Massively parallel Monte Carlo diffusion MR simulator written in Python.

Last update: Nov 11, 2022

Overview

Disimpy

Disimpy is a Python package for generating simulated diffusion-weighted MR signals that can be useful in the development and validation of data acquisition and analysis methods. The data is generated by Monte Carlo random walk simulations that run in massively parallel on Nvidia CUDA-capable GPUs. If you use Disimpy in work that leads to a scientific publication, please cite [1], where the details about signal generation can also be found.

Requirements and installation

Follow the installation instructions.

Usage example

Read the tutorial to learn how to use Disimpy.

Validation

Disimpy's functionality has been validated by comparing its results to analytical solutions and to results from other simulators (e.g., Camino and MISST), and by automated testing (disimpy.tests). Examples of simulations used for validation are provided here. However, Disimpy is research software and some bugs undoubtedly remain. If you find any of them or encounter unexpected behaviour, please open an issue on GitHub.

Contribute

If you want to contribute to the development of Disimpy, start by reading the contributing guidelines.

Support

If you have questions or need help, open an issue on Github.

References

[1]	Kerkelä et al., (2020). Disimpy: A massively parallel Monte Carlo simulator for generating diffusion-weighted MRI data in Python. Journal of Open Source Software, 5(52), 2527. https://doi.org/10.21105/joss.02527

Massively parallel Monte Carlo diffusion MR simulator written in Python.

Related tags

Overview

Disimpy

Requirements and installation

Usage example

Validation

Contribute

Support

References

Owner

Leevi

An end-to-end PyTorch framework for image and video classification

Walk with fastai

Repository aimed at compiling code, papers, demos etc.. related to my PhD on 3D vision and machine learning for fruit detection and shape estimation at the university of Lincoln

Deep Ensemble Learning with Jet-Like architecture

LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

Deep Learning Based Fasion Recommendation System for Ecommerce

PyTorch code for DriveGAN: Towards a Controllable High-Quality Neural Simulation

The Noise Contrastive Estimation for softmax output written in Pytorch

Medical-Image-Triage-and-Classification-System-Based-on-COVID-19-CT-and-X-ray-Scan-Dataset

Pull sensitive data from users on windows including discord tokens and chrome data.

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Code for the CVPR2021 workshop paper "Noise Conditional Flow Model for Learning the Super-Resolution Space"

This is the implementation of the paper "Self-supervised Outdoor Scene Relighting"

Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation.

Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://arxiv.org/abs/2103.06332).

Planning from Pixels in Environments with Combinatorially Hard Search Spaces -- NeurIPS 2021

Fine-tune pretrained Convolutional Neural Networks with PyTorch

The code used for the free [email protected] Webinar series on Reinforcement Learning in Finance

Sign Language Transformers (CVPR'20)

Forecasting for knowable future events using Bayesian informative priors (forecasting with judgmental-adjustment).