Real‐time 3D motion estimation from undersampled MRI using multi‐resolution neural networks. Issue 11 (26th October 2021)

• Record Type: Journal Article
• Authors: Terpstra, Maarten L.; Maspero, Matteo; Bruijnen, Tom; Verhoeff, Joost J.C.; Lagendijk, Jan J.W.; van den Berg, Cornelis A.T.
• Is Part Of: Medical physics. Volume 48:Issue 11(2021)
• Page Start: 6597
• Page End: 6613
• Publication Date: 2021-10-26
• Subjects: deep learning -- artificial intelligence -- MRI -- radiotherapy -- registration -- motion estimation -- MRI‐guided radiotherapy -- adaptive radiotherapy -- MR‐Linac; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.15217
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract: Purpose : To enable real‐time adaptive magnetic resonance imaging–guided radiotherapy (MRIgRT) by obtaining time‐resolved three‐dimensional (3D) deformation vector fields (DVFs) with high spatiotemporal resolution and low latency ( < 500 ms). Theory and Methods : Respiratory‐resolved T 1 ‐weighted 4D‐MRI of 27 patients with lung cancer were acquired using a golden‐angle radial stack‐of‐stars readout. A multiresolution convolutional neural network (CNN) called TEMPEST was trained on up to 32 × retrospectively undersampled MRI of 17 patients, reconstructed with a nonuniform fast Fourier transform, to learn optical flow DVFs. TEMPEST was validated using 4D respiratory‐resolved MRI, a digital phantom, and a physical motion phantom. The time‐resolved motion estimation was evaluated in‐vivo using two volunteer scans, acquired on a hybrid MR‐scanner with integrated linear accelerator. Finally, we evaluated the model robustness on a publicly‐available four‐dimensional computed tomography (4D‐CT) dataset. Results : TEMPEST produced accurate DVFs on respiratory‐resolved MRI at 20‐fold acceleration, with the average end‐point‐error < 2 mm, both on respiratory‐sorted MRI and on a digital phantom. TEMPEST estimated accurate time‐resolved DVFs on MRI of a motion phantom, with an error < 2 mm at 28 × undersampling. On two volunteer scans, TEMPEST accurately estimated motion compared to the self‐navigation signal using 50 spokes per dynamic (366 × undersampling). At this undersampling factor, DVFs were estimated within 200 ms, including MRI acquisition. On fully sampled CT data, we achieved a target registration error of 1.87 ± 1.65 mm without retraining the model. Conclusion : A CNN trained on undersampled MRI produced accurate 3D DVFs with high spatiotemporal resolution for MRIgRT.