{"id":381,"date":"2021-08-04T23:45:08","date_gmt":"2021-08-04T23:45:08","guid":{"rendered":"https:\/\/mri.sbollmann.net\/?p=381"},"modified":"2021-08-29T23:43:34","modified_gmt":"2021-08-29T23:43:34","slug":"showcase-event-1-ml-ai-in-imaging","status":"publish","type":"post","link":"https:\/\/mri.sbollmann.net\/index.php\/2021\/08\/04\/showcase-event-1-ml-ai-in-imaging\/","title":{"rendered":"ML4AU – Showcase event ML\/AI in Imaging"},"content":{"rendered":"\n

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<\/a> that was trained with purely synthetic data describing the forward problem and the network learns an efficient inversion of this. I showed the challenges of the first prototypes and how we are addressing these in the current works to enable a translation of this technique to a clinical MRI system. A second example shows the use of deep learning in predicting calibration data of the MRI system<\/a> and how we inform a physics calculation with this initial prediction to make sure that the results are plausible and deliver a robust imaging result. Finally, I highlighted some of the open-source aspects of this work<\/a> and show how we shared the data, model and training code with the MRI community<\/a> to make it easier to build on our work and improve it further.<\/p>\n\n\n\n

This is the talk recording:<\/p>\n\n\n\n

\n