CN109691985A - A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM - Google Patents
A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM Download PDFInfo
- Publication number
- CN109691985A CN109691985A CN201811560099.5A CN201811560099A CN109691985A CN 109691985 A CN109691985 A CN 109691985A CN 201811560099 A CN201811560099 A CN 201811560099A CN 109691985 A CN109691985 A CN 109691985A
- Authority
- CN
- China
- Prior art keywords
- dti
- white matter
- epilepsy
- index
- magnetic resonance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4094—Diagnosing or monitoring seizure diseases, e.g. epilepsy
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Neurology (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Veterinary Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM, belongs to epilepsy aided diagnosis technique field.The present invention is first by pre-processing disperse magnetic resonance imaging；The disperse magnetic resonance index for extracting the main white matter fiber skeleton of brain, calculates multiple disperse indexs in 50 core white matter regions according to graph cut, then extracts the disperse index in the white matter region with significant difference；Then classify using the machine learning method of support vector machines, using the disperse index in the white matter region of most distinction as input feature vector, carry out model training test.Be finally reached to left temporal lobe epilepsy, right side patients with temporal lobe epilepsy, normal person Classification and Identification.Present invention incorporates the Classification and Identifications that emerging magnetic resonance imaging mode and machine learning carry out patients with temporal lobe epilepsy, provide new thinking and approach for the auxiliary diagnosis of clinically patients with temporal lobe epilepsy.
Description
Technical field
The invention belongs to epilepsy aided diagnosis technique fields, more particularly to one kind to be based on diffusion tensor (diffusion
Tensor imaging, DTI) and support vector machines (support vector machine, SVM) temporal epilepsy
The method that (temporal lobe epilepsy, TLE) patient identifies classification.
Background technique
Temporal epilepsy is the clinically most common medically intractable epilepsy, focal epilepsy.Seizure types include simple portion
Divide property breaking-out, complex partial seizures and secondary generalized seizures or combinations of these breaking-outs, often there is febrile convulsion medical history
With epilepsy family history.The typical feature of simple partial seizure is that have the symptom of autonomic nerve and (or) spirit, most common
It is the feeling that upper abdomen one gas up rushes.For the TLE patient that part can not be controlled with drug, operation excision Epileptic focus is one
The effective therapeutic modality of kind.The operative treatment mode of TLE specifically include that anterior temporal lobectomy, preceding medial temporal lobe resection and
Selective amygdalohippocampectomy etc..But many TLE patients conventional Magnetic resonance imaging (magnetic in the preoperative
Resonance imaging, MRI) check show no obvious abnormalities, but often there is extensive white matter and gray matter loss in patients.
DTI is a kind of emerging magnetic resonance imaging mode of unique non-intrusion type reflection cerebral white matter fiber beam.Pass through reflection
The motion conditions of hydrone in organism, Fractional anisotropy (fractional anisotropy, FA) axially diffuse rate
(axial diffusivity, AD), radial diffusion rate (radial diffusivity, RD), Mean diffusivity (mean
Diffusivity, MD) etc. parameters can reflect the integrality of white matter structure indirectly.Since TLE patient's Epileptic focus singularly put by epilepsy
Electricity, white matter fiber tract become the propagation path of Epileptic discharge, and long-term abnormal electrical activity and epileptic attack repeatedly cause brain group
The variation for knitting microenvironment leads to the damage of brain tissue microstructure, such as axonal degeneration, myelinoclasis or extracellular oedema, causes
Free water molecule increases in organizing, and causes the broadening of space between cells, to change hydrone disperse movement degree.Therefore, can lead to
Preoperative assessment can be carried out to TLE patient's Epileptic focus and surrounding annulus beam relationship by crossing DTI and white matter fiber tract tracer technique, be
The clinic of TLE patient's lesion determines side and positioning provides objective imaging evidence, deepens people to TLE patient's pathophysiological mechanism
Understanding.
Using machine learning method analysis MR data more and more attention has been paid to.Traditional analysis is based on magnetic resonance
The double sample t method of inspection of the voxel hypothesis testing of image, however this method can only be found in group level patient group with just
Difference between ordinary person's group can not carry out auxiliary diagnosis to individual from Point of View of Clinical.And machine learning used by us
Method is the mode identification method based on feature, can be found feature and classification using the indices of brain as feature
Relationship between attribute, and distinguish patient and normal person from individual level and position the Ipsilateral of patient's Epileptic focus.Therefore, originally
Invention combines disperse magnetic resonance imaging mode and machine learning method to carry out the Classification and Identification of patients with temporal lobe epilepsy, can be used as one kind
Preoperative diagnosis, curative effect evaluation and a kind of means routinely checked.
Summary of the invention
The present invention is intended to provide a kind of side for reaching identification patients with temporal lobe epilepsy using machine learning method analysis DTI data
Method.The lesion that the main white matter of brain index using SVM and TLE patient carries out TLE patient determines side, by left and right side temporal epilepsy
Patient and normal control mutually distinguish in individual level.
In order to achieve the above objectives, the technical solution adopted by the present invention is divided into three modules: DTI image pre-processing module；DTI
Image characteristics extraction module；Svm classifier module based on DTI feature: left temporal lobe epilepsy, right side patients with temporal lobe epilepsy are distinguished
And normal person.
(a) DTI image pre-processing module
Magnetic resonance image is pre-processed based on PANDA, fsl:
Step A1: the image of collected DICOM format is converted to the image of 3D or 4D NIFTI format；
Step A2: obtaining full brain mask to the image that step A1 is obtained, and carries out the dynamic correction of current vortex, head；
Step A3: the related each index of DTI is calculated using DTIFIT tool to the image of step A2, obtains the related respectively finger of DTI
Logo image；The related each index of DTI includes FA, AD, RD, MD value；
(b) DTI image characteristics extraction module
Skeletonizing, which is carried out, based on the related each index image of DTI that PANDA extracts step (a) extracts brain main skeleton
Each index of average DTI of fibre bundle, method includes the following steps:
Step B1: the related each indicatrix non-linear registration of DTI will be obtained to normed space；
Step B2: the FA figure equalization of normed space is obtained into average FA figure；
Step B3: average FA figure skeletonizing, thresholding are obtained into average FA skeleton drawing；
Step B4: each indicatrix of the DTI of normed space is projected to average FA skeleton drawing, obtains the DTI on white matter skeleton
Each index feature figure；
Step B5: it is based on ICBM-DTI-81 white matter map, each index feature figure of DTI obtained in the previous step is divided respectively
For 50 core white matter regions, each index feature value of DTI in this 50 core white matter regions is obtained；
(c) based on the svm classifier module of DTI feature, this method is mainly comprised the steps that
Step C1: two is passed through to each index feature value of DTI in 50 core white matter regions of patient's group and Normal group
Sample t-test extracts the feature of most difference；Patient's group includes left temporal lobe epileptic, right side temporal epilepsy trouble
Person；
Step C2: inputting above-mentioned most variant feature as feature, and input sample (includes training set and survey
Examination collection), then classified using support vector machine method；If sample size is smaller, it can be used and a cross-validation method is stayed to assess
The discrimination of SVM classifier.
Detailed description of the invention
Fig. 1 is whole implementation mode flow chart of the present invention；
Fig. 2 is the flow chart of DTI image preprocessing；
Fig. 3 is that embodiment 1 extracts the discrepant DTI feature flow chart of tool；
Specific embodiment
The present invention will be described in detail for result specific embodiment and attached drawing below, but embodiments of the present invention are not
It is limited to this.
Embodiment 1
Magnetic resonance image is pre-processed based on PANDA, fsl, method includes the following steps:
Step A1: the image of collected DICOM format is converted to the image of 3D or 4D NIFTI format；
Step A2: obtaining full brain mask, carries out the dynamic correction of current vortex, head；
Step A3: DTI index of correlation is calculated using DTIFIT tool, obtains the DTI index of correlation figure such as FA, AD, RD, MD
Picture.
Skeletonizing, which is carried out, based on DTI index of correlation image of the PANDA to extraction extracts brain main skeleton fibre bundle
Average DTI index, method includes the following steps:
Step B1: the indexs of correlation such as FA non-linear registration will be obtained to normed space；
Step B2: the FA figure equalization of normed space is obtained into average FA figure；
Step B3: average FA figure skeletonizing, thresholding (FA > 0.2) are obtained into average FA skeleton drawing；
Step B4: the figures such as FA, AD, RD, MD of normed space are projected to average FA skeleton drawing, are obtained on white matter skeleton
FA, AD, RD, MD figure；
Step B5: it is based on ICBM-DTI-81 white matter map, each DTI indicatrix obtained in the previous step is divided into 50 cores
FA, AD, RD, MD value in each white matter region can be obtained in the white matter region of the heart.
TLE based on SVM identifies classification, and this method mainly comprises the steps that
Step C1: two is passed through to each DTI index in 50 core white matter regions of patient's group and Normal group
Sample t-test extracts the feature of most distinction；It is specifically shown in Fig. 3, Fig. 3 is parts of images treatment process.
Step C2: it is inputted the feature of most distinction as feature.And input sample (includes training set and test
Collection).Then classified using SVM method, if sample size is smaller, can be used and a cross-validation method is stayed to assess SVM classifier
Discrimination.
Claims (8)
1. combining the temporal epilepsy aided diagnosis method of disperse magnetic resonance imaging and support vector machines, it is characterised in that: this method
It comprises the steps of,
Step a:DTI image preprocessing；
Step b:DTI image white matter framework characteristic extracts；
Step c:DTI feature selecting；
Step d: in conjunction with the Classification and Identification of the patients with temporal lobe epilepsy of the DTI feature and SVM method of cerebral white matter skeleton.
2. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: the image pre-processing method of step a comprises the steps of:
Magnetic resonance image is pre-processed based on PANDA, fsl:
Step A1: the image of collected DICOM format is converted to the image of 3D or 4D NIFTI format；
Step A2: obtaining full brain mask to the image that step A1 is obtained, and carries out the dynamic correction of current vortex, head；
Step A3: the related each index of DTI is calculated using DTIFIT tool to the image of step A2, obtains the related each indicatrix of DTI
Picture；The related each index of DTI includes FA, AD, RD, MD.
3. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: the DTI image white matter framework characteristic extracting method of step b comprises the steps of:
Skeletonizing, which is carried out, based on the related each index image of DTI that PANDA extracts step (a) extracts brain main skeleton fiber
Each index of average DTI of beam, method includes the following steps:
Step B1: the related each indicatrix non-linear registration of DTI will be obtained to normed space；
Step B2: the FA figure equalization of normed space is obtained into average FA figure；
Step B3: average FA figure skeletonizing, thresholding are obtained into average FA skeleton drawing；
Step B4: each indicatrix of the DTI of normed space is projected to average FA skeleton drawing, the DTI obtained on white matter skeleton respectively refers to
Mark characteristic pattern；
Step B5: it is based on ICBM-DTI-81 white matter map, each index feature figure of DTI obtained in the previous step is divided into 50 respectively
A core white matter region obtains each index feature value of DTI in this 50 core white matter regions.
4. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: step c, in d the following steps are included:
Step C1: two is passed through to each index feature value of DTI in 50 core white matter regions of patient's group and Normal group
Sample t-test extracts the feature of most difference；Patient's group includes left temporal lobe epileptic, right side temporal epilepsy trouble
Person；
Step C2: inputting above-mentioned most variant feature as feature, and input sample includes training set and test set,
Then classified using support vector machine method；If sample size is smaller, SVM classifier is assessed using a cross-validation method is stayed
Discrimination.
5. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: four dispersive tests extracted on the cerebral white matter skeleton of disperse magnetic resonance imaging include FA, AD, RD, MD
The Ipsilateral that value carries out patients with temporal lobe epilepsy lesion identifies classification.
6. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: the cerebral white matter framework characteristic of extracted DTI image is to be based on ICBM-DTI-81 white matter map for brain
White matter skeleton is divided into 50 core white matter regions, then the DTI index of 50 all voxels in core white matter region is sought averagely
The DTI index of each white matter fiber tract can be obtained in value.
7. the temporal epilepsy auxiliary diagnosis side of combination disperse magnetic resonance imaging according to claim 1 and support vector machines
Method, it is characterised in that: the white matter of brain index based on patients with temporal lobe epilepsy carries out patients with temporal lobe epilepsy lesion using SVM method
Ipsilateral identification classification.
8. the system obtained according to claim 1-7 either method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811560099.5A CN109691985A (en) | 2018-12-19 | 2018-12-19 | A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811560099.5A CN109691985A (en) | 2018-12-19 | 2018-12-19 | A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109691985A true CN109691985A (en) | 2019-04-30 |
Family
ID=66232717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811560099.5A Pending CN109691985A (en) | 2018-12-19 | 2018-12-19 | A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109691985A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111161261A (en) * | 2020-01-07 | 2020-05-15 | 南京慧脑云计算有限公司 | Quantitative analysis method for newborn brain development based on magnetic resonance diffusion tensor brain image |
| CN111311585A (en) * | 2020-02-24 | 2020-06-19 | 南京慧脑云计算有限公司 | Magnetic resonance diffusion tensor brain image analysis method and system for neonates |
| CN111543994A (en) * | 2020-04-24 | 2020-08-18 | 天津大学 | Epilepsy auxiliary detection system based on white matter connection diagram and parallel convolution neural network |
| CN111956221A (en) * | 2020-09-07 | 2020-11-20 | 南京医科大学 | Temporal lobe epilepsy classification method based on wavelet scattering factor and LSTM neural network model |
| CN113545766A (en) * | 2021-06-18 | 2021-10-26 | 遵义医科大学附属医院 | Method for predicting gross motor function of spastic cerebral palsy children based on MRI nomogram |
| CN114376522A (en) * | 2021-12-29 | 2022-04-22 | 四川大学华西医院 | Method for constructing computer recognition model for recognizing juvenile myoclonus epilepsy |
| CN114418982A (en) * | 2022-01-14 | 2022-04-29 | 太原理工大学 | Method for constructing DTI multi-parameter fusion brain network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170087367A1 (en) * | 2012-11-16 | 2017-03-30 | Rio Grande Neurosciences, Inc. | System for variably configurable, adaptable electrode arrays and effectuating software |
| CN103996196B (en) * | 2014-05-28 | 2017-06-30 | 西安电子科技大学 | A kind of DTI image analysis methods based on multivariable |
| CN108652630A (en) * | 2018-04-13 | 2018-10-16 | 廉江市人民医院 | A kind of neurosurgery cerebral operations auxiliary machine |
-
2018
- 2018-12-19 CN CN201811560099.5A patent/CN109691985A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170087367A1 (en) * | 2012-11-16 | 2017-03-30 | Rio Grande Neurosciences, Inc. | System for variably configurable, adaptable electrode arrays and effectuating software |
| CN103996196B (en) * | 2014-05-28 | 2017-06-30 | 西安电子科技大学 | A kind of DTI image analysis methods based on multivariable |
| CN108652630A (en) * | 2018-04-13 | 2018-10-16 | 廉江市人民医院 | A kind of neurosurgery cerebral operations auxiliary machine |
Non-Patent Citations (6)
| Title |
|---|
| CUI ZAIXU ET AL: "《PANDA: a pipeline toolbox for analyzing brain diffusion images》", 《FRONTIERS IN HUMAN NEUROSCIENCE》 * |
| DIEGO CANTOR-RIVERA等: "《Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative MR imaging》", 《ROBARTS IMAGING PUBLICATIONS》 * |
| HAI LI 等: "《Distinguishing Left or Right Temporal Lobe Epilepsy from Controls Using Fractional Anisotropy Asymmetry Analysis》", 《MEDICAL IMAGING AND VIRTUAL REALITY. SPRINGER, BERLIN, HEIDELBERG》 * |
| 安杰: "《应用机器学习方法对内侧颞叶癫痫患者全脑白质的研究》", 《中国博士学位论文全文数据库医药卫生科技辑》 * |
| 张瑛等: "《儿科护理学》", 30 June 2016 * |
| 赵地: "《颞叶癫痫病患者脑部弥散张量影像研究》", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111161261A (en) * | 2020-01-07 | 2020-05-15 | 南京慧脑云计算有限公司 | Quantitative analysis method for newborn brain development based on magnetic resonance diffusion tensor brain image |
| CN111311585A (en) * | 2020-02-24 | 2020-06-19 | 南京慧脑云计算有限公司 | Magnetic resonance diffusion tensor brain image analysis method and system for neonates |
| CN111543994A (en) * | 2020-04-24 | 2020-08-18 | 天津大学 | Epilepsy auxiliary detection system based on white matter connection diagram and parallel convolution neural network |
| CN111543994B (en) * | 2020-04-24 | 2023-04-07 | 天津大学 | Epilepsy auxiliary detection system based on white matter connection diagram and parallel convolution neural network |
| CN111956221A (en) * | 2020-09-07 | 2020-11-20 | 南京医科大学 | Temporal lobe epilepsy classification method based on wavelet scattering factor and LSTM neural network model |
| CN111956221B (en) * | 2020-09-07 | 2022-06-07 | 南京医科大学 | Temporal lobe epilepsy classification method based on wavelet scattering factor and LSTM neural network model |
| CN113545766A (en) * | 2021-06-18 | 2021-10-26 | 遵义医科大学附属医院 | Method for predicting gross motor function of spastic cerebral palsy children based on MRI nomogram |
| CN114376522A (en) * | 2021-12-29 | 2022-04-22 | 四川大学华西医院 | Method for constructing computer recognition model for recognizing juvenile myoclonus epilepsy |
| CN114376522B (en) * | 2021-12-29 | 2023-09-05 | 四川大学华西医院 | Method for constructing computer identification model for identifying juvenile myoclonus epilepsy |
| CN114418982A (en) * | 2022-01-14 | 2022-04-29 | 太原理工大学 | Method for constructing DTI multi-parameter fusion brain network |
| CN114418982B (en) * | 2022-01-14 | 2022-11-01 | 太原理工大学 | Method for constructing DTI multi-parameter fusion brain network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109691985A (en) | A kind of temporal epilepsy aided diagnosis method based on DTI technology and SVM | |
| Li et al. | Deep learning for hemorrhagic lesion detection and segmentation on brain CT images | |
| Zhuang et al. | Multimodal classification of drug-naïve first-episode schizophrenia combining anatomical, diffusion and resting state functional resonance imaging | |
| Moosavi et al. | Imaging features of vessels and leakage patterns predict extended interval aflibercept dosing using ultra-widefield angiography in retinal vascular disease: findings from the PERMEATE study | |
| Cenek et al. | Survey of image processing techniques for brain pathology diagnosis: Challenges and opportunities | |
| Zhu et al. | Discovering dense and consistent landmarks in the brain | |
| Kar et al. | Multi-compartment spatially-derived radiomics from optical coherence tomography predict anti-VEGF treatment durability in macular edema secondary to retinal vascular disease: preliminary findings | |
| Mostafa et al. | Parkinson’s disease detection using ensemble architecture from mr images | |
| JP6771966B2 (en) | Magnetic resonance imaging device and image processing device | |
| Yang et al. | Exploring sMRI biomarkers for diagnosis of autism spectrum disorders based on multi class activation mapping models | |
| Xie et al. | Cntseg: A multimodal deep-learning-based network for cranial nerves tract segmentation | |
| Presson et al. | Quantifying white matter structural integrity with high-definition fiber tracking in traumatic brain injury | |
| Iqbal et al. | Hybrid Parallel Fuzzy CNN Paradigm: Unmasking Intricacies for Accurate Brain MRI Insights | |
| Wang et al. | A calibrated SVM based on weighted smooth GL1/2 for Alzheimer’s disease prediction | |
| EP3956675A1 (en) | Methods and apparatus for detecting injury using multiple types of magnetic resonance imaging data | |
| Jain et al. | A review of deep learning-based disease detection in Alzheimer's patients | |
| Hassen et al. | Deep learning methods for early detection of Alzheimer’s disease using structural MR images: A survey | |
| Dicente Cid et al. | From local to global: A holistic lung graph model | |
| Li et al. | A hybrid approach to detection of brain hemorrhage candidates from clinical head ct scans | |
| Zhang et al. | Multi-scale discriminative regions analysis in FDG-PET imaging for early diagnosis of Alzheimer’s disease | |
| ElNakieb et al. | Identifying brain pathological abnormalities of autism for classification using diffusion tensor imaging | |
| Miao et al. | CoWRadar: Visual Quantification of the Circle of Willis in Stroke Patients. | |
| Coluzzi et al. | Biomarker Investigation using Multiple Brain Measures from MRI through XAI in Alzheimer's Disease Classification | |
| Xie et al. | Deep Multimodal Fusion Network for the Retinogeniculate Visual Pathway Segmentation | |
| Qu et al. | Multiple classifier fusion and optimization for automatic focal cortical dysplasia detection on magnetic resonance images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190430 |
|
| RJ01 | Rejection of invention patent application after publication |