Prediction of Personality using Diffusion MRI Local Connectome Fingerprints

Project info

Title: Prediction of Personality using Diffusion MRI Local Connectome Fingerprints

Project lead: Fang-Cheng Yeh

Project collaborators:

Registered Brainhack Global 2020 Event: The Pittsburgh Brainhack: DeBurghing 2020, Pittsburgh, PA,

Project Description: Local connectome fingerprints (LCF) are voxel-based metrics derived from diffusion MRI to provide a subject-specific quantification of brain connections. The task of this project is to predict personality using LCF.

Good first issues:

1. Build a regression or classification model to predict the first answer to the personality question.
2. Estimating predicting accuracy using 10-fold cross-validation

Data to use: https://pitt.box.com/v/HCP1062-NEOFAC

There are a total of 1062 subjects included in this data set. Each LCF of a subject has a total of 128894 brain fingerprint features. Each feature has an associated location (mni_location) and fiber orientation (fiber_direction) to allow plotting the spatial distribution of the feature. Please note that each voxel may have more than one feature (because there could be multiple fiber populations within the same voxel).

• number of samples: 1062
• input data: subjects
• variables to predict: NEOFAC

dimension: the image dimension of the original MRI data fiber_direction: the axonal fiber direction for each feature mni_location: the spatial location for each feature names: HCP serial number for each subject subjects: The LCFs of 1062 subjects (features) NEOFAC: subjects answers to 60 questions (variable to be predicted). The NEO-FFI variable can be 0.3: strongly disagree, 0.4 disagree, 0.5 neutral, 0.6: agree, 0.7: strongly agree.

Link to project repository/sources: http://dsi-studio.labsolver.org/download-images/local-connectome-fingerprints-of-hcp-1062-subjects-for-neofac-prediction

Goals for Brainhack Global 2020 The goal is to test whether fixed behaviors could be predicted from LCF.

Skills: Data regression using statistics or machine learning methods.

Tools/Software/Methods to Use: Python, Matlab, or R Any data analysis packages.

Communication channels: Twitter account: @FangChengYeh

Project labels

Now the real list (please indicate all of the labels you’d like to add to your project):

• Type of project: #coding_methods, #data_management, #method_development

• Project development status: #releases_existing

• Topic of the projet: #connectome, #deep_learning, #diffusion, #machine_learning, #MR_methodologies, #neural_decoding, #statistical_modelling,

• Tools used in the project: #DSIStudio

• Tools skill level required to enter the project (more than one possible): #comfortable, #expert, #familiar

• Programming language used in the project: #Matlab, #Python, #R

• Modalities involved in the project (if any): #behavioral, #DWI, #MRI

• Git skills required to enter the project (more than one possible): #0_no_git_skills

Project Submission

Submission checklist

Once the issue is submitted, please check items in this list as you add under ‘Additional project info’

• Link to your project: could be a code repository, a shared document, etc.

• Goals for Brainhack Global 2020: describe what you want to achieve during this brainhack.

• Flesh out at least 2 “good first issues”: those are tasks that do not require any prior knowledge about your project, could be defined as issues in a GitHub repository, or in a shared document.

• Skills: list skills that would be particularly suitable for your project. We ask you to include at least one non-coding skill. Use the issue labels for this purpose.

• Chat channel: A link to a chat channel that will be used during the Brainhack Global 2020 event. This can be an existing channel or a new one. We recommend using the Brainhack space on Mattermost.

• Provide an image of your project for the Brainhack Global 2020 website.