Containers
ReproNim Talk about Neurodesk
I was recently invited to talk about Neurodesk in the ReproNim webinar. The recording of the talk is available here: The slides are available here:
Deep Learning
NeXtQSM—A complete deep learning pipeline for data-consistent Quantitative Susceptibility Mapping trained with hybrid data
Our latest work just got published in Medical Image Analysis: Deep learning based Quantitative Susceptibility Mapping (QSM) has shown great potential in recent years, obtaining similar results to established non-learning approaches. Many current deep learning approaches are not data consistent, require in vivo training data or solve the QSM problem Read more…
Conferences
Talk about Open Data and Neurodesk at MRItogether
This week I gave a talk about the Open Data ecosystem and how our open-source project https://NeuroDesk.org makes it very easy to access and publish open data. Here is the recording: Here are the slides:
Data management
TOMCAT dataset on Oracle Open Data
Oracle Cloud recently launched a platform to host scientific datasets and we uploaded our unique Hippocampus dataset (Towards Optimising MRI Characterisation of Tissue (TOMCAT) Dataset including all Longitudinal Automatic Segmentation of Hippocampal Subfields (LASHiS) data – ScienceDirect): https://opendata.oraclecloud.com/ords/r/opendata/opendata/details?data_set_id=28&bucket_name=TOMCAT&prefix=&clear=RR&session=610618357889967&cs=1o7GdDLNfm3PHWwxI2thFXrA8jHPcvjZCdFibkYYIPPofNfOuvVt8B6S0B7YTnzIOf6cDk9BXW5hSV9b8LmhoQA More background can be found in this blogpost: Oracle Open Data platform Read more…
Python
Combining conda and google colab
Sometimes it’s necessary to downgrade packages in google colab to restore compatibility with an older version (e.g. pytorch). One way of doing this is using conda within colab and a few tricks make this work. Here is the colab notebook: https://colab.research.google.com/drive/1W5UnflB8m1zo6lP1y11V78QczMRBI0FE?usp=sharing Here a quick code gist:
Containers
Behind the scenes of NeuroDesk : What we learned so far in building and distributing containers in a community driven fashion
These are the slides for the talk I gave at the ARCOS Symposium in November 2021:
Containers
QSMxT: Robust masking and artifact reduction for quantitative susceptibility mapping
Our article “QSMxT: Robust masking and artifact reduction for quantitative susceptibility mapping” was just published in MRM 🙂 In this article we developed an automated, scalable, and robust QSM workflow that starts from Dicom images and produces segmentations of regions of interest: The full paper is here (unfortunately behind a Read more…
CloudStor
Neurodesk at the ANZ ISMRM reproducibility workshop
We had the fantastic opportunity to present the neurodesk project in today’s ANZ ISMRM reproducibility workshop. The 50 participants across Australia got to see the first live demo of the project and I am glad everything worked out and ran smoothly 🙂 We will post the recordings as soon as Read more…
CloudStor
Interoperability Between AARNet Cloudstor and External Services – Researcher Talks Webinar
I had the great opportunity to present in the AARnet Reseracher Talks webinar Winter Series 2021 and in this Research Showcase Webinar I highlighted interoperability examples between AARnet CloudStor with external tools and services like Zotero, the open science foundation (OSF) or high-performance computing clusters. I showed how CloudStor can Read more…
Deep Learning
ML4AU – Showcase event ML/AI in Imaging
I recently had the wonderful opportunity to present our deep learning work in magnetic resonance imaging at the ML4AU CoP showcase event to more than 65 participants. I showed one example on efficiently solving an ill-posed inverse problem for quantitative susceptibility mapping that was trained with purely synthetic data describing Read more…