The digitalisation of radiology: launching our Machine Learning challenge!
The digital transformation plays an essential role in the industries we operate in. Within the radiology sector, the digitalisation of our systems has been put into action over the past couple of years, and we’ve also seen the emergence of the new technologies such as Artificial Intelligence, Internet of Things, Cybersecurity and Big Data.
Based on the four pillars of Thales’ digital transformation, we aim to advance innovation in order to simplify the tasks of medical professionals so that they can focus on what’s most important, their patients.
With the help of our partners, Kaizen Solutions and the Data Institute, we’re launching an Artificial Intelligence challenge, which focuses on Machine Learning*, on Thursday 21st March. On this day, access to the online platform Codalab, where the challenge will be published, will go live. The challenge will also then be promoted in April at the conference organised by our partner Kaizen Solutions.
As part of this initiative, we hope to collaborate with the engineers of tomorrow and show the world our commitment to innovation. The goal of participants will be to find a solution that allows the completion of one step of the calibration of X-ray images by creating a Machine Learning algorithm.
This algorithm will be used within the framework of a “3D4CARM” project introduced by Thales, focused on facilitating the production of 3D images during surgical operations with the help of a mobile radiology system called C-ARM. The goal of the algorithm will be to localise the X-ray generator and detector in order to generate these 3D images, using 2D images as a base.
The conclusion of the challenge is scheduled for this summer, when the €3000 prize will be presented and split between three winners.
We encourage both students and experts in this domain to participate and join us in our goal of advancing healthcare innovation!
*Machine Learning consists of teaching a system to carry out actions or execute tasks by itself.