In a real world visual search is a common task depending from
sensory, perceptual and cognitive processes. Different classes
of eye movements are necessary to hold an image on the retina
during head rotation or movement of the image, and to move
the eye suddenly to a new point of interest in space. From a
functional point of view, two major classes of eye movements
are described in humans: those stabilizing gaze (optokinetic
nystagmus, oculovestibular reflex) and those movinggaze
(saccades, pursuits and vergence). Under natural conditions,
however, a mix of all kinds of eye movements permit
continuous scanning of the visual scene. The sequence of
fixations and saccades during visual exploration isan
expression of a number of cognitive processes; the use of
standardized tasks with pre-defined spatial-temporal variables
allows us to assess specific cognitive domains, such as
perception, attention, memory, preference and motivation.
Manipulating the search task can vary the demands on brain. In
turn, brain modulates visual search by selecting and limiting
the information available at various levels of processing.
The EVA software is a complete system based on a set of
stimulus and patient’s case able to stress brain functionalities in
order to assess some cognitive functions.
Who ever said advanced OCT scanning had to be complicated? When an OCT design puts user experience first, it can be simple to learn and easy to use. So it is with the Optovue iSeries. To be any easier they would have to run themselves—and sometimes they do!
But don’t confuse simplicity with performance. The iSeries systems are fully featured and deliver many exclusive Optovue capabilities such as ganglion cell complex (GCC) analysis with focal loss volume (FLV%) and global loss volume (GLV%) metrics, the iWellnessExam® and the Cornea Advance module, which includes Vault Mapping for specialty lens fitting. The iSeries also benefits from a large, ethnically diverse normative database.
Novel deep learning-powered diagnostics hardware for assessing retinal health.
The impact of deep learning and artificial intelligence for the design practice itself is covered better in https://algorithms.design/ and the focus of this presentation is in the visual function diagnostics.
How is the future looking for your high-street optician's (e.g. Specsavers, Boots) vision exam going beyond simple refraction correction, and how possibly in the future AR glasses could allow design of "smarter" every-day eyewear also for health monitoring.
Talk given for “Future of Eyecare: How we see and how we want to be seen” organized by Flora McLean.
Royal College of Art - London UK
From unimodal image classification to integrative multimodal deep learning pipelines in disease classification, disease management and predictive personalised healthcare.
Who ever said advanced OCT scanning had to be complicated? When an OCT design puts user experience first, it can be simple to learn and easy to use. So it is with the Optovue iSeries. To be any easier they would have to run themselves—and sometimes they do!
But don’t confuse simplicity with performance. The iSeries systems are fully featured and deliver many exclusive Optovue capabilities such as ganglion cell complex (GCC) analysis with focal loss volume (FLV%) and global loss volume (GLV%) metrics, the iWellnessExam® and the Cornea Advance module, which includes Vault Mapping for specialty lens fitting. The iSeries also benefits from a large, ethnically diverse normative database.
Novel deep learning-powered diagnostics hardware for assessing retinal health.
The impact of deep learning and artificial intelligence for the design practice itself is covered better in https://algorithms.design/ and the focus of this presentation is in the visual function diagnostics.
How is the future looking for your high-street optician's (e.g. Specsavers, Boots) vision exam going beyond simple refraction correction, and how possibly in the future AR glasses could allow design of "smarter" every-day eyewear also for health monitoring.
Talk given for “Future of Eyecare: How we see and how we want to be seen” organized by Flora McLean.
Royal College of Art - London UK
From unimodal image classification to integrative multimodal deep learning pipelines in disease classification, disease management and predictive personalised healthcare.
Evaluating Human Visual Search Performance by Monte Carlo methods and Heurist...Giacomo Veneri
Visual search is an everyday activity that enables
humans to explore the real world. Given the visual input,
during a visual search, it’s required to select some aspects of the input in order to move to the next location. Exploration is guided by two factors: saliency of image (bottom-up) and endogenous mechanism (top-down). These two mechanisms interact to perform an efficient visual search. We developed a stochastic model, the ”break away from fixations” (BAF), to emulate the visual search on a high cognitively demanding task such as a trail making test (TMT). The paper reports a case study providing evidence that human exploration performs an efficient visual search based also on an internal model of regions already explored.
Ryan Match Moving For Area Based Analysis Of Eye Movements In Natural TasksKalle
Analysis of recordings made by a wearable eye tracker is complicated by video stream synchronization, pupil coordinate mapping, eye movement analysis, and tracking of dynamic Areas Of Interest (AOIs) within the scene. In this paper a semi-automatic system is developed to help automate these processes. Synchronization is accomplished
via side by side video playback control. A deformable eye template and calibration dot marker allow reliable initialization via simple drag and drop as well as a user-friendly way to correct the algorithm when it fails. Specifically, drift may be corrected by nudging the detected pupil center to the appropriate coordinates. In a case study, the impact of surrogate nature views on physiological health and perceived well-being is examined via analysis of gaze over images of nature. A match-moving methodology was developed to track AOIs for this particular application but is applicable toward similar future studies.
An Eye of technology For the people who suffer with PALS (People with ALS). Amyotrophic lateral sclerosis is a debilitating, neurodegenerative disease. Its various symptoms include dysphagia, dysarthria, respiratory distress, pain, and psychological disorders. It is characterized by progressive muscular paralysis reflecting degeneration of motor neurons, conspiratorial tracts and the spinal cord. Most cases of ALS are readily diagnosed and the error rate of diagnosis in large ALS clinics is less than 10%.
1.2 VISION SYSTEM FOR HUMAN COMMUNICATION
How do you communicate when your brain is active but your body isn't? The Project Oculus, designed to communicate for those who is suffering from ALS, uses low-cost eye-tracking glasses and open-source software to allow people suffering from any kind of neuromuscular syndrome to write and draw by tracking their eye movement and translating it to lines on a screen.
Study the influence of (eye) motor control on selective attention
Develop a method to extract motor control parameters during visual search
Develop a method to extract selective attention features during visual search
Study the influence of (eye) motor control on selective attention
Develop a method to extract motor control parameters during visual search
Develop a method to extract selective attention features during visual search
Mulligan Robust Optical Eye Detection During Head MovementKalle
Finding the eye(s) in an image is a critical rst step in a remote gaze-tracking system with a working volume large enough to encompass head movements occurring during normal user behavior. We briey review an optical method which exploits the retroreective properties of the eye, and present a novel method for combining difference images to reject motion artifacts. Best performance is obtained when a curvatur operator is used to enhance punctate features, and search is restricted to a neighborhood about the last known location. Optimal setting of the size of this neighborhood is aided by a statistical model of naturally-occurring head movements; we present head-movement statistics mined from a corpus of around 800 hours of video, collected in a team-performance experiment.
Spike removal through multiscale wavelet and entropy analysis of ocular motor...Giuseppe Fineschi
Wavelet decomposition of ocular motor signals was investigated with a view to its use for noise analysis and filtering. Ocular motor noise may be physiological, depending on brain activities, or experimental, depending on the eye recording machine, head movements and blinks. Experimental noise, such as spikes, must be removed, preserving noise due to neuro-physiological activities. The proposed method uses wavelet multiscale decomposition to remove spikes and optimizes the procedure by means of the covariance of the eye signals. To measure the noise on eye motor control, we used the wavelet entropy. The method was tested on patients with cerebellar disorders and healthy subjects. A significant difference in wavelet entropy was observed, indicating this quantity as a valuable measure of physiological motor noise.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
THE ROLE OF LATEST FIXATIONS ON ONGOING VISUAL SEARCH Giacomo Veneri
The aim of the study is to understand the selection process, that modulates the exploration mechanism, during the execution of a high cognitively demanding task. The main purpose is to identify the mechanism competition mechanism between top-down and bottom-up. We developed an adaptive system trying to emulate this mechanism.
Walking in Place with Wearable Technology: the development of a system for tr...Karel Van Isacker
Walking in Place with Wearable Technology: the development of a system for travel training and applied travel for people with a visual impairment (Steven Battersby, David Brown and Orly Lahav)
Interactive Technologies and Games (ITAG) Conference 2015
Health, Disability and EducationDates: Thursday 22 October 2015 - Friday 23 October 2015 Location: The Council House, NG1 2DT
Giacomo Veneri Thesis 1999 University of SienaGiacomo Veneri
In proteomics, two dimensional gel electrophoresis (2–DE) is a separation technique for proteins.
Gel electrophoresis is registered and the final digital image is computer analyzed for protein spots finding; the protein spots can be detected by visual inspection of a digital gel image or by image processing algorithm. On computer image analysis, difficulties arise from image noise, spot saturation and irregular geometric distortions.
Aiming at the automated analysis of large series of 2–DE images, the bottleneck is to solve the two most basic algorithmic problems: identifying protein spots and computing the protein spots map in order to compare it to database or different image.
We developed a robust Analysis of Variance (ANOVA) based algorithm able to excite spot in order to be easy found and separated by classic algorithm as edge detection or watershed.
Industrial IoT - build your industry 4.0 @techitalyGiacomo Veneri
Explore industrial processes, devices, and protocols
Design and implement the I-IoT network flow
Gather and transfer industrial data in a secure way
Get to grips with popular cloud-based platforms
Understand diagnostic analytics to answer critical workforce questions
Discover the Edge device and understand Edge and Fog computing
Implement equipment and process management to achieve business-specific goals
The eye gaze analysis represents a challenging field of
research, since it offers a reproducible method to study the mechanisms of the brain. Eye movements are arguably the most frequent of all human movements and an essential part of human vision: they drive the fovea and consequently, the attention towards regions of interest in space. This enables the visual system to fixate and to process an image or its details with high resolution: act of fixation. This chapter investigates some common techniques and algorithms to study human vision.
More Related Content
Similar to EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
Evaluating Human Visual Search Performance by Monte Carlo methods and Heurist...Giacomo Veneri
Visual search is an everyday activity that enables
humans to explore the real world. Given the visual input,
during a visual search, it’s required to select some aspects of the input in order to move to the next location. Exploration is guided by two factors: saliency of image (bottom-up) and endogenous mechanism (top-down). These two mechanisms interact to perform an efficient visual search. We developed a stochastic model, the ”break away from fixations” (BAF), to emulate the visual search on a high cognitively demanding task such as a trail making test (TMT). The paper reports a case study providing evidence that human exploration performs an efficient visual search based also on an internal model of regions already explored.
Ryan Match Moving For Area Based Analysis Of Eye Movements In Natural TasksKalle
Analysis of recordings made by a wearable eye tracker is complicated by video stream synchronization, pupil coordinate mapping, eye movement analysis, and tracking of dynamic Areas Of Interest (AOIs) within the scene. In this paper a semi-automatic system is developed to help automate these processes. Synchronization is accomplished
via side by side video playback control. A deformable eye template and calibration dot marker allow reliable initialization via simple drag and drop as well as a user-friendly way to correct the algorithm when it fails. Specifically, drift may be corrected by nudging the detected pupil center to the appropriate coordinates. In a case study, the impact of surrogate nature views on physiological health and perceived well-being is examined via analysis of gaze over images of nature. A match-moving methodology was developed to track AOIs for this particular application but is applicable toward similar future studies.
An Eye of technology For the people who suffer with PALS (People with ALS). Amyotrophic lateral sclerosis is a debilitating, neurodegenerative disease. Its various symptoms include dysphagia, dysarthria, respiratory distress, pain, and psychological disorders. It is characterized by progressive muscular paralysis reflecting degeneration of motor neurons, conspiratorial tracts and the spinal cord. Most cases of ALS are readily diagnosed and the error rate of diagnosis in large ALS clinics is less than 10%.
1.2 VISION SYSTEM FOR HUMAN COMMUNICATION
How do you communicate when your brain is active but your body isn't? The Project Oculus, designed to communicate for those who is suffering from ALS, uses low-cost eye-tracking glasses and open-source software to allow people suffering from any kind of neuromuscular syndrome to write and draw by tracking their eye movement and translating it to lines on a screen.
Study the influence of (eye) motor control on selective attention
Develop a method to extract motor control parameters during visual search
Develop a method to extract selective attention features during visual search
Study the influence of (eye) motor control on selective attention
Develop a method to extract motor control parameters during visual search
Develop a method to extract selective attention features during visual search
Mulligan Robust Optical Eye Detection During Head MovementKalle
Finding the eye(s) in an image is a critical rst step in a remote gaze-tracking system with a working volume large enough to encompass head movements occurring during normal user behavior. We briey review an optical method which exploits the retroreective properties of the eye, and present a novel method for combining difference images to reject motion artifacts. Best performance is obtained when a curvatur operator is used to enhance punctate features, and search is restricted to a neighborhood about the last known location. Optimal setting of the size of this neighborhood is aided by a statistical model of naturally-occurring head movements; we present head-movement statistics mined from a corpus of around 800 hours of video, collected in a team-performance experiment.
Spike removal through multiscale wavelet and entropy analysis of ocular motor...Giuseppe Fineschi
Wavelet decomposition of ocular motor signals was investigated with a view to its use for noise analysis and filtering. Ocular motor noise may be physiological, depending on brain activities, or experimental, depending on the eye recording machine, head movements and blinks. Experimental noise, such as spikes, must be removed, preserving noise due to neuro-physiological activities. The proposed method uses wavelet multiscale decomposition to remove spikes and optimizes the procedure by means of the covariance of the eye signals. To measure the noise on eye motor control, we used the wavelet entropy. The method was tested on patients with cerebellar disorders and healthy subjects. A significant difference in wavelet entropy was observed, indicating this quantity as a valuable measure of physiological motor noise.
The International Journal of Engineering & Science is aimed at providing a platform for researchers, engineers, scientists, or educators to publish their original research results, to exchange new ideas, to disseminate information in innovative designs, engineering experiences and technological skills. It is also the Journal's objective to promote engineering and technology education. All papers submitted to the Journal will be blind peer-reviewed. Only original articles will be published.
THE ROLE OF LATEST FIXATIONS ON ONGOING VISUAL SEARCH Giacomo Veneri
The aim of the study is to understand the selection process, that modulates the exploration mechanism, during the execution of a high cognitively demanding task. The main purpose is to identify the mechanism competition mechanism between top-down and bottom-up. We developed an adaptive system trying to emulate this mechanism.
Walking in Place with Wearable Technology: the development of a system for tr...Karel Van Isacker
Walking in Place with Wearable Technology: the development of a system for travel training and applied travel for people with a visual impairment (Steven Battersby, David Brown and Orly Lahav)
Interactive Technologies and Games (ITAG) Conference 2015
Health, Disability and EducationDates: Thursday 22 October 2015 - Friday 23 October 2015 Location: The Council House, NG1 2DT
Giacomo Veneri Thesis 1999 University of SienaGiacomo Veneri
In proteomics, two dimensional gel electrophoresis (2–DE) is a separation technique for proteins.
Gel electrophoresis is registered and the final digital image is computer analyzed for protein spots finding; the protein spots can be detected by visual inspection of a digital gel image or by image processing algorithm. On computer image analysis, difficulties arise from image noise, spot saturation and irregular geometric distortions.
Aiming at the automated analysis of large series of 2–DE images, the bottleneck is to solve the two most basic algorithmic problems: identifying protein spots and computing the protein spots map in order to compare it to database or different image.
We developed a robust Analysis of Variance (ANOVA) based algorithm able to excite spot in order to be easy found and separated by classic algorithm as edge detection or watershed.
Industrial IoT - build your industry 4.0 @techitalyGiacomo Veneri
Explore industrial processes, devices, and protocols
Design and implement the I-IoT network flow
Gather and transfer industrial data in a secure way
Get to grips with popular cloud-based platforms
Understand diagnostic analytics to answer critical workforce questions
Discover the Edge device and understand Edge and Fog computing
Implement equipment and process management to achieve business-specific goals
The eye gaze analysis represents a challenging field of
research, since it offers a reproducible method to study the mechanisms of the brain. Eye movements are arguably the most frequent of all human movements and an essential part of human vision: they drive the fovea and consequently, the attention towards regions of interest in space. This enables the visual system to fixate and to process an image or its details with high resolution: act of fixation. This chapter investigates some common techniques and algorithms to study human vision.
Bayesain Hypothesis of Selective Attention - Raw 2011 posterGiacomo Veneri
The aim of the study is to understand the process of target averaging during the selection process. We analyzed the probability to select the target after a fixation outside ROIs from the duration of fixations and the distance to the target. We aimed to respond to the question “is it possible to predict the selected area?” . In this study we tested the presence of information in non-ROI fixation data about the occurrence of a target at the next saccade. A classification algorithm was trained to predict the target vs. non-target outcome (dependent variable) of a saccade from summary statistics of fixation data (covariates). We claim that significantly accurate predictions are substantial evidence to support the hypothesis of "presence of information".
Raw 2009 -THE ROLE OF LATEST FIXATIONS ON ONGOING VISUAL SEARCH A MODEL TO E...Giacomo Veneri
The aim of the study is to understand the selection process, that modulates the exploration mechanism, during the execution of a high cognitively demanding task. The main purpose is to identify the mechanism competition mechanism between top-down and bottom-up. We developed an adaptive system trying to emulate this mechanism.
In proteomics, two dimensional gel electrophoresis (2–DE) is a separation technique for proteins.
Gel electrophoresis is registered and the final digital image is computer analyzed for protein spots finding; the protein spots can be detected by visual inspection of a digital gel image or by image processing algorithm. On computer image analysis, difficulties arise from image noise, spot saturation and irregular geometric distortions.
Aiming at the automated analysis of large series of 2–DE images, the bottleneck is to solve the two most basic algorithmic problems: identifying protein spots and computing the protein spots map in order to compare it to database or different image.
We developed a robust Analysis of Variance (ANOVA) based algorithm able to excite spot in order to be easy found and separated by classic algorithm as edge detection or watershed. The implementation is done in a client standalone application called VisualBio.
Synthetic Fiber Construction in lab .pptxPavel ( NSTU)
Synthetic fiber production is a fascinating and complex field that blends chemistry, engineering, and environmental science. By understanding these aspects, students can gain a comprehensive view of synthetic fiber production, its impact on society and the environment, and the potential for future innovations. Synthetic fibers play a crucial role in modern society, impacting various aspects of daily life, industry, and the environment. ynthetic fibers are integral to modern life, offering a range of benefits from cost-effectiveness and versatility to innovative applications and performance characteristics. While they pose environmental challenges, ongoing research and development aim to create more sustainable and eco-friendly alternatives. Understanding the importance of synthetic fibers helps in appreciating their role in the economy, industry, and daily life, while also emphasizing the need for sustainable practices and innovation.
Francesca Gottschalk - How can education support child empowerment.pptxEduSkills OECD
Francesca Gottschalk from the OECD’s Centre for Educational Research and Innovation presents at the Ask an Expert Webinar: How can education support child empowerment?
Acetabularia Information For Class 9 .docxvaibhavrinwa19
Acetabularia acetabulum is a single-celled green alga that in its vegetative state is morphologically differentiated into a basal rhizoid and an axially elongated stalk, which bears whorls of branching hairs. The single diploid nucleus resides in the rhizoid.
Model Attribute Check Company Auto PropertyCeline George
In Odoo, the multi-company feature allows you to manage multiple companies within a single Odoo database instance. Each company can have its own configurations while still sharing common resources such as products, customers, and suppliers.
Biological screening of herbal drugs: Introduction and Need for
Phyto-Pharmacological Screening, New Strategies for evaluating
Natural Products, In vitro evaluation techniques for Antioxidants, Antimicrobial and Anticancer drugs. In vivo evaluation techniques
for Anti-inflammatory, Antiulcer, Anticancer, Wound healing, Antidiabetic, Hepatoprotective, Cardio protective, Diuretics and
Antifertility, Toxicity studies as per OECD guidelines
A Strategic Approach: GenAI in EducationPeter Windle
Artificial Intelligence (AI) technologies such as Generative AI, Image Generators and Large Language Models have had a dramatic impact on teaching, learning and assessment over the past 18 months. The most immediate threat AI posed was to Academic Integrity with Higher Education Institutes (HEIs) focusing their efforts on combating the use of GenAI in assessment. Guidelines were developed for staff and students, policies put in place too. Innovative educators have forged paths in the use of Generative AI for teaching, learning and assessments leading to pockets of transformation springing up across HEIs, often with little or no top-down guidance, support or direction.
This Gasta posits a strategic approach to integrating AI into HEIs to prepare staff, students and the curriculum for an evolving world and workplace. We will highlight the advantages of working with these technologies beyond the realm of teaching, learning and assessment by considering prompt engineering skills, industry impact, curriculum changes, and the need for staff upskilling. In contrast, not engaging strategically with Generative AI poses risks, including falling behind peers, missed opportunities and failing to ensure our graduates remain employable. The rapid evolution of AI technologies necessitates a proactive and strategic approach if we are to remain relevant.
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
1. EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI
AUTOMATIC CASE
BASE SYSTEM
EYE TRACKING & VISION APPLICATIONS LAB (EVA
LAB) – DEPARTMENT OF NEUROLOGICAL
NEUROSURGICAL AND BEHAVIORAL SCIENCE –
UNIVERSITY OF SIENA
Giacomo Veneri, Pamela Federighi, Elena Pretegiani, Francesca Rosini, Nicola R Polizzotto, Francesco Fragnoli,
Emiliano Santarnecchi, Giacomo DeMurtas, Antonio Federico & Alessandra Rufa
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
2. EVA Light System
2
EVA
EYE TRACKING -
STIMULUS
INTEGRATED SEMI
AUTOMATIC CASE
BASESYSTEM
To test the cognitive
system by multi-stimulus
Diagnosis by Case Base
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
3. Summary
3
Background (2m) Analysis (5m)
Testing Saccade: Velocity,Amplitude
the cognitive
functionalities by gaze Duration, Latency, Error
Fixation: dispersion
Stimulus Architecture (5m)
Task: sequencing
Saccadic Behavior
Decision Making
Visual Search
Results (5m)
Gaze Contingent
TMS Interference Case Base (1m)
Sound integration and
joystick
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
4. Background
4
“BY TESTING THE RESPONSE TO VISUAL STIMULI WE CAN TEST
MORE THAN 60% OF BRAIN ACTIVITY”
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI
AUTOMATIC CASE BASE SYSTEM 01/07/13
5. Vision
5
“More 60% of our Barin
works on vision …”:
Image Processing
Spatial Attention
Working memory
Memory
Visual-Spatial exploration
Eye Movement Command
Decision Making The focus of attention is jointly determined by stimulus
salience and top-down control signals. IOR is implemented by
a mechanism that reduces the salience of stimuli at recently
explored spatial locations.
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
6. Eye Movement & Attention
6
Eye movements
Sequences of fixation and
saccade
The sequences of saccade-
and-fixation enable humans
to receive a continuous flow
of information from the world. Peripheral attention
Saccadic eye movements
Attention
Overlapped region
Attention is the process of
selecting a few relevant
perceptive stimuli by filtering
of negligible aspect of the
environment
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
7. Working Memory & Visual Search
7
Visual working memory :
is a theoretical construct
that refers to the
structures and processes
used for temporarily
storing and manipulating
visual information.
information
Visual Search
memory maintains the
information in order to
allow past experience to
guide future behaviors
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
8. Decision making
8
Decision making:
can be regarded as an
outcome of mental
processes (cognitive
process) leading to the
selection of a course of
action among several
alternatives.
Basic connectivity framework. Dotted arrows represent external
inputs to the model. Abbreviations: 5-HT, dorsal raphe
serotonergic neurons; ACC, anterior cingulate cortex; AMYG,
amygdala; DA, midbrain dopaminergic neurons; DLPFC,
dorsolateral prefrontal cortex; OFC, orbitofrontal cortex; VS,
ventral striatum.
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
9. The Main Idea: 3 steps
9
1. To develop a multistimlus
system able to stress some
part and functionalities of
brain in order to make a low
cost pre-diagnosis of patient.
1. Interference: TMS, sound
2. Sensory stimulus: video, audio
3. Output: Eyetracking, joystick
2. To develop indicators from
specific task in order to test
the brain response.
3. To develop a database of
case which can suggest
dignosis avoiding any euristic
or expert system logic.
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
10. Preview: clinical case & research case
10
Clinical case
Patients with movement disorder including cerebellar patients.
Neo Cortex injury.
Neglect patients (parietal abnormalities).
Frontal prefrontal lesions
Pre and post pharmacological assumption.
Deficit on attention & dyslexic patients.
Research case
Temporary interference by TMS
Decision Making (NeuroEconomy – Dept. Economic)
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
11. Task
11
SACCADES, MEMORY GUIDED Saccade, TMT, SOUND GUIDED
visual exploration or saccades, GAZE CONTINGENT, FACE
ANALYSIS, GAME THEORY.
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI
AUTOMATIC CASE BASE SYSTEM 01/07/13
12. Stimulus System
12
Saccade Visual Search: time line
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
13. Saccade / Anti saccade / Memory guided
13
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
14. Trail Making Task
14
Visual Search depends on
sensory, perceptual and
cognitive processes
TMTB is used to measure
the cognitive domains of
processing speed,
sequencing, visual search
abilities and visual-motor
skills.
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
15. Gaze Contingent
15
Reactive gaze-contingent
display (GCD), which
uses a simple hole
forcing only foveal vision
during exploration by
blinding peripheral vision,
in order to test and
stress overt mechanisms
of visual search in
normal subjects and
clinical contexts
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
16. Decision Making
16
Game Theory
The subject was asked
to choose between two
sign according to
previous chooses
Overconfident
Bayesian
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
17. Analysis
17
INDICATORS
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
18. Features
18
Common New
Saccades Saccades
Velocity Peak
Going from/in ROI
Mean Velocity
Time
Fixations Delta time among ROI
N° fixations in ROI
(step to step time)
Fixations Duration
Errors
Time
ROI re-exploration
Task duration
Sequencing 1 2
Time in ROI
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
19. Algorithms
19
Signal processing
Spurious data purging
Saccade detection
Fixations identification
Visual Search indicator
Best Squence [BestSequenceAlgorithm]
Fixations distance
8PS Model
Decision Indicator
Likelihood function
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
20. Best Sequence Algorithm
20
Is a tree exploration
algorithm that extract the
Sequencing Index as an
indicator of the ability in
gazing correctly a logic
sequence
Subject 1:
O1A2B3C4BD5EE5O5A1
AB52
Patient 1:
O13C4BD5E2ABE5OAE1
A12B
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
21. SCA2 (subject 1) vs CTRL (subject 2)
21
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
22. Fixation Distance From ROI
22
The distance from
nearest ROI
It’s an indicator of fixation
dispersion during visual
exploration
fs (xf,yf))**minROI ((δ((xf,yf), (xr,yr)))
fs (xf,yf minROI δ((xf,yf), (xr,yr)))
The distance from target
It’s an indicator of goal
directed visual exploration
fs (xf,yf))**((δ((xf,yf), (xr r(t+1),yr r(t+1))))
fs (xf,yf δ((xf,yf), (x (t+1),y (t+1))))
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
23. 8Pointed Star -Model
23
Direction Error (ε*) = (direction observed (ο*) – expected (η*) )
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
24. Ongoing Search abilities
24
Direction error may
provide a quantitative
assessment of the
visual search strategy
provides an
estimation of the
ongoing visual search
capabilities.
Δεε*= εεt*t-- εε*t-1
Δ* = * *
t-1
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
Using Simplified Trial Making Test B to Evaluate Ongoing Learning Capabilities on Visual Search
01/07/13
25. Upcoming direction versus previous fixations
25
The forthcoming
direction minus the
minimum/maximum
distribution of fixation
(ο*)) – min(direction(fixations))
(ο* – min(direction(fixations))
It’s an expression to plan
the saccade far from
visited location (fixated)
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
26. Decision: likelihood function
26
Likelihood function was expressed as the probability
that a subject spends more time looking the object
which will be choose during the last 3 seconds
preceding the explicit decision.
Time on sign / /Time total elapsed
Time on sign Time total elapsed
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
27. Results
27
PATIENTS & SUBJECTS
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI
AUTOMATIC CASE BASE SYSTEM 01/07/13
28. Movement Disorder Saccade Analysis
28
Saccade Cerebellar patients
Three group were analyzed
600
Control (healthy subject)
500
SCA2 (Autosomal Dominant
400
Cerebellar Atrophiy)
pCA (Autosomal Recessive
300 CTRL
pCA
Pure Cerebellar Atrophy)
SCA2
200
Significant differences were
found on
100
Peak Velocity, Duration. Amplitude
Gain
0
10° 18°
Peak Velocity (°/s)
20° 10° 18°
Mean Velocity (°/s)
20° 10° 18°
Duration (s)
20°
Error
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
29. Visual Search TMT Analysis
29
Fixation Cerebellar patients
Three group were analyzed
Control (healthy subject)
SCA2 (Autosomal Dominant
Cerebellar Atrophiy)
Fixation dispersion
pCA (Autosomal Recessive
Pure Cerebellar Atrophy)
Significative differences
were found on
Sequencing ability
Fixation distances
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
30. Visual Search: gaze contingent analysis
30
TMT Fixation
Two group were analyzed
Control (healthy subject)
FV (foveate vision inhibited by
gaze contingent)
Significant differences were
found on
Fixations dinstance
Revisited ROI
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
31. Decision Making Analysis
31
20 subjects were asked to take a decision in a game
theory context
Overconfident subjects confirmed the theory that “gaze is
a renforcement of decision and vice-versa”
bayesiani overconfident
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
32. direction versus previous fixations
32
40 subjects
Distance from previous fixations increase on the last
800ms
Distance from unexplored region decreases on the last
800ms
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
33. Case Based System
33
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI
AUTOMATIC CASE BASE SYSTEM 01/07/13
34. System Analysis
34
Ca ree
Ca ee
Tr
se
T
se
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
35. Analysis System
35
Time Saccade Analysis Main Sequence
Visual Search Analysis
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
36. Case Base
36
The case base look for the N cases nearest to the current case according to the
previous indicators
Euclidean distance
Mahalanobis distance
Case Base suggests diagnosis
The case base actually works on 82 subjects
Case Base
New Patient
indicators
Diagnosis
Diagnosis
Diagnosis
Diagnosis
indicators Diagnosis
Diagnosis
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
37. 37
Case Base
Analysis
(Indicators)
Diagnosis
Vision Cognitive
Task
Rehabilitation
STIMULUS INTEGRATED SEMI
AUTOMATIC CASE BASE SYSTEM
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
38. Further Work
38
To extend the case base with:
Degenerative brain diseases
Movement disorders
Attention deficit
Developing new indicators in order to find saccadic
intrusion and micro-saccade
Developing new indicators (markov chain) in order to
evaluate decision
Improve the search algorithm using Genetic
algorithm
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena
EVA – EYE TRACKING - STIMULUS INTEGRATED SEMI AUTOMATIC CASE BASE SYSTEM
01/07/13
39. EVA Lab
ALESSANDRA RUFA (MD PhD),
GIACOMO VENERI (MSC),
PAMELA FEDERIGHI (MSC),
ELENA PRETEGIANI(MD),
FRANCESCA ROSINI (MD),
NICOLA R. POLIZZOTTO (MD),
EMILIANO SANTARNECCHI (PhD),
FRANCESCO FRAGNOLI (MD)
GIACOMO DE MURTAS (MSC),
ANTONIO FEDERICO (MD)
www.evalab.unisi.it – visionlab@unisi.it
Eye tracking & Vision Applications Lab (EVA Lab) – Department of Neurological Neurosurgical and Behavioral Science – University of Siena