To enable magnetic resonance imaging (MRI)-guided radiotherapy with real-time adaptation, motion must be quickly estimated with low latency. The motion estimate is used to adapt the radiation beam to the current anatomy, yielding a more conformal dose distribution. As the MR acquisition is the largest component of latency, deep learning (DL) may reduce the total latency by enabling much higher undersampling factors compared to conventional reconstruction and motion estimation methods. The benefit of DL on image reconstruction and motion estimation was investigated for obtaining accurate deformation vector fields (DVFs) with high temporal resolution and minimal latency. 2D cine MRI acquired at 1.5 T from 135 abdominal cancer patients were retrospectively included in this study. Undersampled radial golden angle acquisitions were retrospectively simulated. DVFs were computed using different combinations of conventional- and DL-based methods for image reconstruction and motion estimation, allowing a comparison of four approaches to achieve real-time motion estimation. The four approaches were evaluated based on the end-point-error and root-mean-square error compared to a ground-truth optical flow estimate on fully-sampled images, the structural similarity (SSIM) after registration and time necessary to acquire k-space, reconstruct an image and estimate motion. The lowest DVF error and highest SSIM were obtained using conventional methods up to . For undersampling factors , the lowest DVF error and highest SSIM were obtained using conventional image reconstruction and DL-based motion estimation. We have found that, with this combination, accurate DVFs can be obtained up to with an average root-mean-square error up to 1 millimeter and an SSIM greater than 0.8 after registration, taking 60 milliseconds. High-quality 2D DVFs from highly undersampled k-space can be obtained with a high temporal resolution with conventional image reconstruction and a deep learning-based motion estimation approach for real-time adaptive MRI-guided radiotherapy.

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.

Skeletons are well-known descriptors used for analysis and processing of 2D binary images. Recently, dense skeletons have been proposed as an extension of classical skeletons as a dual encoding for 2D grayscale and color images. Yet, their encoding power, measured by the quality and size of the encoded image, and how these metrics depend on selected encoding parameters, has not been formally evaluated. In this paper, we fill this gap with two main contributions. First, we improve the encoding power of dense skeletons by effective layer selection heuristics, a refined skeleton pixel-chain encoding, and a postprocessing compression scheme. Secondly, we propose a benchmark to assess the encoding power of dense skeletons for a wide set of natural and synthetic color and grayscale images. We use this benchmark to derive optimal parameters for dense skeletons. Our method, called Compressing Dense Medial Descriptors (CDMD), achieves higher-compression ratios at similar quality to the well-known JPEG technique and, thereby, shows that skeletons can be an interesting option for lossy image encoding.

No abstract