A Machine Learning project predicting dementia progression from MRI data using SVM, One-vs-Rest and One-vs-One classifiers

Simulating T1- and T2-weighted MRI images with arbitrary values of TI or TE, respectively. (Python 3)

Docker container for FiberNavigator for Brainlife.io

Calculating theoretical MRI images with both TI (T1-weighting) and TE (T2-weighting) of choice, from separate T1-weighted and T2-weighted sets of images. (Python 3)

Tool for calculating swelling tablet eroding front's diffusion rate D and the rate of the swelling k from time series of either T2-maps or MRI images in FDF or Text Image format. (Python 3)

Detection and removal of biases from brain MRI using adversarial architectures. This was my final project for CS 231n (Convolutional Neural Networks for Visual Recognition) at Stanford.

MATLAB code for extracting, converting and anonymising files in CTF MEG proprietary format.

Extracting MRI sequence header data (Magnetic field, Echo Time, Frequency, etc.) from JSON files (.json)

k-space weighting and masking for denoising of MRI image without blurring or losing contrast, as well as for brightening of the objects in the image with simultaneous noise reduction (on the example of Agilent FID data). (Python 3)

Normative modelling code to go along with Bethlehem et al. 2018

A Streamlit application in Python with deep learning based models to assess ligament tear as well as the grade of the tear

k-space based details/edges detection in MRI images with optional k-space based denoising and detail control (on the example of Agilent FID data). (Python 3)

Graduate k-space masking for MRI image denoising and blurring (on the example of Agilent FID data). (Python 3)

We developed a guide for researchers in the Netherlands who want to share brain MRI data to help them get started.

Simulating T1-weighted saturation recovery MRI images for arbitrary values of TR from a set of T1-weighted inversion recovery MRI images. (Python 3)

Collection of virtual objects for numerical MR experiments.

Fully supervised, healthy/malignant prostate detection in multi-parametric MRI (T2W, DWI, ADC), using a modified 2D RetinaNet model for medical object detection, built upon a shallow SEResNet backbone.

Code to run and analyze fMRI study of somatosensory detection task

Basic reconstruction scripts for data uploaded to mridata.org

Flexible bidsificator for multimodal datasets