Jessica Dafflon, PhD

Jessica Dafflon, PhD

Research Scientist

NIMH, NIH

Biography

I am a Research Scientist working at the intersection between Machine Learning and Neuroscience. My research focuses on using machine learning tools to find patterns in brain images and building computational models to simulate brain processes. Currently, I am a member of the Data Science and Sharing Team at the National Institute of Mental Health, NIH. I love learning new tools and methods and applying them to real datasets.

Interests
  • Artificial Intelligence
  • Neuroimaging
  • Machine Learning
  • Medical Imaging
  • Brain Computer Interfaces
Education

  • PhD in Neuroimaging, 2020

    King's College London

  • MRes in Medical Imaging, 2016

    King's College London

  • MSc in Neuroscience, 2015

    ETH Zürich

  • BSc in Biology, 2013

    ETH Zürich

News

  • July, 2022: I was invited to give a talk at SIPS 22 at the multiverse analysis session
  • June, 2022: The “into the multiverse of neuroimaging” was finally published on Nature Communications.
  • April, 2021: My PhD thesis was selected for the 2021 King’s Outstanding Thesis Prize.

Projects

*
All Deep Learning Other
Predicting Age from Neuroimaging using an Automated Machine Learning approach (autoML)
In neuroscience, the choice of the machine learning algorithm and its hyperparameters, are often arbitrary and frequently do not correspond to the statistical properties of the data being analysed. In this project, I used an autoML approach to explore a vast space of models and their hyperparameters, and in an entirely data-driven fashion, find the pipeline that most accurately predicts brain age.
PDF Github Google Scholar
Predicting Age from Neuroimaging using an Automated Machine Learning approach (autoML)
A comparison between machine learning to predict brain age
Different algorithms have been used to predict brain age from structural images. However, every study uses different algorithms on different datasets, making it difficult to compare the results among each other. This project aimed to bridge this gap and rigorously compare the most commonly used algorithms to predict brain age and to compare the impact of using different inputs on the precision of the analysis.
PDF Google Scholar Brain-age-prediction
An Embodied Simulation of the Human Brain
Although different computational models have been developed to investigate the neural dynamics of the brain, less is known about the brain-environment interaction and how the latter influence brain dynamics. Therefore, we developed a virtual agent, whose activity is driven by a computational model, and analysed how the environment influenced its neural dynamics.
PDF Video
An Embodied Simulation of the Human Brain
Computational Models of Social Learning and Decision Making
This project aimed to develop and test computational models of learning that quantify how people learn under social uncertainty .We used a combination of methods, which included: hierarchical Bayesian model of learning, model-based fMRI and DCMs
PDF
Implementation of Large-scale Brain Simulations on NeuroML
This project aimed to implement Large-scale Brain Simulations, which are models that simulate the interaction between different brain areas, in NeuroML. NeuroML is a tool that standardises commonly used parameters to describe neuroscience models.
PDF WilsonandCowan delMolino MejiasEtAl2016
Implementation of Large-scale Brain Simulations on NeuroML

Selected Publications

Quickly discover relevant content by filtering publications.
Jessica Dafflon, Pedro F. da Costa, František Váša, Ricardo Pio Monti, Danilo Bzdok, Peter J. Hellyer, Federico Turkheimer, Jonathan Smallwood, Emily Jones, Robert Leech (2022). A guided multiverse study of neuroimaging analyses. Nature Communications.

Cite DOI URL

Walter HL Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F Da Costa, Virginia Fernandez, Parashkev Nachev, Sebastien Ourselin, M Jorge Cardoso (2022). Brain imaging generation with latent diffusion models. Deep Generative Models: Second MICCAI Workshop, DGM4MICCAI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings.

Cite

Pedro F Da Costa, Jessica Dafflon, Sergio Leonardo Mendes, João Ricardo Sato, M Jorge Cardoso, Robert Leech, Emily JH Jones, Walter HL Pinaya (2022). Transformer-based normative modelling for anomaly detection of early schizophrenia. arXiv preprint arXiv:2212.04984.

Cite

Lea Baecker, Jessica Dafflon, Pedro F. Costa, Rafael Garcia-Dias, Sandra Vieira, Cristina Scarpazza, Vince D. Calhoun, João R. Sato, Andrea Mechelli, Walter H. L. Pinaya (2021). Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data. Human Brain Mapping.

Cite DOI URL

Jessica Dafflon, Pedro F. da Costa, František Váša, RicardoPio Monti, Danilo Bzdok, Peter J. Hellyer, Federico Turkheimer, Jonathan Smallwood, Emily Jones, Robert Leech (2020). Neuroimaging: into the Multiverse. bioRxiv.

Cite DOI

Federico E Turkheimer, Peter Hellyer, Angie A Kehagia, Paul Expert, Louis-David Lord, Jakub Vohryzek, Jessica De Faria Dafflon, Mick Brammer, Robert Leech (2019). Conflicting emergences. Weak vs. strong emergence for the modelling of brain function. Neurosci Biobehav Rev.

Cite DOI