Skip to content

Latest commit

 

History

History
29 lines (20 loc) · 1.07 KB

README.md

File metadata and controls

29 lines (20 loc) · 1.07 KB

PialNet

Repo for the 2020 UQ Summer School of AI Hackathon project: "Segmentation of Magnetic Resonance Angiography data"

Goal: Providing an automated pial vessel segmentation framework that learns vessels of interest in high-resolution MRA data, from synthetic data.

Input: 3D MRA scans Output: Binary 3D mask of vessels Database: DeepVesselNet synthetic data Methods: ???

Slides from Dr. Saskia Bollmann's pitch can be found here:

https://cloudstor.aarnet.edu.au/plus/s/e4NVp4aU6JYiNAv

Training data examples and validation sample can be found here:

https://cloudstor.aarnet.edu.au/plus/s/o6yxfKA4rBrKNip

The corresponding paper can be found here

https://www.frontiersin.org/articles/10.3389/fnins.2020.592352/full

NB: we cannot provide validation data, but we can show examples and run code on the data on Wiener

Full training data:

https://github.com/giesekow/deepvesselnet/wiki/Datasets

Example 1: DeepVesselNet

https://github.com/giesekow/deepvesselnet/tree/master/dvn

Example 2: BRAVE-NET

https://github.com/prediction2020/brain-vessel-segmentation