Cambridge PhD in Medicine (Emergency Medicine) | Cambridge Trust Scholar | +9 years teaching experience in medical imaging, AI and neuroscience to students, doctors, researchers | More than 1000 stud

Details

At a high level, my courses provide comprehensive training in neuroscience, brain imaging and computational modelling, from undergraduate through to advanced postgraduate and research level. The content integrates biological foundations of brain function with modern data-driven and machine-learning approaches used in contemporary neuroscience and medical research.

You can =find my academic background and publications on:
️
LinkedIn:
(concealed information)

Cambridge Neuroscience:
(concealed information)

University of Cambridge (Department of Medicine ):
(concealed information)

️
️Neuroimaging Modalities
• Structural MRI (brain anatomy and tissue segmentation)
• Functional MRI (fMRI) for brain activation and functional connectivity
• Diffusion MRI and DTI for white-matter and network mapping
• Arterial Spin Labelling (ASL) for cerebral blood flow analysis
• Electroencephalography (EEG) for electrical brain dynamics
• Multimodal brain imaging and data integration

️Neuroimaging Software and Pipelines
• FSL for preprocessing, statistics and diffusion imaging
• AFNI for fMRI analysis and time-series modelling
• FreeSurfer for cortical and subcortical segmentation
• SPM for preprocessing, postprocessing, QC, and …
• CONN toolbox for resting-state and task-based connectivity
• End-to-end neuroimaging pipelines and quality control
• Some other toolbox, such as: DPARSF, DPABI, DPABINet, BCT, pNet, BrainNetClass BRAPH, BRAPH2, GraphVar, Panda, Gretna, CAT12, ANTs, Nilearn, PRoNTo, MNE-Python, EEGLAB,

️Unix and Computational Foundations for Neuroimaging
• Navigating directory trees and file systems
• Copying, moving and removing files
• Reading and processing text files
• Shell environments and path variables
• For-loops and conditional statements
• Writing shell scripts
• Stream editing with sed
• Automating neuroimaging workflows

️fMRI Analysis
• Data acquisition and organisation
• Task design and experimental paradigms
• Visual inspection and quality control
• Preprocessing pipelines
• Statistical modelling and GLM analysis
• Script-based fMRI workflows
• Second-level (group) analysis
• Third-level (multi-group) analysis
• ROI-based analysis
• Interpretation and reporting

️Structural and Surface-Based Neuroimaging
• FreeSurfer for cortical and subcortical segmentation
• Voxel-based morphometry with CAT12
• Image visualisation with MRIcroGL and ITK-Snap
• Brain labelling and region-of-interest definition

️Diffusion and Perfusion Imaging
• Diffusion MRI and tractography with MRtrix
• Tract-Based Spatial Statistics (TBSS)
• ASL (arterial spin labelling) for cerebral blood flow
• Quantification and interpretation of perfusion data

️Large-Scale Brain Datasets and Platforms
• Human Connectome Project (HCP)
• Neurodesk for reproducible neuroimaging
• 3D Slicer for advanced image analysis

️Statistics and Machine Learning for Neuroimaging
• Statistics for neuroimagers
• Machine learning for brain data
• Model evaluation and validation
• Meta-analysis for fMRI

️Programming for Neuroimaging
• MATLAB for neuroimagers
• Python for neuroimagers
• Pipeline development and automation

️Advanced Registration and Normalisation
• Advanced Normalisation Tools (ANTs)
• Cross-subject alignment and spatial normalisation

️High-Performance and Reproducible Neuroscience
• Introduction to supercomputing
• Running large-scale neuroimaging pipelines
• Open science and reproducible research

️Brain Connectivity, Connectomics and Network Modelling
• Construction of functional and structural brain connectomes
• Brain parcellation and atlas-based network analysis
• Adjacency and connectivity matrices
• Brain networks represented as graphs (nodes and edges)
• Graph-theoretical characterisation of brain organisation
• Network integration, segregation and hub identification
• Centrality, clustering, efficiency and modularity
• Network modules, communities and large-scale organisation
• Multiscale mapping of human brain connectomics
• Network resilience, communication and information flow
• Applications to healthy and diseased brains

️Generative and Statistical Models of Brain Networks
• Probabilistic models of network formation
• Wiring rules and connection probability
• Growth and optimisation models of brain networks
• Statistical inference in connectomics

️Dynamical and Computational Models of Brain Networks
• Mathematical modelling of neural systems
• Whole-brain and network-level dynamical models
• Neural oscillations and large-scale brain dynamics
• Simulation of brain activity
• Computational approaches to understanding brain function

️Data Analysis and Scientific Computing
• Data preprocessing, cleaning and harmonisation
• Statistical modelling and hypothesis testing
• Time-series analysis
• High-dimensional data analysis
• Reproducible scientific workflows

️Programming for Neuroscience and Medical AI
• MATLAB for signal processing and neuroimaging analysis
• Python for data science, neuroimaging and machine learning
• Scientific libraries for imaging, statistics and modelling
• Pipeline automation and reproducible research

️Machine Learning and Artificial Intelligence
• Supervised and unsupervised learning
• Deep learning and neural networks
• Medical imaging AI
• Feature extraction and biomarker discovery
• Predictive modelling for neurological disorders

️Clinical and Translational Applications
• Alzheimer’s disease, Parkinson’s disease and dementia
• Traumatic brain injury and stroke
• Neurodevelopmental and psychiatric disorders
• Imaging-based diagnosis and prognosis
• AI-driven clinical decision support

️Neuroanatomy and Brain Organisation
• Structural organisation of the human brain
• Cortical and subcortical regions
• Functional brain systems (sensory, motor, cognitive and emotional)
• Large-scale brain networks and their interaction
• Anatomical and functional brain atlases

️Nervous System Structure and Function
• Central nervous system: brain and spinal cord
• Peripheral and autonomic nervous systems
• Sensory processing and motor control
• Cognitive and behavioural functions
• Integration of perception, action and cognition

️️Machine Learning, Deep Learning and Data Science for Neuroscience and Medical AI

️Foundations of Machine Learning for Brain and Medical Data
• Introduction to supervised, unsupervised and semi-supervised learning
• Data-driven modelling vs hypothesis-driven neuroscience
• What features, labels and targets represent in medical and brain
datasets
• Types of variables: numerical, categorical, binary and temporal
• Train–validation–test splitting
• Bias–variance trade-off, overfitting and generalisation
Data Preprocessing and Feature Engineering
• Scaling and normalisation
• Handling missing data (imputation)
• Encoding categorical variables
• Detecting and handling outliers
• Working with imbalanced clinical datasets
• Feature extraction from neuroimaging and electrophysiology
• Building pipelines and preventing data leakage

️Supervised Learning and Predictive Modelling
Core Models
• Linear and regularised models
• Linear Discriminant Analysis (LDA)
• Support Vector Machines (SVM)
• k-Nearest Neighbours
• Naive Bayes classifiers
• Decision Trees
• Ensemble learning
• Random Forest
• Gradient Boosting
• Multi-class classification
• Semi-supervised learning

️Applications in Neuroscience and Medicine
• Disease classification and diagnosis
• Outcome and prognosis prediction
• Modelling continuous variables (age, cognition, brain volume, biomarkers)
• Feature selection and representation learning for brain imaging
Unsupervised Learning and Representation Discovery
• Principal Component Analysis (PCA)
• Independent Component Analysis (ICA)
• Gaussian Mixture Models
• Clustering and biclustering
• Manifold learning for nonlinear dimensionality reduction
• t-SNE and UMAP for data visualisation

️Deep Learning and Neural Networks
• Neural network fundamentals
• Deep feed-forward networks
• Convolutional neural networks for medical and brain images
• Recurrent and sequence models for time-series and EEG
• Deep feature learning and biomarker discovery
• AI-based modelling of complex brain data

️Model Training and Optimisation
• Dataset preparation and splitting
• Loss functions and objective functions
• Parameter optimisation
• Regularisation and model stability
• Preventing overfitting and improving generalisation

️Model Evaluation and Validation
• Cross-validation strategies
• Accuracy, precision, recall and F1-score
• ROC curves, sensitivity and specificity
• Predictive value and clinical relevance
• Interpreting reliability and uncertainty in medical models

️Anomaly Detection and Clinical Outliers
• Isolation Forest
• One-Class SVM
• Local Outlier Factor

️Neural and Medical Data Analysis in Python and MATLAB
• Neuroimaging and electrophysiology data processing
• Statistical analysis and modelling
• Signal processing and time-series analysis
• Machine-learning pipelines
• Reproducible, research-grade computational workflows

️Explainable and Trustworthy AI
• Feature importance
• Permutation importance
• Partial dependence plots
• Practical introduction to SHAP

️Understanding what models learn from brain and clinical data
Real-World Machine Learning Practice
• Working with time-series and longitudinal medical data
• Preventing data leakage
• Testing on unseen and out-of-distribution data
• Project-level ML workflow from data to report
• Bias, fairness and ethics in medical AI

️Whole-Brain Dynamical Systems
• Kuramoto models of neural synchronisation
• Wilson–Cowan excitatory–inhibitory population models
• Coupled oscillator systems
• Emergence of large-scale brain rhythms
• Linking structure to function

️Simulation of Neural Dynamics
• Neurolib and Python-based modelling frameworks
• Simulation of large-scale brain activity
• Parameter exploration and model fitting
• Computational experiments and hypothesis testing

️Neuronal and Spiking Dynamics
• Biophysical and mathematical neuron models
• Spiking neurons and firing rate models
• Synaptic plasticity and learning rules
• Neural coding and signal transmission

️Hodgkin–Huxley and Biophysical Models
• Ion channel dynamics
• Action potential generation
• Membrane excitability
• Linking cellular physiology to network activity

️Electrical Signalling in the Brain
• Neuronal electrical activity
• Brain oscillations and rhythms
• Cognitive and behavioural correlates
• Neural synchronisation and communication

️Synaptic Events and Neural Communication
• Excitation and inhibition
• Synaptic transmission
• Temporal integration and spike timing

️Neural Recording and Brain Monitoring
• Intracellular and extracellular recording techniques
• Single-unit, multi-unit and population activity
• Linking neural signals to behaviour and cognition

️EEG and Event-Related Potentials
• Scalp-level brain recordings
• Event-related potentials (ERPs)
• Time-locked neural responses
• Cognitive and clinical applications

️Brain Oscillations and Brain States
• Neural rhythms and frequency bands
• Sleep, attention and cognitive states
• Functional brain dynamics

️Advanced Electrophysiological Data Analysis
• Signal processing and feature extraction
• Time–frequency analysis
• Statistical modelling of neural signals
• Noise reduction and artefact correction

️Research Design and Experimental Planning
• Formulating scientific questions
• Designing neuroscience experiments
• Linking models, data and hypotheses
• Reproducible and rigorous research workflows