Stability of conventional and machine learning-based tumor auto-segmentation techniques using undersampled dynamic radial bSSFP acquisitions on a 0.35 T hybrid MR-linac system

Abstract

Purpose: Hybrid MRI-linear accelerator systems (MR-linacs) allow for the incorporation of MR images with high soft-tissue contrast into the radiation therapy procedure prior to, during, or post irradiation. This allows not only for the optimization of the treatment planning, but also for real-time monitoring of the tumor position using cine MRI, from which intrafractional motion can be compensated. Fast imaging and accurate tumor tracking are crucial for effective compensation. This study investigates the application of cine MRI with a radial acquisition scheme on a low-field MR-linac to accelerate the acquisition rate and evaluates the effect on tracking accuracy.

Methods: An MR sequence using tiny golden-angle radial k-space sampling was developed and applied to cine imaging on patients with liver tumors on a 0.35 T MR-linac. Tumor tracking was assessed for accuracy and stability from the cine images with increasing k-space undersampling factors. Tracking was achieved using two different auto-segmentation algorithms: a deformable image registration B-spline similar to that implemented on the MR-linac and a convolutional neural network approach known as U-Net.

Results: Radial imaging allows for increased temporal resolution with reliable tumor tracking, although tracking robustness decreases as temporal resolution increases. Additional acquisition-based artifacts can be avoided by reducing the angle increment using tiny golden-angles. The U-net algorithm was found to have superior auto-segmentation metrics compared to B-spline. U-net was able to track two well-defined tumors, imaged with just 30 spokes per image (10.6 frames per second), with an average Dice coefficient ≥ 83%, Hausdorff distance ≤ 1.4 pixel, and mean contour distance ≤ 0.5 pixel.

Conclusions: Radial acquisitions are commonplace in dynamic imaging; however, in MR-guided radiotherapy, robust tumor tracking is also required. This study demonstrates the in vivo feasibility of tumor tracking from radially acquired images on a low-field MR-linac. Radial imaging allows for decreased image acquisition times while maintaining robust tracking. The U-net algorithm can track a tumor with higher accuracy in images with undersampling artifacts than a conventional deformable B-spline algorithm and is a promising tool for tracking in MR-guided radiation therapy.

Keywords: MR-linac; auto-segmentation; golden-angle; machine learning; tumor tracking.