BrainHack Lucca 2024

2 - 5 December 2024

BrainHack Lucca

%d

Days

%h

Hours

%m

Minutes

%s

Seconds

About BraianHack Lucca

Open science and open data

The purpose of Brainhack is to bridge the data science and neuroscience research communities to advance the progress of brain science research. This collaborative workshop brings researchers from across the globe and different disciplines to work together on innovative projects related to neuroscience combining elements of Hackathons, with a variety of educational activities. Year after year, global Brainhack events have brought together researchers to participate in open collaboration and regional Brainhack events keep the momentum going throughout the year.

Read the BH code of conduct

BrainHack Global

The world-wide organization that helps with the organization of local events

Program

IMPORTANT NOTICE: we recorded a short video on how to write an efficient project for the BrainHack.
You can find the link to the video in the heading of the Projects section

You can find the complete BrainHack Lucca program here.
The first day is dedicated to teaching, with training sessions on different open science tools.
The following days will be focused on collaborative working (hacking sessions).

Welcoming, coffee and delicacies

Registration and breakfast

Badges at IMT school and coffee at 'La Pecora Nera'

Ruggero Basanisi

Introduction to BrainHack - Ruggero Basanisi (Lucca, IMT)

Introduction to BrainHack Lucca 2024

Fabio Pinelli

Training: Python basics - Fabio Pinelli (Lucca, IMT)

Brief Introduction to Python

Ruggero Basanisi

Training: Going on with Python - Ruggero Basanisi (Lucca, IMT)

Exploring useful libraries for Python programming

Matteo Lionello

Training: Git & GitHub - Matteo Lionello (Lucca, IMT)

How to keep track of code changes and boost collaboration

Buon Appetito

Lunch Break

Lunch will be served at 'Marameo'

Fabio Pinelli

Training: Machine learning with Python: an overview - Fabio Pinelli (Lucca, IMT)

Introduction to machine learning basics using Python

COFFEEEEEE

Coffee Break

Coffee Break will be served at 'La Pecora Nera'

Giacomo Handjaras

Training: Tools for fMRI processing - Giacomo Handjaras (Lucca, IMT)

How to manage and process fMRI data

Projects' Presentation

Projects pitches - Projects leaders

Short presentations of the available projects

Party!

Social Night Event - All the Brainhackers

The social night event will be hosted in IMT school

Breakfast

Breakfast

Breakfast will be served at 'La Pecora Nera'

Hack those brains!

Hacking session - Working groups

Collective work on projects!

Buon Appetito

Lunch Break

Lunch will be served at 'Marameo'

Hack those brains!

Hacking session - Working groups

Collective work on projects!

Willow Trantow

Coffee Break

Coffee Break will be served at 'La Pecora Nera'

Hack those brains!

Hacking session - Working groups

Collective work on projects!

Breakfast

Breakfast

Breakfast will be served at 'La Pecora Nera'

Hack those brains!

Hacking session - Working groups

Collective work on projects!

Buon Appetito

Lunch Break

Lunch will be served at 'Marameo'

Hack those brains!

Hacking session - Group Work

Collective work on projects!

Willow Trantow

Coffee Break

Coffee Break will be served at 'La Pecora Nera'

Hack those brains!

Hacking session - Group Work

Collective work on projects!

Breakfast

Breakfast

Breakfast will be served at 'La Pecora Nera'

Hack those brains!

Hacking session - Group Work

Are you starting to getting tired? Don't give up!

Buon Appetito

Lunch Break

Lunch will be served at 'Marameo'

Hack those brains!

Hacking session - Group Work

The last straight line!

Willow Trantow

Coffee Break

Coffee Break will be served at 'La Pecora Nera'

Hack those brains!

Slides preparation - Group Work

Finish the figures and prepare a few slides

All

BrainHack Lucca Wrapup - All the BrainHackers

Presentation of the results of BrainHack Lucca projects

Some numbers from the last edition

Teaching hours

Hacking hours

Projects

Participants

Register

Registration is now closed.

Register

Registration is now closed.

Participants' checklist

In order to facilitate the participation to first day's training sessions, participants are recommended to follow these few preliminar steps:

Projects

Here you can find all the informations about the proposed projects.
If you want to submit a project you should first register, then follow the link to fill the form through a github issue.
Projects can be anything you'd like to work on during the event with other people (coding, discussing a procedure with coworkers, brainstorming about a new idea), as long as you're ready to minimally organize this!

Click here to watch a short video about "How to write a project for the BrainHack", in which we discuss how a project should be conceived and project leaders' duties.


Projects can be pre-registered and published on the website until 30/11/2024!

After this deadline, it will still be possible to propose a project during the 'project pitches' on day 1.

Click to submit a project filling a GitHub issue template!


Exploring How Music Shapes Emotions in the Brain. A network connectivity analysis perspective on fMRI data

By Matteo Lionello

Description


Music has a unique ability to evoke emotions, but what’s actually happening in the brain when we feel something while listening to it? This project dives into that question using fMRI data from participants (25) listening to music during fMRI scans (2 runs 20mins each, total +5K timepoints). Some of the boring initial stuff has already been done! Brain data has already been preprocessed, and some cool features are already extracted from the music itself and available to play with - acoustic and spectral qualities, emotional cues, and deep features from a VGGish audio model.
Here’s what we want to do:

  • Understand Brain Connectivity: Figure out which brain networks are involved in processing emotions while listening to music, and track how these networks change over time.
  • Link Music Features to Brain Activity: Use machine learning and causal analysis to see how different music features (like tempo, spectral, and emotional feedbakcs patterns) impact brain connections and dynamics.

Goals for the BrainHack:
  • Framework set up with fMRI data aligned to music features.
  • Preliminary connectivity and feature-to-network mappings complete.
  • Eye-catching visualizations, even if they’re just the beginning of the journey.
Contributors' skills:
  • Matlab
  • Basic fMRI data analysis knowledge


Functional MRI Analysis of Connectivity and Network Dynamics of central fatigue in Multiple Sclerosis disease

By Alberto Benelli

Description


Fatigue is a debilitating symptom of multiple sclerosis (MS), affecting over 80% of patients and significantly impairing their quality of life. Despite its prevalence, the neural mechanisms underlying fatigue in MS remain poorly understood. Functional magnetic resonance imaging (fMRI) offers a powerful tool to investigate the brain’s intrinsic connectivity and dynamic network behavior. This project aims to analyze fMRI time-series data to uncover differences in functional connectivity and network dynamics among MS patients with fatigue, MS patients without fatigue, and healthy controls. By identifying distinct connectivity patterns and their relationships with structural MRI findings, this study seeks to advance our understanding of MS-related fatigue and identify potential neuroimaging biomarkers.

Goals for the BrainHack:

  • Primary Objective: To investigate differences in functional connectivity and network dynamics among:
    • MS patients with fatigue
    • MS patients without fatigue
    • Healthy controls
  • Secondary Objectives:
    • To explore correlations between fMRI connectivity metrics and clinical measures of fatigue severity
    • To integrate structural MRI findings (e.g., lesion load, gray matter atrophy) with functional connectivity results to provide a comprehensive view of the neural underpinnings of fatigue in MS
Contributors' skills:
  • Python codind
  • fMRI
  • MRI segmentation


NeuroInfer and Database update

By Davide Coraci, Matteo Lionello & Sara Mazzuccato

Description


NeuroInfer (NI) is a software to support neuroscientists' inference on fMRI data. It implements a Bayesian approach and it is currently based on a dataset of more than 14,000 fMRI studies (shared with NeuroSynth). The aim of the project is to update the database and, in particular, define a pipeline for extracting relevant information from the texts of fMRI studies (i.e., terms and coordinates of brain activation).
Goals for the BrainHack:

  • Check the current version of NeuroInfer
  • Define a flowchart for processing texts of fMRI studies
  • Develop a pipeline to process texts
Contributors' skills:
  • Python (basics)
  • Experience with API would be cool!


Dreamcatcher: decoding dream-event in EEG data with multimodal language models and interpretability tools

By Lorenzo Bertiolini

Description


In recent years, multimodal systems based on large language models (LLMs) have been successfully applied to encode and decode information from neurophysiological data. Most applications have focused on tracing and reconstructing images and language in the brain, using pictures, textual reports, and EEG data. While previous work has unveiled plausible spatial neural correlates of dream events, its time aspect remains elusive, In this project, we aim to trace dream events in EEG signals, using pre-trained LLMs and standard interpretability tools from the NLP and AI literature.

Goals for the BrainHack:

  • Develop a framework to pre-process EEG data having different formats for the same LLM
  • Set up a training regime suitable to the available data
  • Train and monitor a first set of models or toy examples
  • Prepare analysis pipeline
  • Analyse a first set of models
Contributors' skills:
  • Basic Python for text mining and analysis
  • Python scientific, neuroscience, or ML (e,g., numpy, scikilearn, seabonr, mne, pytorch, hugging face)
  • EEG/neuroscience data analysis knowledge
  • ML/AI knowledge (even basic)


Navigating Depression on Social Media: NLP and Cognitive Network Insights

By Irene Sánchez Rodríguez, Liber Dorizzi, Mattia Marzi & Riccardo Vella

Description


We are using NLP and cognitive network analysis to explore and map depression-related discussions on social media, aiming to uncover patterns and insights into how mental health struggles are expressed online. By combining advanced tools like transformer models, interpretability frameworks, and graph analysis, we aim to create a novel approach to understand depression narratives. Resources include pre-trained models and a curated dataset to help participants dive right into preprocessing, modeling, and visualization.

Goals for the BrainHack:

  • Preprocess and clean the social media dataset
  • Perform exploratory data analysis to identify key patterns and statistics
  • Fine-tune transformer-based models for classifying depression-related posts
  • Use XAI to extract key features driving model predictions
  • Construct a cognitive network of depression-related terms and relationships
  • Compare traditional NLP models with network-enhanced approaches
Contributors' skills:
  • Python coding
  • NLP and text analysis: Knowledge of text preprocessing, tokenization, and working with existing tools in this matter
  • Machine learning: Familiarity with training and fine-tuning transformer models like BERT
  • Graph analysis: Experience with tools like NetworkX or Gephi to build and analyze cognitive networks
  • Critical thinking and communication: Ability to interpret results, suggest improvements, and collaborate effectively, especially for participants less familiar with coding


The Influence of Arousal on Brain Connectivity: A Multimodal Study Proposal

By Santa Sozzi, Miriam Acquafredda & Giacomo Mazzotta

Description


Arousal, defined as the behavioral state of alertness, is a potential driver of variability in brain activity and functional connectivity, particularly within networks such as the Default Mode Network and the Salience Network. In this project, we aim to investigate the effects of arousal on brain connectivity using a recently published open-access dataset that integrates pre-processed pupillometry, fMRI, and EEG data, enabling a comprehensive multimodal analysis. By combining pupillometry (as a proxy to identify high and low arousal levels), EEG (offering high temporal resolution of brain activity), and fMRI (providing high spatial resolution of functional activity), we can investigate the relationships between arousal states and both functional and effective connectivity across key brain regions.

Goals for the BrainHack:

  • Identify arousal-related brain regions through the analysis of the relationships between pupil dynamics and fMRI signals at both voxel and region levels (e.g., via correlation or regression analyses on resting-state data)
  • Compare functional and effective connectivity within arousal-related networks across high and low arousal states, using indices derived from both fMRI and EEG resting-state connectivity
As a secondary objective, we aim to replicate these analyses on a visual task dataset to compare the impact of arousal under resting-state and task-based conditions.

Contributors' skills:
  • MATLAB programming (basic)
  • Python programming (basic)
  • Basic fMRI/EEG/pupillometry analysis knowledge


Probabilistic models of brain connectivity at rest from fMRI data

By Miguel Ibanez Berganza, Arianna Armanetti, Gabriele Poidomani & Francesca Santucci

Description


We aim to develop a new class of probabilistic models to enhance the understanding of brain connectivity at rest, leveraging resting-state fMRI data. Our goal is to create models that balance the simplicity of traditional Gaussian approaches with the complexity and richness of dynamic models like DCM, addressing neuroscientists' need for more interpretable and efficient tools to analyse functional brain networks.
Our focus will be on extending Gaussian models through regularization techniques and introducing a novel approach based on neural network tools such as the Boltzmann Machine. These methods promise to offer both simplicity and robust performance in capturing the intricacies of brain connectivity.
We will use a preprocessed dataset, allowing us to immediately begin developing and testing our models. Our process involves reproducing results from established Gaussian approaches in the literature as a baseline, followed by tackling the more challenging task of implementing and training innovative models.
We believe this project is valuable because it introduces fresh, effective methods for modeling brain connectivity using relatively simple yet powerful approaches.

Goals for the BrainHack:

  • Baseline implementation: Reproduce existing results using traditional Gaussian models to validate the initial setup
  • Enhancement of existing model
    • Study the possible regularisation techniques for the gaussian model
    • Implement 2 or three gaussian regularised models
    • Test their performance in out-of-sample predictability
  • Implement a new model
    • Implement the Boltzman Machine for this specific dataset
    • Train the model
    • Test its performance in out-of-sample predictability
  • Comparison: Compare the performance of the different models and find the best one
  • Bonus: train the Boltzman Machine model on a labeled dataset and test its classification performance
Contributors' skills:
  • Python coding
  • Basic notions of probabilistic models


Towards the extension of visual/audio human-computer interfaces based on movement patterns to piano-generated rhythms

By Gianluca Maraschio, Stefano Menchetti, Francesco Biancalani, Giorgio Stefano Gnecco, Valentina Pieroni & Alessandro Betti

Description


Recent studies have explored the potential of rhythmic pattern extraction for the development of human-computer interfaces able to provide visual or audio feedback - potentially in real-time - with various goals, such as assessing the effectiveness of performing specific motor tasks, facilitating learning and skill acquisition, and enhancing the reproducibility of technical gestures. A recent example is the TickTacking interface from Rocchesso et al. (2023), where a trajectory is drawn on a screen based on rhythms extracted by the bimanual tapping of two buttons.
This project aims to explore the possibility of developing an interface similar to TickTacking in which a piano keyboard replaces the two buttons, and the user is either a beginner or an expert pianist. Onset detection (i.e., the detection of the starting time of each note) is of fundamental importance to achieve this goal. Indeed, its analysis allows one to extract the inter-onset interval provided as an input to the interface. Hence, this project is focused on evaluating the feasibility of the application of various algorithms for onsets and tempo detection in the case of publicly available recordings and live performances obtained using an electronic piano at the disposal of the researchers. The project itself is part of the broader PRIN 2022 project MAHATMA (Multiscale Analysis of Human and Artificially Generated Trajectories, Models and Applications).
Possible developments of this research are:

  • classifying automatically audio excerpts executed by beginners or experts
  • evaluating the effectiveness of the video/audio feedback generated by the extended interface in the context of a learning process in which a beginner pianist follows a rhythmic (or polyrhythmic) pattern generated by an expert
  • generating artificial rhythmic patterns imitating expert behavior using generative adversarial learning techniques
Goals for the BrainHack:
  • Evaluating the feasibility of the application of various algorithms for onsets and tempo detection (applied, e.g., to the first prelude of Bach's Well-Tempered Clavier and the first movement of Beethoven's Moonlight Sonata) in the case of publicly available recordings and live performances obtained using an electronic piano at the disposal of the researchers
  • Extracting various inter-onset intervals from the available data and performing their statistical analysis
Contributors' skills:
  • MATLAB programming
  • Python programming
  • ML and statistical analysis
  • Sound processing (basic)


Team

The BrainHack Lucca organizing committee

Davide Coraci

PhD Student

Giacomo Handjaras

Assistant Professor

Guillaume Legendre

PostDoctoral Fellow

Matteo Lionello

PhD Student

Monica Betta

Assistant Professor

Ruggero Basanisi

PostDoctoral Fellow

Tommaso Gili

Assistant Professor

Valentina Elce

PostDoctoral Fellow

Valerie van Es

PhD Student

Questions, Services &
Useful Resources

Here you can find useful information about services in Lucca.

1. Do I need programming skills to participate?

The aim of BHL is to create an exchange environment accessible to all participants, allowing to propose projects in which different levels of programming skills are needed. Thus, participating to BHL can demand different levels of programming skills depending on the project that a participant decides to attend, from zero to hero.

2. Which kind of project can I propose as project leader?

All kind of projects are accepted, from zero programming skills projects (e.g.: brainstorming on a peculiar topic or discussing about common proceedings) to fully computational projects (e.g.: programming a toolbox to perform data analysis using a new methodological framework). The only limitation is that they should be brain-themed projects.

3. What do I need to participate BHL?

To participate BHL you just need your laptop and good vibes. The organization team will try to provide all participants with electrical supplies, if your laptop has a short charger cable we advise to bring with you an extension cord in order to reach plugs.

4. Where can I find an accomodation?

Lucca offers tons of possibilities in terms of accomodations with hotels and B&Bs. Accomodations inside the walled city are generally more expensive than accomodations outside or around the walls. In the near future we will try to stipulate an agreement with some structures for hosting participants at lower fares. We will keep you posted on this topic.

5. Where can I eat in Lucca?

BHL provides their participants with two coffee breaks per day, lunch and a buffet for the social event on the first night. However, if you want to discover the typical flavours of Tuscany, here we give you some suggestions for restaurants:

As an alternative, you can easily find around the city lots of spots to eat sandwiches, pizza and stuffed 'focaccia'.

6. What can I visit in Lucca?

You can enjoy Lucca just by hanging around the ancient walls or the streets of the walled city.
Moreover it offers some attractions:

Social networks

Here you can find our social media links

Contacts

Any question? Write us a message!
You can find more information about the school and how to reach us following THIS LINK.

Past editions

Visit the past editions of BrainHack Lucca