixels except map automatic segmentation result are true
Negative (TN), not including the number of pixels of manual segmentation area in map automatic segmentation result is false positive (FP), by hand
Number of pixels in segmentation result not comprising map automatic segmentation result region is false negative (FN).Using Kappa coefficient, Dice
Coefficient and coverage rate (Overlap Ratio, OR) analyze segmentation result reliability:
Kappa coefficient:
Dice coefficient:
Coverage rate:
Wherein, similarity Dice coefficient refers to that the number of pixels of correct segmentation result accounts for entire cut zone (comprising by hand
Segmentation and all areas divided automatically of map) ratio, value model very sensitive to the difference of two area sizes and position
Enclosing indicates completely the same for [0,1], 1.Since TN number of pixels is infinity relative to target core group number of pixels, to make
Kappa coefficient is equal with Dice coefficient.Coverage rate refers to that the number of pixels being correctly partitioned into accounts for manual segmentation result and map point
Cut the ratio that result jointly comprises region.
The atlas calculation of the selection optimum superposing ratio is as follows:
In the present embodiment, for 5 subject magnetic susceptibility figures for evaluation and test, respectively not using 10 kinds made of the invention
The probability atlas registration of negative lap rate and the method delineated by hand obtain two groups of ROI, then carry out Dice to this two groups of ROI regions
Coefficient and coverage measure, and the two result is weighed, select the probability map of best overlapped ratio as finally general
Rate map.
In order to guarantee the reliability of optimal map selection, use the method for multiple averaging: firstly, find out each subject by
The Dice coefficient and coverage rate between ROI that the ROI and map that every researcher delineates manually are divided automatically, by two researchers
Obtained numerical value is averaged, and the average value of each subject two researchers in each region evaluation and test is obtained;Secondly, to all subjects
Average Dice coefficient and average coverage rate be averaging again, thus obtain each research core group final Dice coefficient value and cover
Lid rate value.It is every one kind situation map using the method for multiple averaging obtain each research core group final Dice coefficient and
Coverage rate, then analyzes their distribution trend, finally obtains optimal map, refering to shown in attached drawing 4,5.
A and b is to be carried out each probability map for test object with 5 normal subjects and divided automatically and two respectively in Fig. 4
Position researcher is divided the average similarity (Dice coefficient) between the kankar group of all area-of-interests of Basal ganglia by hand and is covered
The comparison result of lid rate, each core group respectively indicates in figure are as follows: caudate nucleus (CN), shell core (PU), globus pallidus (GP), left (L), right
(R), it is seen that the probability map overlapping percentages Dice coefficient that all cores are rolled into a ball when taking 50% reaches maximum value, and coverage rate reaches at this time
70% or more, it contains core and rolls into a ball most of region, therefore the map that Basal ganglia part finally takes overlapping percentages when being 50%
Make final probability map.
The same with Fig. 4, a and b is the kankar of the area-of-interest in the basis cranii and cerebellum to 5 test objects in Fig. 5
Group is assessed, and each core group respectively indicates in figure are as follows: black substance (SN), rubrum (RN), dentate nucleus (DN), left (L), right (R), it is seen that
Equally at 50%, the Dice coefficient of all core groups reaches maximum value to probability map overlapping percentages, and coverage rate reaches 60% at this time
More than, it contains core and rolls into a ball most of region, therefore the map when core group in basis cranii and cerebellum is also 50% with overlapping percentages
Make final probability map.
Protection content of the invention is not limited to above embodiments.Without departing from the spirit and scope of the invention, originally
Field technical staff it is conceivable that variation and advantage be all included in the present invention, and with appended claims be protect
Protect range.
Claims (2)
1. a kind of construction method based on quantitative susceptibility imaging human brain gray matter core group probability map, which is characterized in that the side
Method the following steps are included:
Step 1: a collection of Healthy subjects are recruited, part of subject is randomly selected as map and makes object, remaining subject conduct
Later period examines the object of map evaluation;
Step 2: acquiring data using MR imaging apparatus and data are rebuild to obtain quantitative magnetic susceptibility image;
Step 3: by the quantitative magnetic susceptibility image registration of all subjects into normed space, that is, space MNI;
Step 4: on the magnetic susceptibility figure of the normed space after all maps production object subject registration, sketching out brain depth by hand
Layer kankar rolls into a ball region, and makes different probability map according to different overlap proportion;
Step 5: in the magnetic susceptibility image for the normed space after map evaluation object subject registration, You Liangwei researcher's hand
Work delineates to obtain brain deep layer kankar group region;
Step 6: the different probability map obtained using step 4 carries out certainly the magnetic susceptibility image being tested for map evaluation object
Dynamic segmentation, and obtained core group and the core that two researchers in step 5 delineate by hand will be divided automatically and roll into a ball i.e. goldstandard, into
The measurement of row similarity and coverage value, probability graph described in the map construction of overlap proportion when similarity being taken to reach peak value
Spectrum.
2. construction method according to claim 1, which is characterized in that by the quantitative magnetic susceptibility image of subject described in step 3
It is registrated in normed space, comprising the following specific steps
Step a1: subject sagittal plain high-resolution T1 structure picture is redeveloped into cross-section position, and removes scalp and cranium, extracts brain group
Knit part;
Step a2: scalp and cranium are removed to the mould figure of subject, extract brain tissue part;
Step a3: the T1 structure picture of subject is registrated with the mould figure of subject using linear registration Algorithm, is obtained by die trial figure
T1 figure in space;
Step a4: it is used what step a3 was obtained in linear registration Algorithm and normed space by the T1 figure in die trial map space
ICBM T1 figure is registrated, and is obtained the subject T1 structure chart in normed space and is converted from by die trial map space to normed space
A matrix;
Step a5: the transition matrix obtained using step a4 is transformed to the magnetic susceptibility figure of subject in normed space, obtains standard
The magnetic susceptibility image of subject in space.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710020265.1A CN106897993B (en) | 2017-01-12 | 2017-01-12 | Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710020265.1A CN106897993B (en) | 2017-01-12 | 2017-01-12 | Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106897993A CN106897993A (en) | 2017-06-27 |
CN106897993B true CN106897993B (en) | 2019-07-26 |
Family
ID=59199173
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710020265.1A Active CN106897993B (en) | 2017-01-12 | 2017-01-12 | Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106897993B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10896508B2 (en) | 2018-02-07 | 2021-01-19 | International Business Machines Corporation | System for segmentation of anatomical structures in cardiac CTA using fully convolutional neural networks |
CN109034136B (en) * | 2018-09-06 | 2021-07-20 | 湖北亿咖通科技有限公司 | Image processing method, image processing apparatus, image capturing device, and storage medium |
CN109272514B (en) * | 2018-10-05 | 2021-07-13 | 数坤(北京)网络科技股份有限公司 | Sample evaluation method and model training method of coronary artery segmentation model |
CN110458869B (en) * | 2019-05-10 | 2021-10-19 | 珠海慧脑云计算有限公司 | Registration method and system for brain image of magnetic resonance structure of newborn |
CN111127526B (en) * | 2019-11-27 | 2023-03-31 | 华东师范大学 | Method for positioning deep nuclei of brain by using quantitative susceptibility map |
CN111481827B (en) * | 2020-04-17 | 2023-10-20 | 上海深透科技有限公司 | Quantitative susceptibility imaging and method for locating target area of potential stimulation of DBS |
CN111445520B (en) * | 2020-05-26 | 2021-09-24 | 河南省人民医院 | Thalamus abdominal intermediate nucleus positioning method and positioning device based on magnetic resonance quantitative magnetic sensitive image |
CN111681230A (en) * | 2020-06-10 | 2020-09-18 | 华中科技大学同济医学院附属同济医院 | System and method for scoring high-signal of white matter of brain |
CN113066113B (en) * | 2021-04-27 | 2022-01-11 | 河北医科大学第二医院 | Method and equipment for constructing spontaneous hypertensive rat brain template and map set |
CN113592847B (en) * | 2021-08-10 | 2023-10-10 | 浙江大学 | Deep learning-based QSM brain deep nucleolus automatic segmentation method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101887583A (en) * | 2010-06-24 | 2010-11-17 | 东软集团股份有限公司 | Method and device for extracting brain tissue image |
CN103442765A (en) * | 2011-03-29 | 2013-12-11 | 瓦尔克公司 | Device and method for altering neurotransmitter level in brain |
CN103826536A (en) * | 2011-09-26 | 2014-05-28 | 大日本印刷株式会社 | Medical image processing device, medical image processing method, program |
CN104523275A (en) * | 2014-12-25 | 2015-04-22 | 西安电子科技大学 | Construction method for health people white matter fiber tract atlas |
CN104644173A (en) * | 2015-01-14 | 2015-05-27 | 北京工业大学 | Depression risk three-grade early warning method and depression risk three-grade early warning system |
CN104921741A (en) * | 2014-03-19 | 2015-09-23 | 柯尼卡美能达株式会社 | Image analysis device, imaging system, and image analysis method |
CN105816192A (en) * | 2016-03-03 | 2016-08-03 | 王雪原 | Method for three-dimensional registration and brain tissue extraction of individual human brain multimodality medical images |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9542763B2 (en) * | 2014-04-25 | 2017-01-10 | The General Hospital Corporation | Systems and methods for fast reconstruction for quantitative susceptibility mapping using magnetic resonance imaging |
US20160054410A1 (en) * | 2014-08-19 | 2016-02-25 | General Electric Company | System and method for locating and quantifying a biomarker for neurological disease |
-
2017
- 2017-01-12 CN CN201710020265.1A patent/CN106897993B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101887583A (en) * | 2010-06-24 | 2010-11-17 | 东软集团股份有限公司 | Method and device for extracting brain tissue image |
CN103442765A (en) * | 2011-03-29 | 2013-12-11 | 瓦尔克公司 | Device and method for altering neurotransmitter level in brain |
CN103826536A (en) * | 2011-09-26 | 2014-05-28 | 大日本印刷株式会社 | Medical image processing device, medical image processing method, program |
CN104921741A (en) * | 2014-03-19 | 2015-09-23 | 柯尼卡美能达株式会社 | Image analysis device, imaging system, and image analysis method |
CN104523275A (en) * | 2014-12-25 | 2015-04-22 | 西安电子科技大学 | Construction method for health people white matter fiber tract atlas |
CN104644173A (en) * | 2015-01-14 | 2015-05-27 | 北京工业大学 | Depression risk three-grade early warning method and depression risk three-grade early warning system |
CN105816192A (en) * | 2016-03-03 | 2016-08-03 | 王雪原 | Method for three-dimensional registration and brain tissue extraction of individual human brain multimodality medical images |
Non-Patent Citations (1)
Title |
---|
Human brain atlas for automated region of interest selection in quantitative susceptibility mapping:Application to determine iron content in deep gray matter structures;Issel Anne L.Lim等;《NeuroImage》;20131115;第82卷(第22期);第449-469页 |
Also Published As
Publication number | Publication date |
---|---|
CN106897993A (en) | 2017-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106897993B (en) | Construction method based on quantitative susceptibility imaging human brain gray matter core group probability map | |
Heiervang et al. | Between session reproducibility and between subject variability of diffusion MR and tractography measures | |
Renvall et al. | Automatic cortical surface reconstruction of high-resolution T1 echo planar imaging data | |
Gao et al. | A universal intensity standardization method based on a many-to-one weak-paired cycle generative adversarial network for magnetic resonance images | |
Parker et al. | Probabilistic Monte Carlo based mapping of cerebral connections utilising whole-brain crossing fibre information | |
Pannek et al. | The average pathlength map: a diffusion MRI tractography-derived index for studying brain pathology | |
Gao et al. | Validation of DTI tractography-based measures of primary motor area connectivity in the squirrel monkey brain | |
Kawahara et al. | T1-weighted and T2-weighted MRI image synthesis with convolutional generative adversarial networks | |
Yang et al. | Computer-aided detection of metastatic brain tumors using magnetic resonance black-blood imaging | |
Feng et al. | MoDL-QSM: Model-based deep learning for quantitative susceptibility mapping | |
US20100226552A1 (en) | Identification and visualization of regions of interest in medical imaging | |
CN104523275A (en) | Construction method for health people white matter fiber tract atlas | |
Voineskos et al. | Quantitative examination of a novel clustering method using magnetic resonance diffusion tensor tractography | |
CN106898000A (en) | A kind of automatic division method of magnetic resonance imaging cerebral gray matter core group | |
CN109242866A (en) | The automatic assisted detection system of tumor of breast based on diffusion magnetic resonance image | |
Campbell et al. | Validation and regularization in diffusion MRI tractography | |
CN106023236B (en) | Cerebral magnetic resonance image partition method based on truncation unlimited Student ' the s t mixed model of Dirichlet process | |
Kim et al. | NEOCIVET: Extraction of cortical surface and analysis of neonatal gyrification using a modified CIVET pipeline | |
German et al. | Brain tissues have single-voxel signatures in multi-spectral MRI | |
Patel et al. | Scalar connectivity measures from fast-marching tractography reveal heritability of white matter architecture | |
Chen et al. | Preserving-texture generative adversarial networks for fast multi-weighted MRI | |
CN111557663B (en) | Human brain magnetic susceptibility tensor imaging method based on cross modality | |
Li et al. | Stability of MRI radiomic features of the hippocampus: An integrated analysis of test-retest variability | |
Haroon et al. | Probabilistic quantification of regional cortical microstructural complexity | |
Zhang et al. | A framework of automatic brain tumor segmentation method based on information fusion of structural and functional MRI signals |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |