Welcome
Marcella Montagnese
Research Fellow
University of Cambridge
Biography
I am a Junior Research Fellow in Biological and Medical Sciences at Christ’s College, University of Cambridge, and a Research Associate in Neuroinformatics at the Department of Psychology and affiliate with the Department of Clinical Neurosciences.
My primary research involves analyzing neuroimaging and clinical data from memory clinics at Addenbrooke’s Hospital and other NHS trusts around the UK. I use artificial intelligence (AI) and normative models (Brain Charts, Bethlehem et al., Nature, 2022) to develop individualised tools for patient stratification and prognostication. Additionally, I have been applying cutting-edge AI techniques to solve complex healthcare challenges through my involvement in the PASSIAN Project, which focuses on implementing federated learning in the NHS. The goal is to pilot a secure, scalable clinical data-sharing solution that will remove a key roadblock to developing AI implementations for real-world biomedical data.
I completed my PhD in Neuroimaging at King’s College London, supervised by Prof Mitul Mehta and Prof Dominic ffytche, where I explored the neural and cognitive correlates of Parkinson’s Disease Psychosis using multimodal imaging techniques (resting-state fMRI, structural, and diffusion imaging) combined with network neuroscience, transcriptomics, and receptor maps approaches. As part of my NIHR SPARC Award at the University of Cambridge, I worked under the guidance of Prof Ed Bullmore and Dr Sarah Morgan to further expand my expertise in graph theoretical and machine learning analyses, and was later affiliated with Trinity College (Cambridge).
My other projects include computational modelling of cognitive performance and cognitive decline, the investigation of psychotic symptoms across diagnostic categories, and the exploration and classification of multimodal hallucinations (i.e. hallucinations occurring across multiple sensory modalities).
Alongside my research, I am passionate about promoting open access to coding and AI resources. As an ambassador for the Women Techmakers Initiative powered by Google, I actively work towards promoting diversity and inclusion in the tech industry.
Outside of work, I am an avid photographer and a cinephile!
- Visual hallucinations and psychosis
- Neuroimaging (diffusion, fMRI, EEG, T1)
- Computational Psychiatry
- Brain networks
- Machine learning
- Open Science
- Federated Learning
PhD in Neuroimaging, 2018-2022
King's College London
MPhil in Computational Psychiatry, 2017-2018
University of Cambridge
BSc in Psychology and Neuroscience, 2014-2017
University of Cambridge
Skills
- Advanced programming
- Computational Modelling
- hBayesDM
- Data analysis and preprocessing
- Advanced illustrations and plotting
- Traditional & multilevel meta-analysis methods
- Linear Mixed Modelling
- Bayesian statistics
- Synthetic data simulation for Null hyp. testing
- Partial Least Square (PLS) Analyses;
- SPLINE Longitudinal Modelling
- fMRI, structural, and diffusion weighted imaging
- Preprocessing and analysis softwares (Freesurfer, SPM, FSL, AFNI, fMRIprep)
- EEG data processing and ERP analyses
- Docker & Reproducible Analysis Pipelines
- Graph theory analyses
- Wavelet Despiking methods
- High-performance computing (Sun Grid Engines & Slurm)
- Data science skills with Python;
- Machine Learning libraries (TensorFlow, PyTorch, Scikit-learn, Numpy, Keras)
- Pycharm, JupyterNotebook, Visual Studio
- Nilearn and Nipype
- Transcriptomic and receptor maps analyses
- Drift diffusion modelling
- Phlebotomy certificate
- Clinical training in electrocardiography (ECG)
- Administering neuropsychological tests (cognition, psychosis,dementia)
- Protocol development for pharmaceutical interventions
Experience
All Publications
Projects
Longitudinal Morphometric Similarity Networks
Constructing and investigating Morphometric Similarity Networks from structural and diffusion weighted imaging data in a large, longitudinal cohort of patients with Parkinson’s Disease Psychosis.
Cognitive Decline in Parkinson’s Psychosis
Using multi-level meta-analytic tools to investigate if a specific profile of impaired cognition and visual function is linked to vulnerability to visual hallucinations in Parkinson’s Disease. The overall aim is to better understand the complex relationship between psychosis and cognitive decline in Parkinson’s patients.
Brain networks in Parkinson’s Disease Psychosis
Using graph theoretical approaches and resting fMRI data to better characterise the neural fingerprints of visual hallucinations in Parkinson’s Disease. This includes (i) evaluating group differences in FC in terms of both Von Economo cytoarchitectonic principles and well-established functional connectivity networks, (ii) NBS analyses, and (iii) machine learning approaches to identify patterns of covariance between rsfMRI networks and cognitive and clinical biomarkers of interest (cognitive tasks, MCI tests, cerebrospinal fluid biomarkers such as β-Amyloid, T-Tau and α-Synuclein)
The neural basis of psychosis in Parkinson’s disease.
Developing targets for understanding current treatments and developing novel treatments The aim of this pharmachological intervention is to implement and enhance a neuroimaging protocol to test for whole brain impairment in PD patients with and without psychosis to (i) enhance understanding of the neural basis of PD psychosis, (ii) estimate the magnitude of impairment both in predefined brain regions and across brain networks and (iii) test for drug effects (5-HT2a inverse agonism) in these networks.
Computational Modelling of RL in Schizophrenia
This work focuses on the application of computational models of reinforcement learning (RL) in patients with schizophrenia, in addition to investigating the link between RL task performance and molecular genetic risk for the disorder.
Multimodal Hallucinations
Hallucinations can occur in different sensory modalities, both simultaneously and serially in time. Hallucinatory experiences occurring in multiple sensory systems—multimodal hallucinations (MMHs)—are more prevalent than previously thought and may have greater adverse impact than unimodal ones, but they remain relatively underresearched.
Grants & Awards
Training & Accomplishments
