Factors affecting the accuracy of respiratory tracking of the image-guided robotic radiosurgery system

Novel utilization and quantification of Xsight diaphragm tracking for respiratory motion compensation in Cyberknife Synchrony treatment of liver tumors

PURPOSE

The Xsight lung tracking system (XLTS) utilizes an advanced image processing algorithm to precisely identify the position of a tumor and determine its location in orthogonal x-ray images, instead of finding fiducials, thereby minimizing the risk of fiducial insertion-related side effects. To assess and gauge the effectiveness of CyberKnife Synchrony in treating liver tumors located in close proximity to or within the diaphragm, we employed the Xsight diaphragm tracking system (XDTS), which was based on the XLTS.

METHODS

We looked back at the treatment logs of 11 patients (8/11 [XDTS], 3/11 [Fiducial-based Target Tracking System-FTTS]) who had liver tumors in close proximity to or within the diaphragm. And the results are compared with the patients who undergo the treatment of FTTS. The breathing data information was calculated as a rolling average to reduce the effect of irregular breathing. We tested the tracking accuracy with a dynamic phantom (18023-A) on the basis of patient-specific respiratory curve.

RESULTS

The average values for the XDTS and FTTS correlation errors were 1.38 ± 0.65  versus 1.50 ± 0.26 mm (superior-inferior), 1.28 ± 0.48  versus 0.40 ± 0.09 mm (left-right), and 0.96 ± 0.32  versus 0.47 ± 0.10 mm(anterior-posterior), respectively. The prediction errors for two methods of 0.65 ± 0.16  versus 5.48 ± 3.33 mm in the S-I direction, 0.34 ± 0.10  versus 1.41 ± 0.76 mm in the A-P direction, and 0.22 ± 0.072  versus 1.22 ± 0.48 mm in the L-R direction. The coverage rate of FTTS slightly less than that of XDTS, such as 96.53 ± 8.19% (FTTS) versus 98.03 ± 1.54 (XDTS). The prediction error, the motion amplitude, and the variation of the respiratory center phase were strongly related to each other. Especially, the higher the amplitude and the variation, the higher the prediction error.

CONCLUSION

The diaphragm has the potential to serve as an alternative to gold fiducial markers for detecting liver tumors in close proximity or within it. We also found that we needed to reduce the motion amplitude and train the respiration of the patients during liver radiotherapy, as well as control and evaluate their breathing.

Revolutionizing radiation therapy: the role of AI in clinical practice

This review provides an overview of the application of artificial intelligence (AI) in radiation therapy (RT) from a radiation oncologist's perspective. Over the years, advances in diagnostic imaging have significantly improved the efficiency and effectiveness of radiotherapy. The introduction of AI has further optimized the segmentation of tumors and organs at risk, thereby saving considerable time for radiation oncologists. AI has also been utilized in treatment planning and optimization, reducing the planning time from several days to minutes or even seconds. Knowledge-based treatment planning and deep learning techniques have been employed to produce treatment plans comparable to those generated by humans. Additionally, AI has potential applications in quality control and assurance of treatment plans, optimization of image-guided RT and monitoring of mobile tumors during treatment. Prognostic evaluation and prediction using AI have been increasingly explored, with radiomics being a prominent area of research. The future of AI in radiation oncology offers the potential to establish treatment standardization by minimizing inter-observer differences in segmentation and improving dose adequacy evaluation. RT standardization through AI may have global implications, providing world-standard treatment even in resource-limited settings. However, there are challenges in accumulating big data, including patient background information and correlating treatment plans with disease outcomes. Although challenges remain, ongoing research and the integration of AI technology hold promise for further advancements in radiation oncology.

Dosimetric impact of phase shifts on Radixact Synchrony tracking system with patient-specific breathing patterns

Purpose

The Synchrony tracking system of Radixact is capable of real‐time tumor tracking by building a correlation model between external light‐emitting diodes on the patient's chest and an internal marker. A phase shift between the chest wall and a lung tumor has been reported. Hence, this study focused on evaluating the accuracy of the tracking system, especially under a patient‐specific breathing pattern with respiratory phase shifts.

Methods

A phantom containing fiducial markers was placed on a moving platform. The intrinsic delivery accuracy was verified with a patient‐specific breathing pattern. Three patient‐specific breathing patterns were then implemented, for which phase shifts, φ, were introduced. Phase shifts with +0.3 s and +1 s were tested for dosimetric aspects, whereas ±0.3, ±0.6, and ±0.8 s shifts were used for tracking accuracy. The resultant dose distributions were analyzed by γ comparison. Dose profiles in the superior‐inferior and lateral directions were compared. Logfiles of the tracking information were extracted from the system and compared with the input breathing pattern. The root mean square (RMS) difference was used to quantify the consistency.

Results

When the φ value was as large as 1 s, a severe inconsistency was observed. The target was significantly underdosed, down to 89% of the originally planned dose. γ analysis revealed that the failed portion was concentrated in the target region. The RMS of the tracking difference was close to 1 mm when φ was ±0.3 s and approximately 4 mm when φ was ±0.8 s. Tracking errors increased with an increase in the degree of phase shifts.

Conclusion

Phase shifts between the patient chest wall and the internal target may hamper treatment delivery and jeopardize treatment using Synchrony Tracking. Hence, a larger planning target volume (PTV) may be necessary if a large phase shift is observed in a patient, especially when an external surrogate shows a lag in motion when compared with the tumor.

Study on Motion Management of Pancreatic Cancer Treated by CyberKnife

Purpose

We investigated the movement characteristics of pancreas and the clinical accuracy of tracking pancreas with the Synchrony Respiratory Tracking System (SRTS) during the CyberKnife treatment. These data provide a clinical data basis for the expansion margins of pancreatic tumor target.

Methods and Materials

Forty-two patients with pancreatic cancer treated by CyberKnife were retrospectively studied. The pancreatic displacement calculated from the x-ray images collected during the time interval between two consecutive movements constituted a data set.

Results

The total mean motion amplitudes and standard deviations of pancreatic tumors in SI, LR, AP, and radial directions were 3.66 ± 1.71 mm, 0.97 ± 0.62 mm, 1.52 ± 1.02 mm, and 1.36 ± 0.49 mm, respectively. The overall mean correlation errors and standard deviations were 0.82 ± 0.46 mm, 0.47 ± 0.33 mm, 0.41 ± 0.24 mm, and 0.98 ± 0.37 mm, respectively. The overall mean prediction errors and standard deviations were 0.57 ± 0.14 mm, 0.62 ± 0.28 mm, 0.39 ± 0.17 mm, and 1.58 ± 0.36 mm, respectively. The correlation errors and prediction errors of pancreatic tumors at different anatomical positions in SI, LR, and AP directions were statistically significant (p < 0.05).

Conclusions

The tumor motion amplitude, the tumor location, and the treatment time are the main factors affecting the tracking accuracy. The pancreatic tumors at different anatomical locations should be treated differently to ensure sufficient dose coverage of the pancreatic target area.

Development of a tracking error prediction system for the CyberKnife Synchrony Respiratory Tracking System with use of support vector regression

PURPOSE

The accuracy of the CyberKnife Synchrony Respiratory Tracking System is dependent on the breathing pattern of a patient. Therefore, the tracking error in each patient must be determined. Support vector regression (SVR) can be used to easily identify the tracking error in each patient. This study aimed to develop a system with SVR that can predict tracking error according to a patient's respiratory waveform.

METHODS

Datasets of the respiratory waveforms of 93 patients were obtained. The feature variables were variation in respiration amplitude, tumor velocity, and phase shift between tumor and the chest wall, and the target variable was tracking error. A learning model was evaluated with tenfold cross-validation. We documented the difference between the predicted and actual tracking errors and assessed the correlation coefficient and coefficient of determination.

RESULTS

The average difference and maximum difference between the actual and predicted tracking errors were 0.57 ± 0.63 mm and 2.1 mm, respectively. The correlation coefficient and coefficient of determination were 0.86 and 0.74, respectively.

CONCLUSION

We developed a system for obtaining tracking error by using SVR. The accuracy of such a system is clinically useful. Moreover, the system can easily evaluate tracking error. We developed a system that can be used to predict the tracking error of SRTS in the CyberKnife Robotic Radiosurgery System using machine learning. The feature variables were the breathing parameters, and the target variable was the tracking error. We used support vector regression algorithm.

Risks and Benefits of Fiducial Marker Placement in Tumor Lesions for Robotic Radiosurgery: Technical Outcomes of 357 Implantations

Simple Summary

Robotic radiosurgery (RRS) allows for the accurate treatment of primary tumors or metastases with high single doses. However, organ motion during or between fractions can lead to imprecise irradiation. We sought to evaluate the risks and advantages of fiducial marker (FM) implantation regarding clinical complications, marker migration, and motion amplitude. Complications were most common in Synchrony^®-tracked lesions affected by respiratory motion, particularly lung lesions. Pneumothoraces and pulmonary bleeding were the most common complications. An increased complication rate was associated with concomitant biopsy sampling and FM implantation. Most FM migration observed in this study occurred after CT-guided placements and clinical FM insertions. The largest motion amplitudes were observed in hepatic and lower lung lobe lesions. This study highlights the benefits of marker implantation, especially in lesions with a large motion amplitude, including hepatic lesions and lesions of the lower lobe of the lung located >100.0 mm from the spine.

Abstract

Fiducial markers (FM) inserted into tumors increase the precision of irradiation during robotic radiosurgery (RRS). This retrospective study evaluated the clinical complications, marker migration, and motion amplitude of FM implantations by analyzing 288 cancer patients (58% men; 63.1 ± 13.0 years) who underwent 357 FM implantations prior to RRS with CyberKnife, between 2011 and 2019. Complications were classified according to the Society of Interventional Radiology (SIR) guidelines. The radial motion amplitude was calculated for tumors that moved with respiration. A total of 725 gold FM was inserted. SIR-rated complications occurred in 17.9% of all procedures. Most complications (32.0%, 62/194 implantations) were observed in Synchrony^®-tracked lesions affected by respiratory motion, particularly in pulmonary lesions (46.9% 52/111 implantations). Concurrent biopsy sampling was associated with a higher complication rate (p = 0.001). FM migration occurred in 3.6% after CT-guided and clinical FM implantations. The largest motion amplitudes were observed in hepatic (20.5 ± 11.0 mm) and lower lung lobe (15.4 ± 10.5 mm) lesions. This study increases the awareness of the risks of FM placement, especially in thoracic lesions affected by respiratory motion. Considering the maximum motion amplitude, FM placement remains essential in hepatic and lower lung lobe lesions located >100.0 mm from the spine.

Comparison of modeling accuracy between Radixact®and CyberKnife®Synchrony®respiratory tracking system

Synchrony Respiratory Tracking system adapted from CyberKnife has been introduced in Radixact to compensate the tumor motion caused by respiration. This study aims to compare the modeling accuracy of the Synchrony system between Radixact and CyberKnife. Two Synchrony plans based on fiducial phantoms were created for CyberKnife and Radixact, respectively. Different respiratory motion traces were used to drive a motion platform to move along the superoinferior and left-right direction. The cycle time and the amplitude of target/surrogate motion of one selected motion trace were scaled to investigate the dependence of modeling accuracy on the motion characteristic. The predicted target position, the correlation error, potential difference (Radixact only) and standard error (CyberKnife only) were extracted from raw data or log files of the two systems. The modeling accuracy was evaluated by calculating the root-mean-square (RMS) error between the predicted target positions and the input motion trace. A threshold T95 within which 95% of the potential difference or the standard error lay was defined and evaluated. Except for the motion trace with a small amplitude and a good (linear) correlation between target and surrogate motion, Radixact showed smaller RMS errors than CyberKnife. The RMS error of both systems increased with the motion amplitude and showed a decreasing trend with the increasing cycle time. No correlation was found between the RMS error and the amplitude of surrogate motion. T95 could be a good estimator of modeling accuracy for CyberKnife rather than Radixact. The correlation error defined in Radixact were largely affected by the number of fiducial markers and the setup error. In general, the modeling accuracy of the Radixact Synchrony system is better than that of the CyberKnife Synchrony system under unfavorable conditions.

Patient-specific PTV margins for liver stereotactic body radiation therapy determined using support vector classification with an early warning system for margin adaptation

PURPOSE

An adaptive planning target volume (PTV) margin strategy incorporating a volumetric tracking error assessment after each fraction is proposed for robotic stereotactic body radiation therapy (SBRT) liver treatments.

METHODS AND MATERIALS

A supervised machine learning algorithm employing retrospective data, which emulates a dry-run session prior to planning, is used to investigate if motion tracking errors are <2 mm, and consequently, planning target volume (PTV) margins can be reduced. A fraction of data collected during the beginning of a treatment course emulates a dry-run session (mock) before planning. Twenty features are calculated using mock data and used for support vector classification (SVC). A treatment course is labeled as Class 1 if the maximum root-mean-square radial tracking error for all remaining fractions is below 2 mm, or Class 2 otherwise. We evaluate the classification using fivefold cross-validation, leave-one-out cross-validation, 500 repeated random subsampling cross-validation, and the receiver operating characteristic (ROC) metric. The classification is independently cross-validated on a cohort of 48 treatment plans for other anatomical sites. A per fraction assessment of volumetric tracking errors is performed for the standard 5 mm PTV margin (PTV_std ) for courses predicted as Class 2; or for a margin reduced by 2 mm (PTV_std-2mm ) for those predicted as Class 1. We perturb the gross tumor volume (GTV) by the tracking errors for each x-ray image acquisition and calculate the fractional GTV voxel occupancy probability (P_i ) inside the PTV for each treatment fraction i. For treatment courses classified as Class 1, an early warning system flags treatment courses having any P_i  < 0.99, and the subsequent treatments are proposed to be replanned using PTV_std .

RESULTS

The classification accuracies are 0.84 ± 0.06 using fivefold cross-validation, and 0.77 when validated using an independent testing set (other anatomical sites). Eighty percent of treatment courses are correctly classified using leave-one-out cross-validation. The sensitivity, precision, specificity, F1 score, and accuracy are 0.81 ± 0.09, 0.85 ± 0.08, 0.80 ± 0.11, 0.83 ± 0.06, and 0.80 ± 0.07, respectively, using 500 repeated random subsampling cross-validation. The area under the curve for the ROC metric is 0.87 ± 0.05. The four most important features for classification are related to standard deviations of motion tracking errors, the linearity between the target location and external LED marker positions, and marker radial motion amplitudes. Eleven of 64 cases predicted to be of Class 1 have 0.96 < P_i  < 0.99 for each treatment fraction, and require replanning using PTV_std . In comparison, the PTV_std always covers the perturbed GTVs with P_i  > 0.99 for all patients.

CONCLUSIONS

Support vector classification is proposed for the classification of different motion tracking errors for patient courses based on a mock session before planning for SBRT liver treatments. It is feasible to implement patient-specific PTV margins in the clinic, assisted with an early warning system to flag treatment courses that require replanning using larger PTV margins in an adaptive treatment strategy.