CN109242816A - Based on tranquillization state brain function to the glioma pathology rank iconography auxiliary judgement method of side positioning - Google Patents
Based on tranquillization state brain function to the glioma pathology rank iconography auxiliary judgement method of side positioning Download PDFInfo
- Publication number
- CN109242816A CN109242816A CN201710551743.1A CN201710551743A CN109242816A CN 109242816 A CN109242816 A CN 109242816A CN 201710551743 A CN201710551743 A CN 201710551743A CN 109242816 A CN109242816 A CN 109242816A
- Authority
- CN
- China
- Prior art keywords
- brain
- tranquillization state
- area
- glioma
- iconography
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
-
- 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
- G06T2207/30096—Tumor; Lesion
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 belongs to Medical Image Processing and application fields, it is related to the tranquillization state magnetic resonance imaging auxiliary judgement method of non-intrusion type, the tranquillization state magnetic resonance imaging auxiliary judgement method of non-intrusion type is carried out more particularly to a kind of pair of glioma WHO Pathological degree, the method of the present invention, pass through tranquillization state functional image and high-precision structure image, carry out synkinesia functional areas to side positioning, and pass through Logistic model, determine glioma pathology rank, as the result is shown, it is able to achieve the high-precision noninvasive glioma pathology grading based on iconography, this method is particularly suitable for brain language, motor area patients with gliomas, it can be used for instructing therapeutic intervention Scheme Choice etc..
Description
Technical field
The invention belongs to Medical Image Processing and application field, the tranquillization state magnetic resonance imaging auxiliary for being related to non-intrusion type is sentenced
Determine method, and in particular to a kind of pair of glioma WHO Pathological degree carries out the tranquillization state magnetic resonance imaging auxiliary of non-intrusion type
Determination method realizes that the height of high accuracy is rudimentary to the brain domain characteristic that side positioning marks especially with tranquillization state brain function
The method that the iconography of other tumour non-intrusion type determines.
Background technique
It is reported that glioma is common central nerve tumor, there is high incidence, high lethality rate, high relapse rate.Face
Bed practice display, the reasonable determination etc. determined for clinical diagnosis, therapeutic intervention scheme to glioma (WHO) Pathological degree
It is most important;According to the newest standard of the World Health Organization, glioma is divided into low level (I grades and II grades) and high-level
(III level and IV grades).The goldstandard about tumour rank is still biopsy and histopathological evaluation at present.But
The local sampling analysis that living tissue detection equally faces lot of challenges, especially tumour may cause high-level tumour and be misdiagnosed as
Low level tumour, and cause to intracranial hemorrhage, meanwhile, the tissue biopsy ten of brain tumor different from the tumour at other positions
Divide difficulty;The a variety of non-intrusion type means different from biopsy are also used for the assessment of malignancy.In recent years, total according to magnetic
The neuroimaging techniques such as vibration morphology, the metabolic index etc. that show, can play certain indicative function, accuracy mainly according to
By the experience accumulation and professional knowledge of read tablet doctor, lacks the standardized index that can quantify, is unfavorable for evaluation,
It is unfavorable for standardized and popularized application.Before this, the imaging evaluation of malignancy be based primarily upon tumor tissues have be different from
The metabolic characteristics of normal tissue is assessed using imaging techniques such as Magnetic Resonance Spectrums (MRS).Sensibility at present
(sensitivity) and specific (specificity) highest method is the Cho (Choline, choline) for calculating tumor region
With the ratio of NAA (N-acetyl-aspartate, N- Acetyl Aspartate), 0.80 sensibility and 0.76 can achieve
Specificity.Using tranquillization state mr techniques, there is research to use the signal intensity of tumor region tranquillization state signal
The indexs such as correlation (SIC) carry out the judgement of high low level to tumour, high-level to 17 low level brain colloids at 18
Realized on tumor sample 89% accuracy rate (sensibility 0.82, specificity 0.96).But these Histopathologic Grade of Cerebral Gliomas results are equal
It has no that independent data is verified, and needs to draw tumor region on nuclear magnetic resonance image manually, be easy to be done by human factor
It disturbs.In fact, tumour to brain function framework, i.e., the influence of the function connects mode of each brain area obtains in many documents
Arrived report, including caused functional compensation, functional network reconstruct etc., study group of the invention proposes a kind of " based on tranquillization early period
The cerebral function area opposite side localization method of state functional MRI " (number of patent application 201710377307.7), with supplementary motor area
To position target, the supplementary motor area of the tranquillization state function connects Pattern localization Ipsilateral from Ipsilateral to strong side.Currently, there is no use
The method that tranquillization state function connects network evaluates glioma height classification.
In order to overcome basis of the existing technology difficult and based on the prior art, present inventor is quasi- to propose one
Kind is based on tranquillization state brain function to the glioma pathology rank iconography auxiliary judgement method of side positioning.This method is non-intruding
Formula, noninvasive, only need measured's minimum level fitness, objective quantification appraisal procedure, high Low grade glioma determines
Precision is suitable for popularization and application up to 90% or more in the hospital for having MR imaging apparatus.
Summary of the invention
The purpose of the present invention is to overcome defect existing in the prior art, the tranquillization state magnetic for providing a kind of non-intrusion type is total
Vibration iconography auxiliary judgement method, and in particular to a kind of pair of glioma WHO Pathological degree carries out the tranquillization state magnetic of non-intrusion type
Resonate iconography auxiliary judgement method, and this method is able to achieve the brain domain characteristic that side positioning marks using tranquillization state brain function
The iconography of the high low level tumour non-intrusion type of high accuracy determines.
Glioma pathology of the brain domain of method of the invention based on tranquillization state functional MRI data to side positioning
Rank evaluation, is able to achieve the high-precision noninvasive glioma pathology grading based on iconography, and this method is particularly suitable for brain
Language, motor area patients with gliomas.
In order to achieve the above purpose, it is of the invention based on tranquillization state brain function to the glioma pathology rank of side positioning
Iconography auxiliary judgement method includes:
Firstly, utilizing " the cerebral function area opposite side localization method based on tranquillization state functional MRI " (number of patent application
201710377307.7) method, functional localization is carried out to the supplementary motor area of the Ipsilateral of Patients with gliomas;Then, it utilizes
The size (that is, number of the included voxel in localization region) of the supplementary motor area of positioning constructs Logistic model, the model with
The supplementary motor area size oriented is input, high-level tumour is considered as positive case, low level tumour is considered as negative case;
The model is applied to patient data, that is, can determine that the case rank for the tumour that it is suffered from.
In the present invention, using biopsy case as goldstandard, (20 low levels are to 31 height in training set for the logistic model
Rank, leave one cross validation Evaluation model accuracy rate) and test set (7 low levels are high-level to 6, direct application training
The model parameter obtained on collection) on reached 90% or more determination rate of accuracy.
Specifically, of the invention sentenced based on glioma pathology rank iconography auxiliary of the tranquillization state brain function to side positioning
Determine method, which is characterized in that itself comprising steps of
1) the tranquillization state functional image for the brain domain patients with gliomas that will acquire and high-precision structure image carry out pre-
Processing, comprising: scanning slice time adjustment, the dynamic correction of head are mapped to standardised space, remove trend term, bandpass filtering and
Scrubbing;While registration, it is removed for standardized influence by tumour MASK, tumor imaging will be not affected by
Healthy side brain is mapped to normed space;
2) the cerebral function area opposite side localization method based on tranquillization state functional MRI is utilized, to the trouble of Patients with gliomas
The supplementary motor area of side carries out functional localization;
3) size of the supplementary motor area obtained using positioning, that is, the number of the included voxel in localization region constructs
The output of Logistic model, Logistic model is higher than the threshold value, is judged as high-level;Otherwise, it is considered as low level.
In step 2) of the present invention, for thering is the supplementary motor area of significant relation to position with tumour rank.
In the present invention, the cerebral function area opposite side localization method based on tranquillization state functional MRI, use as
Lower technical solution:
The division of function sub-district is carried out to brain area using the tranquillization state function connects of full brain, later for each function
Area, Training Support Vector Machines (SVM, support vector machine) classifier, by establishing it to each function sub-district
Specific half brain tranquillization state function connects of opposite side, and the training classifier in Healthy People big data, it is final to realize to each function
The positioning of sub-district;Comprising steps of
1. obtaining brain domain patients with gliomas 5 minutes tranquillization state functional images using tranquillization state functional MRI technology
And high-precision structure image, multinomial standardized pretreatment: scanning slice time adjustment is taken, the dynamic correction of head is mapped to standard
Change space, removes trend term, bandpass filtering and Scrubbing;Later to the brain data pre-processed according to Montreal mind
Through research establishment propose AAL (automated anatomical labelling) template, be to brain Preliminary division
45 brain areas (each 45 of bilateral symmetry);
2. the division of function sub-district is carried out to each brain area using the tranquillization state function connects of full brain voxel level, in full brain
Function zoning obtains 218 function sub-districts;In embodiment, to each brain area, the quiet of all voxels of this brain area is calculated
State signal is ceased, the related coefficient of itself and the remaining 88 brain area average signals of full brain is calculated separately later, is obtaining related coefficient square
After battle array, chooses suitable λ opt and 0-1ization is carried out to matrix:
Classified later using LM algorithm (a minimum network linking algorithm based on local property), to obtain
The sub-zone dividing of each brain area;The λ opt wherein chosen is obtained by 50 grouping crosschecks, especially by meter
Calculate normalised mutual information
To make NMI (X, Y) maximum λ, division result the most stable is obtained, so that the body in each sub-regions
It is known as almost the same tranquillization state function chain feature;
3. being directed to each function sub-district, Training Support Vector Machines (SVM, support vector machine) classifier;
In embodiment, for each brain subregion, all voxels within the scope of this region and its surrounding 6mm are focused on, are instructed
Voxel inside objective function area is labeled as 1 by the output of experienced classifier, and the voxel on objective function area periphery is labeled as
0, then, the input feature vector of the classifier is the tranquillization state brain function connection mode of half brain of opposite side, is defined as follows: judging certain
Whether a voxel belongs to specified functional areas, needs to calculate the half brain tranquillization state function connects of specific opposite side of the voxel, these are special
Anisotropic function connects are connected by comparing the tranquillization state brain function of voxel to all voxels of half brain of opposite side inside and outside given functional areas
It connects and provides: wherein calculating separately the average signal of the inside and outside two groups of voxels in functional areas, while being connected to opposite side half brain computing function
Intensity carries out comparison among groups t- inspection and identifies the brain area cluster with significant group difference after multiple alignment corrects,
Find the input feature vector that the inside and outside opposite side brain function with significant difference in these functional areas is connected to classifier;By to each
Function sub-district establishes its half brain tranquillization state function connects of specific opposite side, and the training classifier in Healthy People big data, finally
Realize the positioning to each function sub-district;
4. each function sub-district positioning result of AAL template is merged, the functional localization map to 45 brain areas is obtained.
More specifically, the cerebral function area opposite side localization method based on tranquillization state functional MRI comprising step
It is rapid:
4) complete 218 sub-district map of brain is established using tranquillization state data by the big data sample of Healthy People;
5) svm classifier is respectively trained for each sub-district in 218 sub-district maps by the big data sample of Healthy People
Device;
6) the tranquillization state functional image for the brain domain patients with gliomas that will acquire and high-precision structure image carry out pre-
Processing, comprising: scanning slice time adjustment, the dynamic correction of head are mapped to standardised space, remove trend term, bandpass filtering and
Scrubbing;While registration, it is removed for standardized influence by tumour MASK, tumor imaging will be not affected by
Healthy side brain is mapped to normed space;
7) for each voxel of Ipsilateral target area, it is related to the multiple characteristic area signals in opposite side to calculate separately it
Coefficient, in this, as the input of support vector machines (SVM) classifier, whether output then belongs to for each voxel of target area
This brain sub-district;
8) it finally, by the result split of all positioning, maps back individual space and is formed to entire Ipsilateral cerebral function area
Positioning result.
In the step 1), while the function connects of the voxel in computing function area Yu full brain remaining 88 brain area, it obtains
Connection matrix M carries out binaryzation to it and classifies after calculating its similar matrix N, is obtained by maximizing mutual information
One stable division result;
When wherein, to similar matrix N binaryzation, cross-checked using 50 groupings, by normalized mutual information,
It obtains so that NMI (X, Y) maximum λ, carries out binaryzation to similar matrix N with this:
In step 1), obtained 218 sub-district map of full brain;
In the step 2), it is defined target area: to each brain area, being with the brain area position of AAL Template Location
Center, the regions of 2 voxels (i.e. 6mm) is expanded using this as target area outward, by functional areas from wherein marking off;
In step 2), calculated on training set each brain subregion and surrounding voxel to half brain of opposite side every individual
The function connects of element carry out comparison among groups t- inspection and identify the brain area with significant group difference after multiple alignment corrects
cluster;
In step 2), connected again with the voxel computing function of target area with the average signal of voxel in the cluster that finds
It connects as feature, for each sub-district one support vector machines (SVM) classifier of training.
In the step 3), by T2 image, tumor section is drawn manually on each tomographic image, and in registration
In the process, the weight of this part of standards is all set as 0, removes tumour for standardized influence;
In the step 4), for each voxel of Ipsilateral target area, itself and the multiple characteristic areas in opposite side are calculated separately
The related coefficient of domain signal, in this, as the input of support vector machines (SVM) classifier, output is then each of target area
Whether voxel belongs to some specific brain domain;
In the step 5), the functional localization result on normed space is mapped back into individual space, by 45 functions
The positioning one by one of brain area draws volume infarct cerebral map in half brain of Ipsilateral.
For the present invention by tranquillization state functional image and high-precision structure image, the opposite side for carrying out synkinesia functional areas is fixed
Position, and by Logistic model, determines glioma pathology rank, the results show that being able to achieve high-precision noninvasive be based on
The glioma pathology of iconography is graded, and this method is particularly suitable for brain language, motor area patients with gliomas, can be used for referring to
Training treats Scheme Choice etc..
The beneficial effects of the present invention are:
1. this method evaluates glioma pathology rank by noninvasive test.
2. this method has 90% or more glioma pathology rank evaluating precision, 95% spy has been reached on training set
Different degree and 87% susceptibility.
3. this method has reached 83% specificity and 100% susceptibility on independent test collection.
Specific embodiment
Embodiment 1
Using tranquillization state functional MRI technology obtain brain domain patients with gliomas 5 minutes tranquillization state functional image and
High-precision structure image, takes multinomial pretreatment: scanning slice time adjustment, and the dynamic correction of head is mapped to standardised space, goes
Gesture item, bandpass filtering and Scrubbing.While registration, it is removed for standardized influence by tumour MASK, is incited somebody to action
The healthy side brain (strong side) that patient is not affected by tumor imaging is mapped to normed space;
Then, using " the supplementary motor area functional localization method based on tranquillization state " to the supplementary motor area of Ipsilateral
Carry out kinetic energy positioning;Then, will the obtained synkinesia functional areas size of positioning as input, bring into it is of the invention establish be used for
The Logistic model of tumor cases circle evaluation, the case rank for estimating the tumour is high level probability.
Due to different machines or sweep parameter, it is understood that there may be systematic bias, therefore on certain magnetic resonance scanner
When using the model, the data of a certain amount of case grading goldstandard with tissue biopsy are needed as training, set threshold
Value;The output of Logistic model is higher than the threshold value, is judged as high-level;Otherwise, it is considered as low level.
By tranquillization state functional image and high-precision structure image in the embodiment of the present invention, synkinesia function is carried out
Area to side positioning, and by Logistic model, determine that the case rank of tumour, high Low grade glioma judgement precision reach
90% or more, it can be used for instructing therapeutic intervention Scheme Choice etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to restrict the invention, all in essence of the invention
Any modifications, equivalent replacements, and improvements etc. done within mind and principle, should all be included in the protection scope of the present invention.
Claims (3)
1. based on tranquillization state brain function to the glioma pathology rank iconography auxiliary judgement method of side positioning, feature includes
Following step:
1) the tranquillization state functional image for the brain domain patients with gliomas that will acquire and high-precision structure image, are located in advance
Reason, comprising: scanning slice time adjustment, the dynamic correction of head are mapped to standardised space, remove trend term, bandpass filtering and
Scrubbing;While registration, it is removed for standardized influence by tumour MASK, tumor imaging will be not affected by
Healthy side brain is mapped to normed space.
2) the cerebral function area opposite side localization method based on tranquillization state functional MRI is utilized, to the Ipsilateral of Patients with gliomas
Supplementary motor area carries out functional localization.
3) using orient come supplementary motor area size (that is, number of the included voxel in localization region) construct Logistic
Model.The output of Logistic model is higher than the threshold value, is judged as high-level;Otherwise, it is considered as low level.
2. according to claim 1 sentenced based on glioma pathology rank iconography auxiliary of the tranquillization state brain function to side positioning
Determine method, which is characterized in that in step 2), for thering is the supplementary motor area of significant relation to position with tumour rank.
3. according to claim 1 sentenced based on glioma pathology rank iconography auxiliary of the tranquillization state brain function to side positioning
Determine method, which is characterized in that based on the cerebral function area opposite side localization method of tranquillization state functional MRI described in step 2)
Comprising steps of
1) complete 218 sub-district map of brain is established using tranquillization state data by the big data sample of Healthy People;
2) SVM classifier is respectively trained for each sub-district in 218 sub-district maps by the big data sample of Healthy People;
3) the tranquillization state functional image for the brain domain patients with gliomas that will acquire and high-precision structure image, are located in advance
Reason, comprising: scanning slice time adjustment, the dynamic correction of head are mapped to standardised space, remove trend term, bandpass filtering and
Scrubbing;While registration, it is removed for standardized influence by tumour MASK, tumor imaging will be not affected by
Healthy side brain is mapped to normed space;
4) for each voxel of Ipsilateral target area, the phase relation of itself and the multiple characteristic area signals in opposite side is calculated separately
Number, in this, as the input of support vector machines (SVM) classifier, whether output then belongs to this for each voxel of target area
A brain sub-district;
5) it finally, by the result split of all positioning, maps back individual space and forms positioning to entire Ipsilateral cerebral function area
As a result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710551743.1A CN109242816B (en) | 2017-07-07 | 2017-07-07 | Brain glioma pathological grade imaging auxiliary judgment method based on resting state brain function contralateral positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710551743.1A CN109242816B (en) | 2017-07-07 | 2017-07-07 | Brain glioma pathological grade imaging auxiliary judgment method based on resting state brain function contralateral positioning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109242816A true CN109242816A (en) | 2019-01-18 |
CN109242816B CN109242816B (en) | 2022-01-18 |
Family
ID=65082746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710551743.1A Active CN109242816B (en) | 2017-07-07 | 2017-07-07 | Brain glioma pathological grade imaging auxiliary judgment method based on resting state brain function contralateral positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109242816B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113466043A (en) * | 2021-07-19 | 2021-10-01 | 蒙娜丽莎集团股份有限公司 | Method for testing fracture toughness of ceramic rock plate |
CN114187227A (en) * | 2021-09-13 | 2022-03-15 | 北京银河方圆科技有限公司 | Method and device for determining functional area of brain tumor affected area |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106204562A (en) * | 2016-07-04 | 2016-12-07 | 西安交通大学 | A kind of method of the arched roof white matter segmentation merged based on fMRI Yu DTI |
CN106485039A (en) * | 2015-08-24 | 2017-03-08 | 复旦大学附属华山医院 | The construction method of Butut distinguished in a kind of Chinese brain language |
US20170103525A1 (en) * | 2015-10-09 | 2017-04-13 | Mayo Foundation For Medical Education And Research | System and Method for Tissue Characterization Based on Texture Information Using Multi-Parametric MRI |
CN106683081A (en) * | 2016-12-17 | 2017-05-17 | 复旦大学 | Brain glioma molecular marker nondestructive prediction method and prediction system based on radiomics |
CN106780515A (en) * | 2017-01-04 | 2017-05-31 | 南京审计大学 | Glioma method for extracting region in a kind of cerebral magnetic resonance image |
US9984283B2 (en) * | 2015-02-14 | 2018-05-29 | The Trustees Of The University Of Pennsylvania | Methods, systems, and computer readable media for automated detection of abnormalities in medical images |
-
2017
- 2017-07-07 CN CN201710551743.1A patent/CN109242816B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9984283B2 (en) * | 2015-02-14 | 2018-05-29 | The Trustees Of The University Of Pennsylvania | Methods, systems, and computer readable media for automated detection of abnormalities in medical images |
CN106485039A (en) * | 2015-08-24 | 2017-03-08 | 复旦大学附属华山医院 | The construction method of Butut distinguished in a kind of Chinese brain language |
US20170103525A1 (en) * | 2015-10-09 | 2017-04-13 | Mayo Foundation For Medical Education And Research | System and Method for Tissue Characterization Based on Texture Information Using Multi-Parametric MRI |
CN106204562A (en) * | 2016-07-04 | 2016-12-07 | 西安交通大学 | A kind of method of the arched roof white matter segmentation merged based on fMRI Yu DTI |
CN106683081A (en) * | 2016-12-17 | 2017-05-17 | 复旦大学 | Brain glioma molecular marker nondestructive prediction method and prediction system based on radiomics |
CN106780515A (en) * | 2017-01-04 | 2017-05-31 | 南京审计大学 | Glioma method for extracting region in a kind of cerebral magnetic resonance image |
Non-Patent Citations (1)
Title |
---|
马琳: "神经导航系统中的高低级别胶质瘤的鉴别诊断以及基于多DTI参数诊断模型的建立", 《中国博士学位论文全文数据库 医药卫生科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113466043A (en) * | 2021-07-19 | 2021-10-01 | 蒙娜丽莎集团股份有限公司 | Method for testing fracture toughness of ceramic rock plate |
CN114187227A (en) * | 2021-09-13 | 2022-03-15 | 北京银河方圆科技有限公司 | Method and device for determining functional area of brain tumor affected area |
CN114187227B (en) * | 2021-09-13 | 2023-01-24 | 北京银河方圆科技有限公司 | Method and device for determining functional area of brain tumor affected area |
Also Published As
Publication number | Publication date |
---|---|
CN109242816B (en) | 2022-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jin et al. | Automated detection of focal cortical dysplasia type II with surface‐based magnetic resonance imaging postprocessing and machine learning | |
Richards et al. | Brains for all the ages: structural neurodevelopment in infants and children from a life-span perspective | |
Horowitz et al. | In vivo correlation between axon diameter and conduction velocity in the human brain | |
Saleem et al. | High-resolution mapping and digital atlas of subcortical regions in the macaque monkey based on matched MAP-MRI and histology | |
US20210369147A1 (en) | Multimodal Neuroimaging-Based Diagnostic Systems and Methods for Detecting Tinnitus | |
CN108961259A (en) | Cerebral function area opposite side localization method based on tranquillization state functional MRI | |
WO2024083058A1 (en) | System for accurate positioning of abnormal regions of brain fiber tracts | |
Wei et al. | Fully automatic quantification of fibroglandular tissue and background parenchymal enhancement with accurate implementation for axial and sagittal breast MRI protocols | |
CN109242816A (en) | Based on tranquillization state brain function to the glioma pathology rank iconography auxiliary judgement method of side positioning | |
Conte et al. | Cortical source analysis of event-related potentials: a developmental approach | |
Howells et al. | Reproducing macaque lateral grasping and oculomotor networks using resting state functional connectivity and diffusion tractography | |
Nguyen et al. | Ocular structures segmentation from multi-sequences MRI using 3D Unet with fully connected CRFs | |
Sherwood et al. | Self-directed down-regulation of auditory cortex activity mediated by real-time fMRI neurofeedback augments attentional processes, resting cerebral perfusion, and auditory activation | |
CN114065825A (en) | Brain magnetic MEG source positioning method based on structural similarity | |
Li et al. | Diffusion tensor-based fast marching for modeling human brain connectivity network | |
Koch et al. | Evaluating reproducibility and subject-specificity of microstructure-informed connectivity | |
Zanin et al. | Using diffusion-weighted magnetic resonance imaging techniques to explore the microstructure and connectivity of subcortical white matter tracts in the human auditory system | |
Chen et al. | Parametric mapping of brain tissues from diffusion kurtosis tensor | |
Zhang et al. | A Bayesian approach to the creation of a study-customized neonatal brain atlas | |
Ellingson et al. | Gray and white matter delineation in the human spinal cord using diffusion tensor imaging and fuzzy logic | |
Forkel et al. | Structural neuroimaging | |
Cárdenes et al. | Analysis of the pyramidal tract in tumor patients using diffusion tensor imaging | |
Dong et al. | Influence of MRI on Diagnostic Efficacy and Satisfaction of Patients with Alzheimer’s Disease | |
CN106875384B (en) | A kind of universal intelligent automation read tablet method | |
KR20210024853A (en) | Diagnosis Method and System of Idiopathic Normal Pressure Hydrocephalus Using Imaging Diagnostic Equipment |
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 |