CN110786868A - Non-invasive detection and eye movement analysis method for ASD screening - Google Patents

Non-invasive detection and eye movement analysis method for ASD screening Download PDF

Info

Publication number
CN110786868A
CN110786868A CN201910994949.0A CN201910994949A CN110786868A CN 110786868 A CN110786868 A CN 110786868A CN 201910994949 A CN201910994949 A CN 201910994949A CN 110786868 A CN110786868 A CN 110786868A
Authority
CN
China
Prior art keywords
eye movement
video
child
asd
stimulation
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
Application number
CN201910994949.0A
Other languages
Chinese (zh)
Inventor
刘昱
李畅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN201910994949.0A priority Critical patent/CN110786868A/en
Publication of CN110786868A publication Critical patent/CN110786868A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/16Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/163Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state by tracking eye movement, gaze, or pupil change
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/16Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165Evaluating the state of mind, e.g. depression, anxiety

Abstract

The invention discloses a non-invasive detection and eye movement analysis method for ASD screening, which adjusts the height of an eye movement instrument to be flush with the binocular of a tested child; initializing and calibrating the sight track of the child by using a guide video played by a three-dimensional video eye tracker; the method comprises the steps that a stimulation video matched with an eye movement tracking task is played by a stereoscopic video eye movement instrument, wherein the stimulation video is designed aiming at ASD (ASD children testing) and accords with social expressions of ASD children diagnosis; watching the stimulation video in the step (3) by using a high-definition hidden camera in a state that the tested child is not aware of (the watching experience is not influenced), and synchronously acquiring the eye movement video of the tested child; and analyzing the acquired data information of the eye movement video of the detected child according to an intelligent eye movement algorithm, and finally calculating the ASD probability of the child. The invention combines non-invasive high-immersion equipment with intelligent eye movement algorithm technology, and provides an effective means for early ASD child discovery and timely tracking treatment.

Description

Non-invasive detection and eye movement analysis method for ASD screening
Technical Field
The invention relates to the technical field of intelligent eye movement data analysis methods and the like, in particular to an intelligent eye movement data analysis method aiming at ASD screening.
Background
ASD (autism spectrum disorder), also known as autism, is a more serious congenital disease of developmental disorders. The core symptoms of patients are: social communication disorder, incapability of smooth communication with other people or lack of normal attaching relationship with parents and the like; language communication is obstructed, and the language development is laggard or language backing phenomenon occurs; the carving action is repeated, and one action is repeated continuously. Not all ASD patients suffer from the above three symptoms, and ASD patients are classified into low-to-high lineages according to the wide degree of the symptom coverage and the prominent degree of the expression, and the lower the ASD patients are more serious, the higher the ASD patients are closer to the ordinary people. The screening and the intervention treatment can achieve better treatment effect as soon as possible.
With the continuous progress of society and the rapid development of science and technology, the presentation experience of the stereoscopic video eye tracker with high comfort and high immersion and the rapid development of an intelligent and efficient deep learning algorithm provide a feasible and effective method for the research of the method. The three-dimensional video playing device, the ASD-oriented stimulation video analysis and production, the high-definition camera eye movement shooting and recording and the intelligent eye movement data analysis technology are non-invasive screening tools which can be used for related technical means based on ASD screening in child health examination. If the realized screening tool can cooperate with medical professionals, the professional quality of the screening tool not only ensures the feasibility of the method technology, but also improves the accuracy and the scientificity of the research carried out by the method.
The above points make possible the research of non-invasive detection and eye movement analysis devices for ASD screening.
Disclosure of Invention
The invention aims to provide a non-invasive detection and eye movement analysis method for ASD screening, and aims to solve the technical problem of realizing the ASD screening based on intelligent eye movement data analysis.
The non-invasive detection and eye movement analysis method for ASD screening has the following positive effects:
the noninvasive high-immersion device and the intelligent eye movement algorithm technology are combined together, and an effective means is provided for early ASD child discovery and timely tracking treatment.
Drawings
Fig. 1 is a flow chart of the non-invasive detection and eye movement analysis device for ASD screening according to the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
The invention relates to a non-invasive detection and eye movement analysis method for ASD screening, which specifically comprises the following steps:
step 1, adjusting the height of an eye tracker to be flush with the binocular of a tested child;
step 2, initializing and calibrating the sight line track of the child by using a guide video played by the stereo video eye tracker;
step 3, a stimulation video matched with the eye movement tracking task is played by using a stereoscopic video eye movement instrument, wherein the stimulation video is a stereoscopic stimulation video which is designed aiming at ASD (ASD children testing) and accords with the social performance of ASD children diagnosis;
step 4, watching the stimulation video in the step 3 in a state that the tested child is not aware of (the watching experience is not influenced) by utilizing the high-definition hidden camera, and synchronously acquiring the eye movement video of the tested child;
step 5, according to the analysis of the intelligent eye movement algorithm, firstly carrying out orbit positioning and standard quantization, then extracting and segmenting pupils and irises by using a deep convolutional neural network on the basis, and finally realizing 3D fitting of eyes so as to realize real-time prediction of sight gaze fixation points; the collected data information of the eye movement video of the detected child obtains the fixation point of each time and the overall sight track of the detected child, and the eye movement information of the child is classified and extracted according to the expert suggestion and compared with a healthy child sample, and finally the ASD probability of the child is calculated.
The technology adopted by the process mainly comprises the setting of a stereoscopic stimulation video playing system and the calibration and analysis of the eye movement track. Through cooperation with professional medical experts, the ASD screening-oriented non-invasive detection method is designed, a stereoscopic video player provides a kaleidoscope type semi-immersion watching experience for children, the children explore eye movement fixation points and tracks of the children by completing a watching task under the guidance of a stimulation video, then the eye movement tracks of the children are analyzed through an intelligent eye movement algorithm combined with deep learning, and finally screening of the early-stage ASD susceptibility of the children can be achieved.

Claims (1)

1. A non-invasive detection and eye movement analysis method for ASD screening is characterized by comprising the following steps:
step 1, adjusting the height of an eye tracker to be flush with the binocular of a tested child;
step 2, initializing and calibrating the sight line track of the child by using a guide video played by the stereo video eye tracker;
step 3, a stimulation video matched with the eye movement tracking task is played by using a stereoscopic video eye movement instrument, wherein the stimulation video is a stereoscopic stimulation video which is designed aiming at ASD (ASD children testing) and accords with the social performance of ASD children diagnosis;
step 4, watching the stimulation video in the step 3 in an unconscious state of the tested child by using a high-definition hidden camera, and synchronously acquiring an eye movement video of the tested child;
step 5, according to the analysis of the intelligent eye movement algorithm, firstly carrying out orbit positioning and standard quantization, then extracting and segmenting pupils and irises by using a deep convolutional neural network on the basis, and finally realizing 3D fitting of eyes so as to realize real-time prediction of sight gaze fixation points; the collected data information of the eye movement video of the detected child obtains the fixation point of each time and the overall sight track of the detected child, and the eye movement information of the child is classified and extracted according to the expert suggestion and compared with a healthy child sample, and finally the ASD probability of the detected child is calculated.
CN201910994949.0A 2019-10-18 2019-10-18 Non-invasive detection and eye movement analysis method for ASD screening Pending CN110786868A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910994949.0A CN110786868A (en) 2019-10-18 2019-10-18 Non-invasive detection and eye movement analysis method for ASD screening

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910994949.0A CN110786868A (en) 2019-10-18 2019-10-18 Non-invasive detection and eye movement analysis method for ASD screening

Publications (1)

Publication Number Publication Date
CN110786868A true CN110786868A (en) 2020-02-14

Family

ID=69439317

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910994949.0A Pending CN110786868A (en) 2019-10-18 2019-10-18 Non-invasive detection and eye movement analysis method for ASD screening

Country Status (1)

Country Link
CN (1) CN110786868A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070177103A1 (en) * 2004-02-04 2007-08-02 Migliaccio Americo A Method and apparatus for three-dimensional video-oculography
WO2008097933A1 (en) * 2007-02-04 2008-08-14 Miralex Systems Incorporated Systems and methods for gaze tracking using multiple images
CN102626304A (en) * 2012-04-19 2012-08-08 重庆大学 Head-mounted wireless video eye tracker
CN108415955A (en) * 2018-02-06 2018-08-17 杭州电子科技大学 A kind of point-of-interest database method for building up based on eye movement blinkpunkt motion track
CN109712710A (en) * 2018-04-26 2019-05-03 南京大学 A kind of infant development obstacle intelligent evaluation method based on three-dimensional eye movement characteristics
US20190298245A1 (en) * 2018-03-29 2019-10-03 Harimata Spolka Z O.O. Method for early diagnosis of autism spectrum disorder in children

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070177103A1 (en) * 2004-02-04 2007-08-02 Migliaccio Americo A Method and apparatus for three-dimensional video-oculography
WO2008097933A1 (en) * 2007-02-04 2008-08-14 Miralex Systems Incorporated Systems and methods for gaze tracking using multiple images
CN102626304A (en) * 2012-04-19 2012-08-08 重庆大学 Head-mounted wireless video eye tracker
CN108415955A (en) * 2018-02-06 2018-08-17 杭州电子科技大学 A kind of point-of-interest database method for building up based on eye movement blinkpunkt motion track
US20190298245A1 (en) * 2018-03-29 2019-10-03 Harimata Spolka Z O.O. Method for early diagnosis of autism spectrum disorder in children
CN109712710A (en) * 2018-04-26 2019-05-03 南京大学 A kind of infant development obstacle intelligent evaluation method based on three-dimensional eye movement characteristics

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
HUYNH-THU 等: "Examination of 3D visual attention in stereoscopic video content", 《PROCEEDINGS OF SPIE》 *
MING JIANG 等: "Learning Visual Attention to Identify People with Autism Spectrum Disorder", 《MING JIANG 等》 *
W W ABBOTT 等: "Ultra low-cost 3D gaze estimation: an intuitive high information throughput complement to direct Brain-Machine-Interfaces", 《JOURNAL OF NEURAL ENGINEERING》 *
刘丹丹: "孤独症谱系障碍儿童眼动特征及诊断价值初步探究", 《中国优秀硕士学位论文全文数据库(电子期刊) 医药卫生科技辑》 *

Similar Documents

Publication Publication Date Title
CN110292378B (en) Depression remote rehabilitation system based on brain wave closed-loop monitoring
WO2020119355A1 (en) Method for evaluating multi-modal emotional understanding capability of patient with autism spectrum disorder
US11659350B1 (en) Metaverse dating
CN109350907B (en) Method and system for testing and training attention deficit hyperactivity disorder of children based on virtual reality
CN110353673B (en) Electroencephalogram channel selection method based on standard mutual information
Vortmann et al. EEG-based classification of internally-and externally-directed attention in an augmented reality paradigm
CN105852831A (en) Equipment based on virtual reality interaction technology and brain function real-time monitoring technology
CA2936343C (en) Systems and methods for diagnosing sleep
Das et al. Stimulus-aware spatial filtering for single-trial neural response and temporal response function estimation in high-density EEG with applications in auditory research
CN110141258A (en) A kind of emotional state detection method, equipment and terminal
Shen et al. Multiscale temporal self-attention and dynamical graph convolution hybrid network for EEG-based stereogram recognition
CN113688710A (en) Child autism training system and method thereof
WO2017136656A1 (en) Methods and systems for identifying non-penetrating brain injuries
CN113408397B (en) Domain-adaptive cross-subject motor imagery electroencephalogram signal identification system and method
Steinert et al. Audio-Visual Recognition of Emotional Engagement of People with Dementia.
Piza et al. The hippocampus of the common marmoset is a GPS, but G is for gaze
CN110801227B (en) Method and system for testing three-dimensional color block obstacle based on wearable equipment
CN112450949A (en) Electroencephalogram signal processing method and system for cognitive rehabilitation training
CN110786868A (en) Non-invasive detection and eye movement analysis method for ASD screening
CN110840467A (en) Correlation analysis method for eye movement data and mental system diseases
Puwakpitiyage et al. A proposed web based real time brain computer interface (BCI) system for usability testing
CN111640496A (en) Traditional Chinese medicine remote consultation system based on artificial intelligence
US20210255706A1 (en) Brain-machine interface based intention determination device and method using virtual environment
CN115659207A (en) Electroencephalogram emotion recognition method and system
CN113974589A (en) Multi-modal behavior paradigm evaluation optimization system and cognitive ability evaluation method

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200214