AUTHOR=Nie Xingyu , Li Guang TITLE=Real-Time 2D MR Cine From Beam Eye’s View With Tumor-Volume Projection to Ensure Beam-to-Tumor Conformality for MR-Guided Radiotherapy of Lung Cancer JOURNAL=Frontiers in Oncology VOLUME=Volume 12 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.898771 DOI=10.3389/fonc.2022.898771 ISSN=2234-943X ABSTRACT=Purpose: To minimize computation latency using a predictive strategy to retrieve and project tumor volume onto 2D MR beam eye’s view (BEV) cine from time-resolved four-dimensional magnetic resonance imaging (TR-4DMRI) libraries (inhalation/exhalation) for personalized MR-guided intensity-modulated radiotherapy (IMRT) or volumetric-modulated arc therapy (VMAT). Methods: Two time-series forecasting algorithms, autoregressive (AR) modeling and deep-learning-based long short-term memory (LSTM), were applied to predict diaphragm position in the next 2D BEV cine to identify a motion-matched and hysteresis-accounted image to retrieve the tumor volume from the inhalation/exhalation TR-4DMRI libraries. Three 40s TR-4DMRI (2Hz, 380 images) per patient of eight lung cancer patients were used to create patient-specific inhalation/exhalation 4DMRI libraries, extract diaphragmatic waveforms, and interpolate them to f=4Hz and 8Hz to match 2D cine frame rates. Along a (40•f)-timepoint waveform, 30•f training timepoints were moved forward to produce 3(10•f-1) predictions. The accuracy of position prediction was assessed against the waveform ground truth. The accuracy of tumor volume projections was evaluated using the center-of-mass difference (∆COM) and Dice similarity index against the TR-4DMRI ground truth for both IMRT (six beam angles, 30˚ interval) and VMAT (240/480 beam angles, 1.5˚/0.75˚ interval, at 4/8Hz, respectively). Results: The accuracy of the first-timepoint prediction is 0.36±0.10mm (AR) and 0.62±0.21mm (LSTM) at 4Hz and 0.06±0.02mm (AR) and 0.18±0.06mm (LSTM) at 8Hz. A 10-20% random error in prediction-library matching increases the overall uncertainty slightly. For both IMRT and VMAT, the accuracy of projected tumor volume contours on 2D BEV cine is ∆COM=0.42±0.11mm and DICE=0.97±0.02 at 4Hz and ∆COM=0.08±0.03mm and DICE=1.00±0.00 at 8Hz. Conclusion: This study demonstrates the feasibility of accurately predicting respiratory motion during 2D BEV cine imaging, identifying a motion-matched and hysteresis-accounted tumor volume, and projecting tumor volume contour on 2D BEV cine for real-time assessment of beam-to-tumor conformality, promising for optimal personalized MR-guided radiotherapy.