Yun Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yun Zhao has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Levin Kuhlmann
Monash University
6 shared publications - Philippa Jane Karoly
The University of Melbourne
4 shared publications Yueyang Liu
Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University
4 shared publicationsAndria Pelentritou
Laboratoire de Recherche en Neuroimagerie (LREN), University Hospital (CHUV) and University of Lausanne (UNIL)
3 shared publications- David Bruce Grayden
Department of Biomedical Engineering, University of Melbourne
3 shared publications David Liley
School of Health Sciences, Swinburne University of Technology
3 shared publications
Latest Publications
- 17 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (08) , 2650021
Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics
Recently, automated Interictal Epileptiform Discharge (IED) detection has attracted significant attention as a challenging predictive data analysis task aimed at improving early epilepsy diagnosis. Automated IED detection simplifies visual inspection and assists clinicians in identifying crucial IED waveform patterns in Electroencephalographic (EEG) brain activities. However, IEDs are vastly outnumbered by non-IED or background data, directly training on such data leads to a detrimental impact on model performance. Moreover, most existing methods lack high precision when tested on cross-institution datasets and this will lead to time wasted by the neurologist having to look at predicted IEDs that are not IEDs. To address these issues, we propose a novel approach that employs probabilistic diffusion models for data augmentation alongside Area Under the Precision–Recall Curve (AUPRC) maximization methods. This approach effectively addresses data scarcity and imbalance by combining real and synthesized IEDs to fully balance the training dataset, resulting in a 4.5% increase in precision and a 0.7% improvement in the F1-score during within-data evaluation. Additionally, it proves to be robust and generalizable, as evidenced by a 40.04% and 18.74% enhancement in precision and F1-score when applied to cross-data evaluation using data from another hospital.
- 17 April 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 36 (08) , 2650021
Interictal Epileptiform Discharge Detection Through Probabilistic Diffusion Models with Maximization of Precision Recall Metrics
Recently, automated Interictal Epileptiform Discharge (IED) detection has attracted significant attention as a challenging predictive data analysis task aimed at improving early epilepsy diagnosis. Automated IED detection simplifies visual inspection and assists clinicians in identifying crucial IED waveform patterns in Electroencephalographic (EEG) brain activities. However, IEDs are vastly outnumbered by non-IED or background data, directly training on such data leads to a detrimental impact on model performance. Moreover, most existing methods lack high precision when tested on cross-institution datasets and this will lead to time wasted by the neurologist having to look at predicted IEDs that are not IEDs. To address these issues, we propose a novel approach that employs probabilistic diffusion models for data augmentation alongside Area Under the Precision–Recall Curve (AUPRC) maximization methods. This approach effectively addresses data scarcity and imbalance by combining real and synthesized IEDs to fully balance the training dataset, resulting in a 4.5% increase in precision and a 0.7% improvement in the F1-score during within-data evaluation. Additionally, it proves to be robust and generalizable, as evidenced by a 40.04% and 18.74% enhancement in precision and F1-score when applied to cross-data evaluation using data from another hospital.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (7) , 1
Generative Consistency Models for Estimation of Kinetic Parametric Image Posteriors in Total-Body PET
Dynamic total body positron emission tomography (TB-PET) makes it feasible to measure the kinetics of the tracer in all organs of the body simultaneously which may lead to important applications in multi-organ disease and systems physiology. Since whole-body kinetics are highly heterogeneous with variable signal-to-noise ratios, parametric images should ideally comprise not only point estimates but also measures of posterior statistical uncertainty. However, standard Bayesian techniques, such as Markov chain Monte Carlo (MCMC), are computationally prohibitive at the total body scale. We introduce a generative consistency model (CM) that generates samples from the posterior distributions of the kinetic model parameters given measured time-activity curves and arterial input function. CM is able to collapse the hundreds of iterations required by standard diffusion models into just 3 denoising steps. The CM was evaluated using physiologically realistic simulations and an application to a subject's dynamic [18F]FDG TB-PET dataset analyzed with a standard single-input two-tissue compartment model. When trained on 500,000 physiologically realistic two-tissue compartment model simulations, the CM produces similar accuracy to MCMC (median absolute percent error < 5%; median K-L divergence < 0.5) but is more than five orders of magnitude faster. CM produces more reliable Ki images than the Patlak method by avoiding the assumption of irreversibility, while also offering valuable information on statistical uncertainty of parameter estimates and the underlying model. The proposed framework removes the computational barrier to routine, fully Bayesian parametric imaging in TB-PET and is readily extensible to other tracers and compartment models.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (7) , 1
Open AccessGenerative Consistency Models for Estimation of Kinetic Parametric Image Posteriors in Total-Body PET
Dynamic total body positron emission tomography (TB-PET) makes it feasible to measure the kinetics of the tracer in all organs of the body simultaneously which may lead to important applications in multi-organ disease and systems physiology. Since whole-body kinetics are highly heterogeneous with variable signal-to-noise ratios, parametric images should ideally comprise not only point estimates but also measures of posterior statistical uncertainty. However, standard Bayesian techniques, such as Markov chain Monte Carlo (MCMC), are computationally prohibitive at the total body scale. We introduce a generative consistency model (CM) that generates samples from the posterior distributions of the kinetic model parameters given measured time-activity curves and arterial input function. CM is able to collapse the hundreds of iterations required by standard diffusion models into just 3 denoising steps. The CM was evaluated using physiologically realistic simulations and an application to a subject's dynamic [18F]FDG TB-PET dataset analyzed with a standard single-input two-tissue compartment model. When trained on 500,000 physiologically realistic two-tissue compartment model simulations, the CM produces similar accuracy to MCMC (median absolute percent error < 5%; median K-L divergence < 0.5) but is more than five orders of magnitude faster. CM produces more reliable Ki images than the Patlak method by avoiding the assumption of irreversibility, while also offering valuable information on statistical uncertainty of parameter estimates and the underlying model. The proposed framework removes the computational barrier to routine, fully Bayesian parametric imaging in TB-PET and is readily extensible to other tracers and compartment models.
- Open Access
- 27 May 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (3) , 036021
Cortical stability and chaos during focal seizures: insights from inference-based modeling
Objective. Epilepsy affects millions globally, with a significant subset of patients suffering from drug-resistant focal seizures. Understanding the underlying neurodynamics of seizure initiation and propagation is crucial for advancing treatment and diagnostics. In this study, we present a novel, inference-based approach for analyzing the temporal evolution of cortical stability and chaos during focal epileptic seizures. Approach. Utilizing a multi-region neural mass model, we estimate time-varying synaptic connectivity from intracranial electroencephalography (iEEG) data collected from individuals with drug-resistant focal epilepsy. Main results. Our analysis reveals distinct preictal and ictal phases characterized by shifts in cortical stability, heightened chaos in the ictal phase, and highlight the critical role of inter-regional communication in driving chaotic cortical behaviour. We demonstrate that cortical dynamics are consistently destabilized prior to seizure onset, with a transient reduction in instability at seizure onset, followed by a significant increase throughout the seizure. Significance. This work provides new insights into the mechanisms of seizure generation and offers potential biomarkers for predicting seizure events. Our findings pave the way for innovative therapeutic strategies targeting cortical stability and chaos to manage epilepsy.
- 27 May 2025
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (3) , 036021
Open AccessCortical stability and chaos during focal seizures: insights from inference-based modeling
Objective. Epilepsy affects millions globally, with a significant subset of patients suffering from drug-resistant focal seizures. Understanding the underlying neurodynamics of seizure initiation and propagation is crucial for advancing treatment and diagnostics. In this study, we present a novel, inference-based approach for analyzing the temporal evolution of cortical stability and chaos during focal epileptic seizures. Approach. Utilizing a multi-region neural mass model, we estimate time-varying synaptic connectivity from intracranial electroencephalography (iEEG) data collected from individuals with drug-resistant focal epilepsy. Main results. Our analysis reveals distinct preictal and ictal phases characterized by shifts in cortical stability, heightened chaos in the ictal phase, and highlight the critical role of inter-regional communication in driving chaotic cortical behaviour. We demonstrate that cortical dynamics are consistently destabilized prior to seizure onset, with a transient reduction in instability at seizure onset, followed by a significant increase throughout the seizure. Significance. This work provides new insights into the mechanisms of seizure generation and offers potential biomarkers for predicting seizure events. Our findings pave the way for innovative therapeutic strategies targeting cortical stability and chaos to manage epilepsy.
- Open Access
Cortical connectivity, local dynamics and stability correlates of global conscious states
Consciousness emerges from complex neural processes, yet its precise neurobiological correlates remain uncertain. Here a space-time-resolved inference-based framework is applied to estimate the neurophysiological variables of a wholecortex model and analyze the neural mechanism correlates of global consciousness by way of a correlation analysis between behavioural and neural variable time-series. Using magnetoencephalography (MEG) data from 15 participants under Xenon-induced anesthesia, interconnected neural mass models (NMMs) were developed and time-evolving regional neurophysiological variables and inter-regional connectivity strengths were inferred from the data. Analyses revealed significant correlations between consciousness levels and inter-regional connectivity, particularly in posterior parietal, occipital, and prefrontal regions. Moreover, results support a parietal, rather than frontal, network backbone to facilitate global consciousness. Regional-level analyses further identified correlates of consciousness within the posterior parietal and occipital regions. Lastly, reductions in consciousness were linked to stabilized cortical dynamics, reflected by changes in the eigenmodes of the system. This framework provides a novel, inference-based approach to investigating consciousness, offering a time-resolved perspective on neural mechanism correlates during altered states.
Open AccessCortical connectivity, local dynamics and stability correlates of global conscious states
Consciousness emerges from complex neural processes, yet its precise neurobiological correlates remain uncertain. Here a space-time-resolved inference-based framework is applied to estimate the neurophysiological variables of a wholecortex model and analyze the neural mechanism correlates of global consciousness by way of a correlation analysis between behavioural and neural variable time-series. Using magnetoencephalography (MEG) data from 15 participants under Xenon-induced anesthesia, interconnected neural mass models (NMMs) were developed and time-evolving regional neurophysiological variables and inter-regional connectivity strengths were inferred from the data. Analyses revealed significant correlations between consciousness levels and inter-regional connectivity, particularly in posterior parietal, occipital, and prefrontal regions. Moreover, results support a parietal, rather than frontal, network backbone to facilitate global consciousness. Regional-level analyses further identified correlates of consciousness within the posterior parietal and occipital regions. Lastly, reductions in consciousness were linked to stabilized cortical dynamics, reflected by changes in the eigenmodes of the system. This framework provides a novel, inference-based approach to investigating consciousness, offering a time-resolved perspective on neural mechanism correlates during altered states.
- Open Access
Inference-based time-resolved cortical stability and chaos analysis for focal epileptic seizures
Epilepsy affects millions globally, with a significant subset of patients suffering from drug-resistant focal seizures. Understanding the underlying neurodynamics of seizure initiation and propagation is crucial for advancing treatment and diagnostics. In this study, we present a novel, inference-based approach for analyzing the temporal evolution of cortical stability and chaos during focal epileptic seizures. Utilizing a multi-region neural mass model, we estimate time-varying synaptic connectivity from intracranial electroencephalography (iEEG) data collected from individuals with drug-resistant focal epilepsy. Our analysis reveals distinct preictal and ictal phases characterized by shifts in cortical stability, heightened chaos in the ictal phase, and highlight the critical role of inter-regional communication in driving chaotic cortical behaviour. We demonstrate that cortical dynamics are consistently destabilized prior to seizure onset, with a transient reduction in instability at seizure onset, followed by a significant increase throughout the seizure. This work provides new insights into the mechanisms of seizure generation and offers potential biomarkers for predicting seizure events. Our findings pave the way for innovative therapeutic strategies targeting cortical stability and chaos to manage epilepsy.
Open AccessInference-based time-resolved cortical stability and chaos analysis for focal epileptic seizures
Epilepsy affects millions globally, with a significant subset of patients suffering from drug-resistant focal seizures. Understanding the underlying neurodynamics of seizure initiation and propagation is crucial for advancing treatment and diagnostics. In this study, we present a novel, inference-based approach for analyzing the temporal evolution of cortical stability and chaos during focal epileptic seizures. Utilizing a multi-region neural mass model, we estimate time-varying synaptic connectivity from intracranial electroencephalography (iEEG) data collected from individuals with drug-resistant focal epilepsy. Our analysis reveals distinct preictal and ictal phases characterized by shifts in cortical stability, heightened chaos in the ictal phase, and highlight the critical role of inter-regional communication in driving chaotic cortical behaviour. We demonstrate that cortical dynamics are consistently destabilized prior to seizure onset, with a transient reduction in instability at seizure onset, followed by a significant increase throughout the seizure. This work provides new insights into the mechanisms of seizure generation and offers potential biomarkers for predicting seizure events. Our findings pave the way for innovative therapeutic strategies targeting cortical stability and chaos to manage epilepsy.
- Open Access
- 1 June 2023
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 20 (3) , 036024
Brain model state space reconstruction using an LSTM neural network
Objective. Kalman filtering has previously been applied to track neural model states and parameters, particularly at the scale relevant to electroencephalography (EEG). However, this approach lacks a reliable method to determine the initial filter conditions and assumes that the distribution of states remains Gaussian. This study presents an alternative, data-driven method to track the states and parameters of neural mass models (NMMs) from EEG recordings using deep learning techniques, specifically a long short-term memory (LSTM) neural network. Approach. An LSTM filter was trained on simulated EEG data generated by a NMM using a wide range of parameters. With an appropriately customised loss function, the LSTM filter can learn the behaviour of NMMs. As a result, it can output the state vector and parameters of NMMs given observation data as the input. Main results. Test results using simulated data yielded correlations with R squared of around 0.99 and verified that the method is robust to noise and can be more accurate than a nonlinear Kalman filter when the initial conditions of the Kalman filter are not accurate. As an example of real-world application, the LSTM filter was also applied to real EEG data that included epileptic seizures, and revealed changes in connectivity strength parameters at the beginnings of seizures. Significance. Tracking the state vector and parameters of mathematical brain models is of great importance in the area of brain modelling, monitoring, imaging and control. This approach has no need to specify the initial state vector and parameters, which is very difficult to do in practice because many of the variables being estimated cannot be measured directly in physiological experiments. This method may be applied using any NMM and, therefore, provides a general, novel, efficient approach to estimate brain model variables that are often difficult to measure.
- 1 June 2023
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 20 (3) , 036024
Open AccessBrain model state space reconstruction using an LSTM neural network
Objective. Kalman filtering has previously been applied to track neural model states and parameters, particularly at the scale relevant to electroencephalography (EEG). However, this approach lacks a reliable method to determine the initial filter conditions and assumes that the distribution of states remains Gaussian. This study presents an alternative, data-driven method to track the states and parameters of neural mass models (NMMs) from EEG recordings using deep learning techniques, specifically a long short-term memory (LSTM) neural network. Approach. An LSTM filter was trained on simulated EEG data generated by a NMM using a wide range of parameters. With an appropriately customised loss function, the LSTM filter can learn the behaviour of NMMs. As a result, it can output the state vector and parameters of NMMs given observation data as the input. Main results. Test results using simulated data yielded correlations with R squared of around 0.99 and verified that the method is robust to noise and can be more accurate than a nonlinear Kalman filter when the initial conditions of the Kalman filter are not accurate. As an example of real-world application, the LSTM filter was also applied to real EEG data that included epileptic seizures, and revealed changes in connectivity strength parameters at the beginnings of seizures. Significance. Tracking the state vector and parameters of mathematical brain models is of great importance in the area of brain modelling, monitoring, imaging and control. This approach has no need to specify the initial state vector and parameters, which is very difficult to do in practice because many of the variables being estimated cannot be measured directly in physiological experiments. This method may be applied using any NMM and, therefore, provides a general, novel, efficient approach to estimate brain model variables that are often difficult to measure.
- Open Access
- 27 August 2022
- Published by Elsevier in NeuroImage
- Vol. 263, 119592
Space-time resolved inference-based neurophysiological process imaging: Application to resting-state alpha rhythm
- 27 August 2022
- Published by Elsevier in NeuroImage
- Vol. 263, 119592
Open AccessSpace-time resolved inference-based neurophysiological process imaging: Application to resting-state alpha rhythm
- Open Access
Space-time resolved inference-based whole-brain neurophysiological mechanism imaging: application to resting-state alpha rhythm
Neural mechanisms are complex and difficult to image. This paper presents a new space-time resolved whole-brain imaging framework, called Neurophysiological Mechanism Imaging (NMI), that identifies neurophysiological mechanisms within cerebral cortex at the macroscopic scale. By fitting neural mass models to electromagnetic source imaging data using a novel nonlinear inference method, population averaged membrane potentials and synaptic connection strengths are efficiently and accurately imaged across the whole brain at a resolution afforded by source imaging. The efficiency of the framework enables return of the augmented source imaging results overnight using high performance computing. This suggests it can be used as a practical and novel imaging tool. To demonstrate the framework, it has been applied to resting-state magnetoencephalographic source estimates. The results suggest that endogenous inputs to cingulate, occipital, and inferior frontal cortex are essential modulators of resting-state alpha power. Moreover, endogenous input and inhibitory and excitatory neural populations play varied roles in mediating alpha power in different resting-state sub-networks. The framework can be applied to arbitrary neural mass models and has broad applicability to image neural mechanisms in different brain states. Highlights The whole-brain imaging framework can disclose the neurophysiological substrates of complicated brain functions in a spatiotemporal manner. Developed a semi-analytical Kalman filter to estimate neurophysiological variables in the nonlinear neural mass model efficiently and accurately from large-scale electromagnetic time-series. The semi-analytical Kalman filter is 7.5 times faster and 5% more accurate in estimating model parameters than the unscented Kalman filter. Provided several group-level statistical observations based on neurophysiological variables and visualised them in a whole-brain manner to show different perspectives of neurophysiological mechanisms. Applied the framework to study resting-state alpha oscillation and found novel relationships between local neurophysiological variables in specific brain regions and alpha power.
Open AccessSpace-time resolved inference-based whole-brain neurophysiological mechanism imaging: application to resting-state alpha rhythm
Neural mechanisms are complex and difficult to image. This paper presents a new space-time resolved whole-brain imaging framework, called Neurophysiological Mechanism Imaging (NMI), that identifies neurophysiological mechanisms within cerebral cortex at the macroscopic scale. By fitting neural mass models to electromagnetic source imaging data using a novel nonlinear inference method, population averaged membrane potentials and synaptic connection strengths are efficiently and accurately imaged across the whole brain at a resolution afforded by source imaging. The efficiency of the framework enables return of the augmented source imaging results overnight using high performance computing. This suggests it can be used as a practical and novel imaging tool. To demonstrate the framework, it has been applied to resting-state magnetoencephalographic source estimates. The results suggest that endogenous inputs to cingulate, occipital, and inferior frontal cortex are essential modulators of resting-state alpha power. Moreover, endogenous input and inhibitory and excitatory neural populations play varied roles in mediating alpha power in different resting-state sub-networks. The framework can be applied to arbitrary neural mass models and has broad applicability to image neural mechanisms in different brain states. Highlights The whole-brain imaging framework can disclose the neurophysiological substrates of complicated brain functions in a spatiotemporal manner. Developed a semi-analytical Kalman filter to estimate neurophysiological variables in the nonlinear neural mass model efficiently and accurately from large-scale electromagnetic time-series. The semi-analytical Kalman filter is 7.5 times faster and 5% more accurate in estimating model parameters than the unscented Kalman filter. Provided several group-level statistical observations based on neurophysiological variables and visualised them in a whole-brain manner to show different perspectives of neurophysiological mechanisms. Applied the framework to study resting-state alpha oscillation and found novel relationships between local neurophysiological variables in specific brain regions and alpha power.