Meeting Banner
Abstract #1142

BoneMRI of the cervical spine: Deep learning-based radiodensity contrast generation for selective visualization of osseous structures

Marijn van Stralen1,2, Britt YM van der Kolk3, Frank Zijlstra1, Mateusz C Florkow1, Elco Oost4, Jorik Slotman5, Jochen AC van Osch6, Martin Podlogar7, Jeroen Hendrikse8, Pim de Jong8, Rene M Castelein9, Max A Viergever1, Mario Maas10, Martijn F Boomsma11, and Peter R Seevinck1,2

1Center for Image Sciences, UMC Utrecht, Utrecht, Netherlands, 2MRIguidance BV, Utrecht, Netherlands, 3Dept. of Emergency Medicine, Isala, Zwolle, Netherlands, 4Image Sciences & Linguistics, MRIguidance BV, Utrecht, Netherlands, 5University of Twente, Enschede, Netherlands, 6Dept. of Medical Physics, Isala, Zwolle, Netherlands, 7Dept. of Neurosurgery, Isala, Zwolle, Netherlands, 8Dept of Radiology, UMC Utrecht, Utrecht, Netherlands, 9Dept of Orthopedics, UMC Utrecht, Utrecht, Netherlands, 10Dept of Radiology and Nuclear Medicine, Academic Medical Center, Amsterdam, Netherlands, 11Dept of Radiology and Nuclear Medicine, Isala, Zwolle, Netherlands

In this work BoneMRI is presented, a deep learning approach aiming at visualisation of radiodensity contrast by learning a mapping from MRI to CT data from 25 patients. Normal as well as pathological osseous structures in the cervical spine were clearly depicted. Quantitatively, radiodensity contrast similarity and high geometrical accuracy of vertebral dimensions was demonstrated. As BoneMRI is a 3D method it facilitates multiplanar reformatting in any desired direction. As such, BoneMRI is a promising tool for efficient morphological assessment of osseous structures without the need for ionizing radiation, simultaneously providing soft tissue contrasts in a single examination.

This abstract and the presentation materials are available to members only; a login is required.

Join Here