Artificial intelligence‐based framework in evaluating intrafraction motion for liver cancer robotic stereotactic body radiation therapy with fiducial tracking

Abstract

Purpose This study aimed to design a fully automated framework to evaluate intrafraction motion using orthogonal x‐ray images from CyberKnife. Methods The proposed framework includes three modules: (a) automated fiducial marker detection, (b) three‐dimensional (3D) position reconstruction, and (c) intrafraction motion evaluation. A total of 5927 images from real patients treated with CyberKnife fiducial tracking were collected. The ground truth was established by labeling coarse bounding boxes manually, and binary mask images were then obtained by applying a binary threshold and filter. These images and labels were used to train a detection model using a fully convolutional network (fCN). The output of the detection model can be used to reconstruct the 3D positions of the fiducial markers and then evaluate the intrafraction motion via a rigid transformation. For a patient test, the motion amplitudes, rotations, and fiducial cohort deformations were calculated used the developed framework for 13 patients with a total of 52 fractions. Results The precision and recall of the fiducial marker detection model were 98.6% and 95.6%, respectively, showing high model performance. The mean (±SD) centroid error between the predicted fiducial markers and the ground truth was 0.25 ± 0.47 pixels on the test data. For intrafraction motion evaluation, the mean (±SD) translations in the superior–posterior (SI), left–right (LR), and anterior–posterior (AP) directions were 13.1 ± 2.2 mm, 2.0 ± 0.4 mm, and 5.2 ± 1.4 mm, respectively, and the mean (±SD) rotations in the roll, pitch and yaw directions were 2.9 ± 1.5°, 2.5 ± 1.5°, and 3.1 ± 2.2°. Seventy‐one percent of the fractions had rotations larger than the system limitations. With rotation correction during rigid registration, only 2 of the 52 fractions had residual errors larger than 2 mm in any direction, while without rotation correction, the probability of large residual errors increased to 46.2%. Conclusion We developed a framework with high performance and accuracy for automatic fiducial marker detection, which can be used to evaluate intrafraction motion using orthogonal x‐ray images from CyberKnife. For liver patients, most fractions have fiducial cohort rotations larger than the system limitations; however, the fiducial cohort deformation is small, especially for the scenario with rotation correction.

A review of artificial intelligence applications for motion tracking in radiotherapy

“…The use of AI for marker‐based tracking approaches has been demonstrated to be highly accurate through several studies. All of the marker‐based tracking approaches discussed achieved sub‐millimetre accuracy 33,44,45 . Mylonas et al 33 .…”

“…Mylonas et al 33 . and Liang et al 44 . use different DL approaches due to the differences in the image acquisition methods.…”

“…However, this approach is not suitable for the discrete X‐ray image acquisition method used by CyberKnife. To overcome this, Liang et al 44 . utilised the U‐Net architecture to perform semantic segmentation of the markers in full‐size X‐ray images.…”

“…This learning period has the drawback of subjecting the patient to additional radiation due to the extra imaging dose. DL methods have been successfully used for the automatic detection of markers in X‐ray and MRI images to overcome these issues 33,44,45 …”

“…A study by Liang et al 44 . presented an automated framework that was used to evaluate intrafraction motion in X‐ray images acquired by CyberKnife.…”