AU2021103997A4 - Artificial neural network based brain disorder diagnostic system - Google Patents
Artificial neural network based brain disorder diagnostic system Download PDFInfo
- Publication number
- AU2021103997A4 AU2021103997A4 AU2021103997A AU2021103997A AU2021103997A4 AU 2021103997 A4 AU2021103997 A4 AU 2021103997A4 AU 2021103997 A AU2021103997 A AU 2021103997A AU 2021103997 A AU2021103997 A AU 2021103997A AU 2021103997 A4 AU2021103997 A4 AU 2021103997A4
- Authority
- AU
- Australia
- Prior art keywords
- meg
- neural network
- diagnostic system
- disease
- brain disorder
- 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.)
- Ceased
Links
- 208000014644 Brain disease Diseases 0.000 title claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 20
- 238000002582 magnetoencephalography Methods 0.000 claims abstract description 32
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 12
- 201000010099 disease Diseases 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012706 support-vector machine Methods 0.000 claims abstract description 6
- 238000002790 cross-validation Methods 0.000 claims abstract description 5
- 238000012502 risk assessment Methods 0.000 claims abstract description 5
- 238000010586 diagram Methods 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 abstract description 9
- 208000024827 Alzheimer disease Diseases 0.000 abstract description 3
- 208000018737 Parkinson disease Diseases 0.000 abstract description 3
- 206010015037 epilepsy Diseases 0.000 abstract description 2
- 210000004556 brain Anatomy 0.000 description 6
- 208000014674 injury Diseases 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 208000027418 Wounds and injury Diseases 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000007177 brain activity Effects 0.000 description 2
- 208000029028 brain injury Diseases 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000008733 trauma Effects 0.000 description 2
- 230000000472 traumatic effect Effects 0.000 description 2
- 208000003174 Brain Neoplasms Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004770 neurodegeneration Effects 0.000 description 1
- 208000015122 neurodegenerative disease Diseases 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/242—Detecting biomagnetic fields, e.g. magnetic fields produced by bioelectric currents
- A61B5/245—Detecting biomagnetic fields, e.g. magnetic fields produced by bioelectric currents specially adapted for magnetoencephalographic [MEG] signals
-
- 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
- A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
- A61B5/4064—Evaluating the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—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
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2576/00—Medical imaging apparatus involving image processing or analysis
- A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
- A61B2576/026—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part for the brain
Abstract
ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER
DIAGNOSTIC SYSTEM
This invention relates to a method for empirical risk assessment of brain disorder
using a neural network diagnostic system. The said method comprises the steps of
magneto-encephalography (MEG) measurement of resting-state MEG signals
using a MEG scanner, data pre-processing of the MEG signals measured,
developing network architecture, made of a convolution neural network, model
training and testing, by evaluating the performance of the developed network
architecture based on the sample data and the open-access databases, nested cross
validation, for classifying 10 patients with Alzheimer's disease, Epilepsy, and
Parkinson's disease, decoding the disease labels, by using relative power of the
MEG signals using a support vector machines (SVM) model.
8
MEG Signals measurement.
Data Pre-processing of the measured MEG Signals.
Developing network architecture model. [
Model training and testing. [
Nested cross-validation of the trained and tested
model,
Decoding the disease labels.
Figure 1. Flow Diagram of Artificial Neural Network Based Brain Disorder Diagnostic System
9
Description
ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER DIAGNOSTIC SYSTEM This invention relates to a method for empirical risk assessment of brain disorder
using a neural network diagnostic system. The said method comprises the steps of
magneto-encephalography (MEG) measurement of resting-state MEG signals
using a MEG scanner, data pre-processing of the MEG signals measured,
developing network architecture, made of a convolution neural network, model
training and testing, by evaluating the performance of the developed network
architecture based on the sample data and the open-access databases, nested cross
validation, for classifying 10 patients with Alzheimer's disease, Epilepsy, and
Parkinson's disease, decoding the disease labels, by using relative power of the
MEG signals using a support vector machines (SVM) model.
MEG Signals measurement.
Data Pre-processing of the measured MEG Signals.
Developing network architecture model. [ Model training and testing. [ Nested cross-validation of the trained and tested model,
Decoding the disease labels.
Figure 1. Flow Diagram of Artificial Neural Network Based Brain Disorder Diagnostic System
(See Section 10; rule 13)
The following specification particularly describes the invention and the manner in which it is to be performed
ARTIFICIAL NEURAL NETWORK BASED BRAIN DISORDER DIAGNOSTIC SYSTEM Description of the invention
• The present invention relates to an assessment of brain disorder and in
particular to the empirical risk assessment of brain disorder using a neural
network diagnostic system.
• Brain disorders are the disease or disabilities which affect the central nervous
system or the brain. Various such disorders affect millions of people annually.
• The conditions in a brain disorder are caused by illness, genetics, and traumatic
injury. Brain injuries are caused by trauma, and this affects the brain's ability to
communicate with the rest of the body.
• Tumors formed or spread in the brain are called brain tumours-other than
these, certain neurodegenerative diseases such as Alzheimer's disease,
Parkinson's disease, etc. Apart fromdiseases and injuries, brain disorders also
include mental disorders.
• To diagnose a brain disorder, the neuro specialist performs a neurological exam
and also gets images of the brain. The most common imaging tools used are
CT, MRI, and PET scans.
• The diagnosis also includes evaluation based on symptoms and history. In an
aspect, the said method comprises the steps of magnetoencephalography
(MEG) measurement, of resting-state MEG signals using a MEG scanner.
• Data pre- processing, of the MEG signals measured by filtering them by a low
pass and a high pass filter, developing network architecture, made of a
convolution neural network in which the features extracted by the
convolutional layers and the relative powers of different frequency bands are
concatenated before fully connected layer, model training and testing, by
evaluating the performance of the developed network architecture based on the
sample dataand the open-access databases.
• In an embodiment of the present invention, Fig 1 illustrates an exemplary flow
chart of the method for the empirical risk assessment of brain disorder using a
neural networkdiagnostic system.
• In an aspect, brain disorders are the disease or disabilities which affect the
central nervous system or the brain. Various such disorders affect millions of
peopleannually.
• The conditions in a brain disorder are caused by illness, genetics, and traumatic
injury. Brain injuries are caused by trauma, and this affects the brain's ability to
communicate with the rest of the body.
• The diagnosis also includes evaluation based on symptoms and history. In an
aspect, with recent advancements in technology available to medical professionals to generate, gather, and analyze data, the development of an intelligent medicaldiagnosis system is being attempted.
• Neural networks are used as a tool for building the intelligent diagnostic
system known as a neural network diagnosis system.
• This diagnosis system is composed of several modules which generate, gather,
and analyze data from various medical equipment and laboratory tests.
• The data is represented in the form of a numerical vector. The system uses a
neural network model which is trained and tested using the sample data
available.
• Thereafter, the trained model analyses live data and give out the result. The
system comprises medical equipment, for collecting data, a sample dataset, and
atrained and tested neural network model.
• In an aspect, the invention discloses a method for empirical risk
assessment of brain disorder using a neural network diagnostic system.
• The said method comprises the steps of magnetoencephalography (MEG)
measurement, data pre- processing, developing network architecture, model
training and testing, nested cross-validation, decoding the disease labels.
• In an aspect, magnetoencephalography (MEG) is a non-invasive method for
diagnosing human brain activity. MEG measures the ongoing brain activity on a millisecond- by-millisecond basis.
• In the present invention, the MEG signals are measured under different
measurement conditions of different sampling frequencies, low pass, and high
pass filters. During MEG measurements, patients are in a supine position with
a centred head in the MEG scanner.
• They are asked not to fall asleep to relax without thinking of anything in
particular during the measurement. However, these guidelines can be changed
based on the type of brain disorder suspected in the patient.
• In an aspect, the data pre-processing of the measured MEG signal is done by
filtering the signals by a low pass filter (typically of 1Hz) and a high pass filter
an important step to improve the quality of data for further statistical analysis.
• The modalities of the MEG scan may contain a broad range of noise, including
motion, average signal intensity, and special distortion. This step further
involves the steps of scaling, correction, stripping/trimming, normalization,
filtering, and smoothing. Scaling corrects several issues such as image resizing,
image registration, and resolution enhancement. Correction corrects the slice
dependent delays of image slices and subject motion. It is made up of a
convolution neural network in which the features extracted by the
convolutionallayers.
" Relative powers of different frequency bands are concatenated before a fully
connected layer.
• A convolution neural network usually takes an input image, assigns learnable
weights with biases to different aspects in the image, differentiating one
picture from the other.
• In at least one of its layers, instead of matrix multiplication, it uses convolution
operation.
Claims (5)
1. This invention focuses on empirical risk assessment of brain disorder using a
neural network diagnostic system.
2. Decoding the disease labels involves classification of decoding features from all input segments and then performing majority voting to determine one disease label. 3. The nested cross-validation (110) is performed in two multi-fold loops,
wherein the outer loop is re-trained and re-tested.
4. The steps of magneto-encephalography (MEG) measurement of resting-state
MEG signals using a MEG scanner, data pre-processing of the MEG signals
measured, developing network architecture, made of a convolution neural
network, model training and testing.
5. Decoding the disease labels is done by using relative power of the MEG
signals using a support vector machines (SVM) model.
Figure 1. Flow Diagram of Artificial Neural Network Based Brain Disorder Diagnostic System
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103997A AU2021103997A4 (en) | 2021-07-09 | 2021-07-09 | Artificial neural network based brain disorder diagnostic system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103997A AU2021103997A4 (en) | 2021-07-09 | 2021-07-09 | Artificial neural network based brain disorder diagnostic system |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021103997A4 true AU2021103997A4 (en) | 2021-09-09 |
Family
ID=77563732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021103997A Ceased AU2021103997A4 (en) | 2021-07-09 | 2021-07-09 | Artificial neural network based brain disorder diagnostic system |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021103997A4 (en) |
-
2021
- 2021-07-09 AU AU2021103997A patent/AU2021103997A4/en not_active Ceased
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mumtaz et al. | Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD) | |
Mumtaz et al. | A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD) | |
Khare et al. | PDCNNet: An automatic framework for the detection of Parkinson’s disease using EEG signals | |
Patidar et al. | An integrated alcoholic index using tunable-Q wavelet transform based features extracted from EEG signals for diagnosis of alcoholism | |
Kulkarni et al. | Extracting salient features for EEG-based diagnosis of Alzheimer's disease using support vector machine classifier | |
Buettner et al. | High-performance diagnosis of sleep disorders: a novel, accurate and fast machine learning approach using electroencephalographic data | |
Al-Qazzaz et al. | Selection of mother wavelets thresholding methods in denoising multi-channel EEG signals during working memory task | |
Amezquita-Sanchez et al. | A new dispersion entropy and fuzzy logic system methodology for automated classification of dementia stages using electroencephalograms | |
Boubchir et al. | A review of feature extraction for EEG epileptic seizure detection and classification | |
JP7373555B2 (en) | Quantification of motor function using EEG signals | |
CN111568446A (en) | Portable electroencephalogram depression detection system combined with demographic attention mechanism | |
EP3241489A1 (en) | Predictive neuromarkers of alzheimer's disease | |
Tawhid et al. | Automatic and efficient framework for identifying multiple neurological disorders from EEG signals | |
Baumgartl et al. | Detecting Antisocial Personality Disorder Using a Novel Machine Learning Algorithm Based on Electroencephalographic Data. | |
Kwon et al. | Deep learning based pre-screening method for depression with imagery frontal eeg channels | |
Soni et al. | Graphical representation learning-based approach for automatic classification of electroencephalogram signals in depression | |
Ein Shoka et al. | EEG seizure detection: concepts, techniques, challenges, and future trends | |
Patil et al. | A method for detection and reduction of stress using EEG | |
Saini et al. | Discriminatory features based on wavelet energy for effective analysis of electroencephalogram during mental tasks | |
AU2021103997A4 (en) | Artificial neural network based brain disorder diagnostic system | |
Nurfirdausi et al. | Wavelet Decomposition and Feedforward Neural Network for Classification of Acute Ischemic Stroke based on Electroencephalography | |
Sharma et al. | The role of EEG signal processing in detection of neurocognitive disorders | |
AU2021104107A4 (en) | A method for empirical risk assessment of brain disorder using neural network diagnostic system | |
Boppana et al. | Deep Learning Approach for an early stage detection of Neurodevelopmental Disorders | |
Qaisar | Adaptive rate EEG processing and machine learning-based efficient recognition of epilepsy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |