Markerless tracking of tumor and tissues: A motion model approach

BACKGROUND

Respiratory motion management is essential in order to achieve high-precision radiotherapy. Markerless motion tracking of tumor can provide a non-invasive way to manage respiratory motion, thereby enhancing treatment accuracy. However, the low contrast in real-time x-ray images for image guidance limits the application of markerless tracking.

PURPOSE

We present a novel approach based on a motion model to perform markerless tracking of tumor and surrounding tissues even when they have low contrast in real-time x-ray images.

METHODS

A proof-of-concept validation of the method has been performed using digital and physical phantoms at breathing conditions that are significantly different than the planning stage. A motion model is first constructed by performing principal component analysis (PCA) on the planning 4DCT. During treatment, the motion of a surrogate is tracked and used as the input of the motion model, which generates a 3D real-time volume estimation. Such 3D estimation is then projected to 2D to create digitally reconstructed radiographs (DRRs). The relationships between the real-time DRRs, reference DRRs, and reference x-ray images are first established to simulate 2D real-time images from the real-time volume. The registration between the simulated 2D real-time images and real-time x-ray images corrects the initial motion model estimation to ensure the estimated volume matches the real-time condition.

RESULTS

In digital phantom, the Dice index of pancreas was improved from 0.74 to 0.78 after correction using real-time DRRs in fully inhaled phase. Validation on lung and pancreas is performed in physical phantom with two motion traces. The surrogate-tumor relationships were intentionally altered to generate large target localization errors due to the differences in body condition between treatment planning stage and during treatment. The real-time correction for the estimated 3D real-time volume was performed using a pair of 2D x-ray images. For the deep breathing motion trace, the tumor localization mean absolute error (MAE) throughout the tracking decreases from around 3 mm to less than 1 mm after correction. For the shallow breathing motion trace with a 1.7 mm baseline shift, the tumor localization MAE throughout the tracking decreases from around 1.5 mm to less than 1 mm after correction.

CONCLUSION

The method combines the detailed structural information from planning 4DCT and real-time information from real-time x-ray images through a motion model. The matching between the real-time model estimation and 2D real-time images is performed in the same modality so that it can be applied to regions with low contrast in the images. The real-time images successfully corrected the initial motion model estimations in our proof-of-concept validation. This suggests the potential to perform markerless tracking in low-contrast region using a motion model.

Deep learning-based target decomposition for markerless lung tumor tracking in radiotherapy

BACKGROUND

In radiotherapy, real-time tumor tracking can verify tumor position during beam delivery, guide the radiation beam to target the tumor, and reduce the chance of a geometric miss. Markerless kV x-ray image-based tumor tracking is challenging due to the low tumor visibility caused by tumor-obscuring structures. Developing a new method to enhance tumor visibility for real-time tumor tracking is essential.

PURPOSE

To introduce a novel method for markerless kV image-based tracking of lung tumors via deep learning-based target decomposition.

METHODS

We utilized a conditional Generative Adversarial Network (cGAN), known as Pix2Pix, to build a patient-specific model and generate the synthetic decomposed target image (sDTI) to enhance tumor visibility on the real-time kV projection images acquired by the onboard kV imager equipped on modern linear accelerators. We used 4DCT simulation images to generate the digitally reconstructed radiograph (DRR) and DTI image pairs for model training. We augmented the training dataset by randomly shifting the 4DCT in the superior-inferior, anterior-posterior, and left-right directions during the DRR and DTI generation process. We performed real-time 2D tumor tracking via template matching between the DTI generated from the CT simulation and the sDTI generated from the real-time kV projection images. We validated the proposed method using nine patients' datasets with implanted beacons near the tumor.

RESULTS

The sDTI can effectively improve the image contrast around the lung tumors on the kV projection images for the nine patients. With the beacon motion as ground truth, the tracking errors were on average 0.8 ± 0.7 mm in the superior-inferior (SI) direction and 0.9 ± 0.8 mm in the in-plane left-right (IPLR) direction. The percentage of successful tracking, defined as a tracking error less than 2 mm in the SI direction, is 92.2% on the 4312 tested images. The patient-specific model took approximately 12 h to train. During testing, it took approximately 35 ms to generate one sDTI, and 13 ms to perform the tumor tracking using template matching.

CONCLUSIONS

Our method offers the potential solution for nearly real-time markerless lung tumor tracking. It achieved a high level of accuracy and an impressive tracking rate. Further development of 3D lung tumor tracking is warranted.

Deep learning-based markerless lung tumor tracking in stereotactic radiotherapy using Siamese networks

BACKGROUND

Radiotherapy (RT) is involved in about 50% of all cancer patients, making it a very important treatment modality. The most common type of RT is external beam RT, which consists of delivering the radiation to the tumor from outside the body. One novel treatment delivery method is volumetric modulated arc therapy (VMAT), where the gantry continuously rotates around the patient during the radiation delivery.

PURPOSE

Accurate tumor position monitoring during stereotactic body radiotherapy (SBRT) for lung tumors can help to ensure that the tumor is only irradiated when it is inside the planning target volume. This can maximize tumor control and reduce uncertainty margins, lowering organ-at-risk dose. Conventional tracking methods are prone to errors, or have a low tracking rate, especially for small tumors that are in close vicinity to bony structures.

METHODS

We investigated patient-specific deep Siamese networks for real-time tumor tracking, during VMAT. Due to lack of ground truth tumor locations in the kilovoltage (kV) images, each patient-specific model was trained on synthetic data (DRRs), generated from the 4D planning CT scans, and evaluated on clinical data (x-rays). Since there are no annotated datasets with kV images, we evaluated the model on a 3D printed anthropomorphic phantom but also on six patients by computing the correlation coefficient with the breathing-related vertical displacement of the surface-mounted marker (RPM). For each patient/phantom, we used 80% of DRRs for training and 20% for validation.

RESULTS

The proposed Siamese model outperformed the conventional benchmark template matching-based method (RTR): (1) when evaluating both methods on the 3D phantom, the Siamese model obtained a 0.57-0.79-mm mean absolute distance to the ground truth tumor locations, compared to 1.04-1.56 mm obtained by RTR; (2) on patient data, the Siamese-determined longitudinal tumor position had a correlation coefficient of 0.71-0.98 with the RPM, compared to 0.07-0.85 for RTR; (3) the Siamese model had a 100% tracking rate, compared to 62%-82% for RTR.

CONCLUSIONS

Based on these results, we argue that Siamese-based real-time 2D markerless tumor tracking during radiation delivery is possible. Further investigation and development of 3D tracking is warranted.

Markerless motion tracking with simultaneous MV and kV imaging in spine SBRT treatment-a feasibility study

Objective. Motion tracking with simultaneous MV-kV imaging has distinct advantages over single kV systems. This research is a feasibility study of utilizing this technique for spine stereotactic body radiotherapy (SBRT) through phantom and patient studies.Approach. A clinical spine SBRT plan was developed using 6xFFF beams and nine sliding-window IMRT fields. The plan was delivered to a chest phantom on a linear accelerator. Simultaneous MV-kV image pairs were acquired during beam delivery. KV images were triggered at predefined intervals, and synthetic MV images showing enlarged MLC apertures were created by combining multiple raw MV frames with corrections for scattering and intensity variation. Digitally reconstructed radiograph (DRR) templates were generated using high-resolution CBCT reconstructions (isotropic voxel size (0.243 mm)3) as the reference for 2D-2D matching. 3D shifts were calculated from triangulation of kV-to-DRR and MV-to-DRR registrations. To evaluate tracking accuracy, detected shifts were compared to known phantom shifts as introduced before treatment. The patient study included a T-spine patient and an L-spine patient. Patient datasets were retrospectively analyzed to demonstrate the performance in clinical settings.Main results. The treatment plan was delivered to the phantom in five scenarios: no shift, 2 mm shift in one of the longitudinal, lateral and vertical directions, and 2 mm shift in all the three directions. The calculated 3D shifts agreed well with the actual couch shifts, and overall, the uncertainty of 3D detection is estimated to be 0.3 mm. The patient study revealed that with clinical patient image quality, the calculated 3D motion agreed with the post-treatment cone beam CT. It is feasible to automate both kV-to-DRR and MV-to-DRR registrations using a mutual information-based method, and the difference from manual registration is generally less than 0.3 mm.Significance. The MV-kV imaging-based markerless motion tracking technique was validated through a feasibility study. It is a step forward toward effective motion tracking and accurate delivery for spinal SBRT.

Effect of different noise reduction techniques and template matching parameters on markerless tumor tracking using dual-energy imaging

PURPOSE

To evaluate the impact of various noise reduction algorithms and template matching parameters on the accuracy of markerless tumor tracking (MTT) using dual-energy (DE) imaging.

METHODS

A Varian TrueBeam linear accelerator was used to acquire a series of alternating 60 and 120 kVp images (over a 180° arc) using fast kV switching, on five early-stage lung cancer patients. Subsequently, DE logarithmic weighted subtraction was performed offline on sequential images to remove bone. Various noise reduction techniques-simple smoothing, anticorrelated noise reduction (ACNR), noise clipping (NC), and NC-ACNR-were applied to the resultant DE images. Separately, tumor templates were generated from the individual planning CT scans, and band-pass parameter settings for template matching were varied. Template tracking was performed for each combination of noise reduction techniques and templates (based on band-pass filter settings). The tracking success rate (TSR), root mean square error (RMSE), and missing frames (percent unable to track) were evaluated against the estimated ground truth, which was obtained using Bayesian inference.

RESULTS

DE-ACNR, combined with template band-pass filter settings of σ_low  = 0.4 mm and σ_high  = 1.6 mm resulted in the highest TSR (87.5%), RMSE (1.40 mm), and a reasonable amount of missing frames (3.1%). In comparison to unprocessed DE images, with optimized band-pass filter settings of σ_low  = 0.6 mm and σ_high  = 1.2 mm, the TSR, RMSE, and missing frames were 85.3%, 1.62 mm, and 2.7%, respectively. Optimized band-pass filter settings resulted in improved TSR values and a lower missing frame rate for both unprocessed DE and DE-ACNR as compared to the use previously published band-pass parameters based on single energy kV images.

CONCLUSION

Noise reduction strategies combined with the optimal selection of band-pass filter parameters can improve the accuracy and TSR of MTT for lung tumors when using DE imaging.

The markerless lung target tracking AAPM Grand Challenge (MATCH) results

PURPOSE

Lung stereotactic ablative body radiotherapy (SABR) is a radiation therapy success story with level 1 evidence demonstrating its efficacy. To provide real-time respiratory motion management for lung SABR, several commercial and preclinical markerless lung target tracking (MLTT) approaches have been developed. However, these approaches have yet to be benchmarked using a common measurement methodology. This knowledge gap motivated the MArkerless lung target Tracking CHallenge (MATCH). The aim was to localize lung targets accurately and precisely in a retrospective in silico study and a prospective experimental study.

METHODS

MATCH was an American Association of Physicists in Medicine sponsored Grand Challenge. Common materials for the in silico and experimental studies were the experiment setup including an anthropomorphic thorax phantom with two targets within the lungs, and a lung SABR planning protocol. The phantom was moved rigidly with patient-measured lung target motion traces, which also acted as ground truth motion. In the retrospective in silico study a volumetric modulated arc therapy treatment was simulated and a dataset consisting of treatment planning data and intra-treatment kilovoltage (kV) and megavoltage (MV) images for four blinded lung motion traces was provided to the participants. The participants used their MLTT approach to localize the moving target based on the dataset. In the experimental study, the participants received the phantom experiment setup and five patient-measured lung motion traces. The participants used their MLTT approach to localize the moving target during an experimental SABR phantom treatment. The challenge was open to any participant, and participants could complete either one or both parts of the challenge. For both the in silico and experimental studies the MLTT results were analyzed and ranked using the prospectively defined metric of the percentage of the tracked target position being within 2 mm of the ground truth.

RESULTS

A total of 30 institutions registered and 15 result submissions were received, four for the in silico study and 11 for the experimental study. The participating MLTT approaches were: Accuray CyberKnife (2), Accuray Radixact (2), BrainLab Vero, C-RAD, and preclinical MLTT (5) on a conventional linear accelerator (Varian TrueBeam). For the in silico study the percentage of the 3D tracking error within 2 mm ranged from 50% to 92%. For the experimental study, the percentage of the 3D tracking error within 2 mm ranged from 39% to 96%.

CONCLUSIONS

A common methodology for measuring the accuracy of MLTT approaches has been developed and used to benchmark preclinical and commercial approaches retrospectively and prospectively. Several MLTT approaches were able to track the target with sub-millimeter accuracy and precision. The study outcome paves the way for broader clinical implementation of MLTT. MATCH is live, with datasets and analysis software being available online at https://www.aapm.org/GrandChallenge/MATCH/ to support future research.

An in-silico assessment of the dosimetric benefits of MR-guided radiotherapy for esophageal cancer patients

PURPOSE

To assess the dosimetric benefits of online MR-guided radiotherapy (MRgRT) for esophageal cancer patients and to assess how these benefits could be translated into a local boosting strategy to improve future outcomes.

METHODS

Twenty-nine patients were in-silico treated with both a MRgRT regimen and a conventional image guided radiotherapy (IGRT) regimen using dose warping techniques. Here, the inter and intrafractional changes that occur over the course of treatment (as derived from 5 MRI scans that were acquired weekly during treatment) were incorporated to assess the total accumulated dose for each regimen.

RESULTS

A significant reduction in dose to the organs-at-risk (OARs) was observed for all dose-volume-histogram (DVH) parameters for the MRgRT regimen without concessions to target coverage compared to the IGRT regimen. The mean lung dose was reduced by 28%, from 7.9 to 5.7 Gy respectively and V20Gy of the lungs was reduced by 55% (6.3-2.8%). A reduction of 24% was seen in mean heart dose (14.8-11.2 Gy), while the V25Gy of the heart was decreased by 53% (14.3-6.7%) and the V40Gy of the heart was decreased by 69% (3.9-1.2%). In addition, MRgRT dose escalation regimens with a boost up to 66% of the prescription dose to the primary tumor yielded approximately the same dose levels to the OARs as from the conventional IGRT regimen.

CONCLUSION

This study revealed that MRgRT for esophageal cancer has the potential to significantly reduce the dose to heart and lungs. In addition, online high precision targeting of the primary tumor opens new perspectives for local boosting strategies to improve outcome of the local management of this disease.

Markerless Real-Time 3-Dimensional kV Tracking of Lung Tumors During Free Breathing Stereotactic Radiation Therapy

Purpose

Accurate verification of tumor position during irradiation could reduce the probability of target miss. We investigated whether a commercial gantry-mounted 2-dimensional (2D) kilo-voltage (kV) imaging system could be used for real-time 3D tumor tracking during volumetric modulated arc therapy (VMAT) lung stereotactic body radiation therapy (SBRT). Markerless tumor tracking on kV fluoroscopic images was validated using a life-like moving thorax phantom and subsequently performed on kV images continuously acquired before and during free-breathing VMAT lung SBRT.

Methods and Materials

The 3D-printed/molded phantom containing 3 lung tumors was moved in 3D in TrueBeam developer mode, using simulated regular/irregular breathing patterns. Planar kV images were acquired at 7 frames/s during 11 Gy/fraction 10 MV flattening filter free VMAT. 2D reference templates were created for each gantry angle using the planning 4D computed tomography inspiration phase. kV images and templates were matched using normalized cross correlation to determine 2D tumor position, and triangulation of 2D matched projections determined the third dimension. 3D target tracking performed on cone beam computed tomography projection data from 18 patients (20 tumors) and real-time online tracking data from 2 of the 18 patients who underwent free-breathing VMAT lung SBRT are presented.

Results

For target 1 and 2 of the phantom (upper lung and middle/medial lung, mean density –130 Hounsfield units), 3D results within 2 mm of the known position were present in 92% and 96% of the kV projections, respectively. For target 3 (inferior lung, mean density –478 Hounsfield units) this dropped to 80%. Benchmarking against the respiratory signal, 13/20 (65%) tumors (10.5 ± 11.1 cm³) were considered successfully tracked on the cone beam computed tomography data. Tracking was less successful (≤50% of the time) in 7/20 (1.2 ± 1.5 cm³). Successful online tracking during lung SBRT was demonstrated.

Conclusions

3D markerless tumor tracking on a standard linear accelerator using template matching and triangulation of free-breathing kV fluoroscopic images was possible in 65% of small lung tumors. The smallest tumors were most challenging.

Fundamental study on quality assurance (QA) procedures for a real-time tumor tracking radiotherapy (RTRT) system from the viewpoint of imaging devices

PURPOSE

The real-time tumor tracking radiotherapy (RTRT) system requires periodic quality assurance (QA) and quality control. The goal of this study is to propose QA procedures from the viewpoint of imaging devices in the RTRT system.

METHODS

Tracking by the RTRT system (equips two sets of colored image intensifiers (colored I.I.s) fluoroscopy units) for the moving gold-marker (diameter 2.0 mm) in a rotating phantom were performed under various X-ray conditions. To analyze the relationship between fluoroscopic image quality and precision of gold marker coordinate calculation, the standard deviation of the 3D coordinate (σ3D [mm]) of the gold marker, the mean of the pattern recognition score (PRS) and the standard deviation of the distance between rays (DBR) (σDBR [mm]) were evaluated.

RESULTS

When tracking with speed of 10-60 mm/s, σDBR increased, though the mean PRS did not change significantly (p>0.05). On the contrary, the mean PRS increased depending on the integral noise equivalent quanta (∫NEQ) that is an indicator of image quality calculated from the modulation transfer function (MTF) as an indicator of spatial resolution and the noise power spectrum (NPS) as an indicator of noise characteristic.

CONCLUSION

The indicators of NEQ, MTF, and NPS were useful for managing the tracking accuracy of the RTRT system. We propose observing the change of these indicators as additional QA procedures for each imaging device from the commissioning baseline.

Dense feature-based motion estimation in MV fluoroscopy during dynamic tumor tracking treatment: preliminary study on reduced aperture and partial occlusion handling

Quality assurance solutions to complement available motion compensation technologies are central for their safe routine implementation and success of treatment. This work presents a dense feature-based method for soft-tissue tumor motion estimation in megavoltage (MV) beam's-eye-view (BEV) projections for potential intra-treatment monitoring during dynamic tumor tracking (DTT). Dense sampling and matching principles were employed to track a gridded set of features landmarks (FLs) in MV-BEV projections and estimate tumor motion, capable to overcome reduced field aperture and partial occlusion challenges. The algorithm's performance was evaluated by retrospectively applying it to fluoroscopic sequences acquired at ∼2 frames s^-1 (fps) for a dynamic phantom and two lung stereotactic body radiation therapy (SBRT) patients treated with DTT on the Vero SBRT system. First, a field-specific train image is initialized by sampling the tumor region at, S, pixel intervals on a grid using a representative frame from a stream of query frames. Sampled FLs are locally characterized in the form of descriptor vectors and geometric attributes representing the target. For motion tracking, subsequent query frames are likewise sampled, corresponding feature descriptors determined, and then patch-wise matched to the training set based on their descriptors and geometric relationships. FLs with high correspondence are pruned and used to estimate tumor displacement. In scenarios of partial occlusions, position is estimated from the set of correctly (visible) FLs on past observations. Reconstructed trajectories were benchmarked against ground-truth manual tracking using the root-mean-square (RMS) as a metric of positional accuracy. A total of 19 fluoroscopy sequences were analyzed. This included scenarios of field aperture obstruction during three-dimensional conformal, as well as step-and-shoot intensity modulated radiotherapy (IMRT) delivery assisted with DTT. The algorithm resolved target motion satisfactorily. The RMS was <1.2 mm and <1.8 mm for the phantom and the clinical dataset, respectively. Dense tracking showed promising results to overcome localization challenges at the field penumbra and partial obstruction by multi-leaf collimator (MLC). Motion retrieval was possible in ∼66% of the control points studied. In addition to MLC obstruction, changes in the external/internal breathing dynamics and baseline drifts were a major source of estimation bias. Dense feature-based tracking is a viable alternative. The algorithm is rotation-/scale-invariant and robust to photometric changes. Tracking multiple features may help overcome partial occlusion challenges by the MLC. This in turn opens up new possibilities for motion detection and intra-treatment monitoring during IMRT and potentially VMAT.

Characterization of Markerless Tumor Tracking Using the On-Board Imager of a Commercial Linear Accelerator Equipped With Fast-kV Switching Dual-Energy Imaging

PURPOSE

To describe and characterize fast-kV switching, dual-energy (DE) imaging implemented within the on-board imager of a commercial linear accelerator for markerless tumor tracking (MTT).

METHODS AND MATERIALS

Fast-kV switching, DE imaging provides for rapid switching between programmed tube voltages (ie, 60 and 120 kVp) from one image frame to the next. To characterize this system, the weighting factor used for logarithmic subtraction and signal difference-to-noise ratio were analyzed as a function of time and frame rate. MTT was evaluated using a thorax motion phantom and fast kV, DE imaging was compared versus single energy (SE) imaging over 360 degrees of rotation. A template-based matching algorithm was used to track target motion on both DE and SE sequences. Receiver operating characteristics were used to compare tracking results for both modalities.

RESULTS

The weighting factor was inversely related to frame rate and stable over time. After applying the frame rate-dependent weighting factor, the signal difference-to-noise ratio was consistent across all frame rates considered for simulated tumors ranging from 5 to 25 mm in diameter. An analysis of receiver operating characteristics curves showed improved tracking with DE versus SE imaging. The area under the curve for the 10-mm target ranged from 0.821 to 0.858 for SE imaging versus 0.968 to 0.974 for DE imaging. Moreover, the residual tracking errors for the same target size ranged from 2.02 to 2.18 mm versus 0.79 to 1.07 mm for SE and DE imaging, respectively.

CONCLUSIONS

Fast-kV switching, DE imaging was implemented on the on-board imager of a commercial linear accelerator. DE imaging resulted in improved MTT accuracy over SE imaging. Such an approach may have application for MTT of patients with lung cancer receiving stereotactic body radiation therapy, particularly for small tumors where MTT with SE imaging may fail.

The first prospective implementation of markerless lung target tracking in an experimental quality assurance procedure on a standard linear accelerator

The ability to track tumour motion without implanted markers on a standard linear accelerator (linac) could enable wide access to real-time adaptive radiotherapy for cancer patients. We previously have retrospectively validated a method for 3D markerless target tracking using intra-fractional kilovoltage (kV) projections acquired on a standard linac. This paper presents the first prospective implementation of markerless lung target tracking on a standard linac and its quality assurance (QA) procedure. The workflow and the algorithm developed to track the 3D target position during volumetric modulated arc therapy treatment delivery were optimised. The linac was operated in clinical QA mode, while kV projections were streamed to a dedicated computer using a frame-grabber software. The markerless target tracking accuracy and precision were measured in a lung phantom experiment under the following conditions: static localisation of seven distinct positions, dynamic localisation of five patient-measured motion traces, and dynamic localisation with treatment interruption. The QA guidelines were developed following the AAPM Task Group 147 report with the requirement that the tracking margin components, the margins required to account for tracking errors, did not exceed 5 mm in any direction. The mean tracking error ranged from 0.0 to 0.9 mm (left-right), -0.6 to  -0.1 mm (superior-inferior) and  -0.7 to 0.1 mm (anterior-posterior) over the three tests. Larger errors were found in cases with large left-right or anterior-posterior and small superior-inferior motion. The tracking margin components did not exceed 5 mm in any direction and ranged from 0.4 to 3.2 mm (left-right), 0.7 to 1.6 mm (superior-inferior) and 0.8 to 1.5 mm (anterior-posterior). This study presents the first prospective implementation of markerless lung target tracking on a standard linac and provides a QA procedure for its safe clinical implementation, potentially enabling real-time adaptive radiotherapy for a large population of lung cancer patients.

Technical Note: 3D localization of lung tumors on cone beam CT projections via a convolutional recurrent neural network

PURPOSE

To design a convolutional recurrent neural network (CRNN) that calculates three-dimensional (3D) positions of lung tumors from continuously acquired cone beam computed tomography (CBCT) projections, and facilitates the sorting and reconstruction of 4D-CBCT images.

METHOD

Under an IRB-approved clinical lung protocol, kilovoltage (kV) projections of the setup CBCT were collected in free-breathing. Concurrently, an electromagnetic signal-guided system recorded motion traces of three transponders implanted in or near the tumor. Convolutional recurrent neural network was designed to utilize a convolutional neural network (CNN) for extracting relevant features of the kV projections around the tumor, followed by a recurrent neural network for analyzing the temporal patterns of the moving features. Convolutional recurrent neural network was trained on the simultaneously collected kV projections and motion traces, subsequently utilized to calculate motion traces solely based on the continuous feed of kV projections. To enhance performance, CRNN was also facilitated by frequent calibrations (e.g., at 10° gantry rotation intervals) derived from cross-correlation-based registrations between kV projections and templates created from the planning 4DCT. Convolutional recurrent neural network was validated on a leave-one-out strategy using data from 11 lung patients, including 5500 kV images. The root-mean-square error between the CRNN and motion traces was calculated to evaluate the localization accuracy.

RESULT

Three-dimensional displacement around the simulation position shown in the Calypso traces was 3.4 ± 1.7 mm. Using motion traces as ground truth, the 3D localization error of CRNN with calibrations was 1.3 ± 1.4 mm. CRNN had a success rate of 86 ± 8% in determining whether the motion was within a 3D displacement window of 2 mm. The latency was 20 ms when CRNN ran on a high-performance computer cluster.

CONCLUSIONS

CRNN is able to provide accurate localization of lung tumors with aid from frequent recalibrations using the conventional cross-correlation-based registration approach, and has the potential to remove reliance on the implanted fiducials.

Real-time intrafraction motion monitoring in external beam radiotherapy

Radiotherapy (RT) aims to deliver a spatially conformal dose of radiation to tumours while maximizing the dose sparing to healthy tissues. However, the internal patient anatomy is constantly moving due to respiratory, cardiac, gastrointestinal and urinary activity. The long term goal of the RT community to 'see what we treat, as we treat' and to act on this information instantaneously has resulted in rapid technological innovation. Specialized treatment machines, such as robotic or gimbal-steered linear accelerators (linac) with in-room imaging suites, have been developed specifically for real-time treatment adaptation. Additional equipment, such as stereoscopic kilovoltage (kV) imaging, ultrasound transducers and electromagnetic transponders, has been developed for intrafraction motion monitoring on conventional linacs. Magnetic resonance imaging (MRI) has been integrated with cobalt treatment units and more recently with linacs. In addition to hardware innovation, software development has played a substantial role in the development of motion monitoring methods based on respiratory motion surrogates and planar kV or Megavoltage (MV) imaging that is available on standard equipped linacs. In this paper, we review and compare the different intrafraction motion monitoring methods proposed in the literature and demonstrated in real-time on clinical data as well as their possible future developments. We then discuss general considerations on validation and quality assurance for clinical implementation. Besides photon RT, particle therapy is increasingly used to treat moving targets. However, transferring motion monitoring technologies from linacs to particle beam lines presents substantial challenges. Lessons learned from the implementation of real-time intrafraction monitoring for photon RT will be used as a basis to discuss the implementation of these methods for particle RT.

Markerless tumor tracking using fast-kV switching dual-energy fluoroscopy on a benchtop system

PURPOSE

To evaluate markerless tumor tracking (MTT) using fast-kV switching dual-energy (DE) fluoroscopy on a bench top system.

METHODS

Fast-kV switching DE fluoroscopy was implemented on a bench top which includes a turntable stand, flat panel detector, and x-ray tube. The customized generator firmware enables consecutive x-ray pulses that alternate between programmed high and low energies (e.g., 60 and 120 kVp) with a maximum frame rate of 15 Hz. In-house software was implemented to perform weighted DE subtraction of consecutive images to create an image sequence that removes bone and enhances soft tissues. The weighting factor was optimized based on gantry angle. To characterize this system, a phantom was used that simulates the chest anatomy and tumor motion in the lung. Five clinically relevant tumor sizes (5-25 mm diameter) were considered. The targets were programmed to move in the inferior-superior direction of the phantom, perpendicular to the x-ray beam, using a cos⁴ waveform to mimic respiratory motion. Target inserts were then tracked with MTT software using a template matching method. The optimal computed tomography (CT) slice thickness for template generation was also evaluated. Tracking success rate and accuracy were calculated in regions of the phantom where the target overlapped ribs vs spine, to compare the performance of single energy (SE) and DE imaging methods.

RESULTS

For the 5 mm target, a CT slice thickness of 0.75 mm resulted in the lowest tracking error. For the larger targets (≥10 mm) a CT slice thickness ≤2 mm resulted in comparable tracking errors for SE and DE images. Overall DE imaging improved MTT accuracy, relative to SE imaging, for all tumor targets in a rotational acquisition. Compared to SE, DE imaging increased tracking success rate of small target inserts (5 and 10 mm). For fast motion tracking, success rates improved from 23% to 64% and 74% to 90% for 5 and 10 mm targets inserts overlapping ribs, respectively. For slow moving targets success rates improved from 19% to 59% and 59% to 91% in 5 and 10 mm targets overlapping the ribs, respectively. Similar results were observed when the targets overlapped the spine. For larger targets (≥15 mm) tracking success rates were comparable using SE and DE imaging.

CONCLUSION

This work presents the first results of MTT using fast-kV switching DE fluoroscopy. Using DE imaging has improved the tracking accuracy of MTT, especially for small targets. The results of this study will guide the future implementation of fast-kV switching DE imaging using the on-board imager of a linear accelerator.

Conditional random fields for phase-based lung feature tracking with ultra-low-dose x-rays

PURPOSE

During radiation therapy, a continuous internal tumor monitoring without additional imaging dose is desirable. In this study, a sequential feature-based position estimation with ultra-low-dose (ULD) kV x rays using linear-chain conditional random fields (CRFs) is performed.

METHODS

Four-dimensional computed tomography (4D-CTs) of eight patients serve as a-priori information from which ULD projections are simulated using a Monte Carlo method. CRFs are trained with Local Energy-based Shape Histogram features extracted from the ULD images to estimate one out of ten breathing phases from the 4D-CT associated with the tumor position.

RESULTS

Compared to a mean accuracy for ±1 breathing phase of 0.867 using a support vector machine (SVM), a mean accuracy of 0.958 results for the CRF with ten incident photons per pixel. This corresponds to a position estimation with a discretization error of 2.4-5.3 mm assuming a linear displacement relation between the breathing phases and a systematic error of 2.0-4.4 mm due to motion underestimation of the 4D-CT.

CONCLUSIONS

The tumor position estimation is comparable to state-of-the-art methods despite its low imaging dose. Training CRFs further allows a prediction of the following phase and offers a precise post-treatment evaluation tool when decoding the full image sequence.

Design and validation of a MV/kV imaging-based markerless tracking system for assessing real-time lung tumor motion

PURPOSE

Localizing lung tumors during treatment delivery is critical for managing respiratory motion, ensuring tumor coverage, and reducing toxicities. The purpose of this project is to develop a real-time system that performs markerless tracking of lung tumors using simultaneously acquired MV and kV images during radiotherapy of lung cancer with volumetric modulated arc therapy.

METHOD

Continuous MV/kV images were simultaneously acquired during dose delivery. In the subsequent analysis, a gantry angle-specific region of interest was defined according to the treatment aperture. After removing imaging artifacts, processed MV/kV images were directly registered to the corresponding daily setup cone-beam CT (CBCT) projections that served as reference images. The registration objective function consisted of a sum of normalized cross-correlation, weighted by the contrast-to-noise ratio of each MV and kV image. The calculated 3D shifts of the tumor were corrected by the displacements between the CBCT projections and the planning respiratory correlated CT (RCCT) to generate motion traces referred to a specific respiratory phase. The accuracy of the algorithm was evaluated on both anthropomorphic phantom and patient studies. The phantom consisted of localizing a 3D printed tumor, embedded in a thorax phantom, in an arc delivery. In an IRB-approved study, data were obtained from VMAT treatments of two lung cancer patients with three electromagnetic (Calypso) beacon transponders implanted in airways near the lung tumor.

RESULT

In the phantom study, the root mean square error (RMSE) between the registered and actual (programmed couch movement) target position was 1.2 mm measured by the MV/kV imaging system, which was smaller compared to the MV or kV alone, of 4.1 and 1.3 mm, respectively. In the patient study, the mean and standard deviation discrepancy between electromagnetic-based tumor position and the MV/KV-markerless approach was -0.2 ± 0.6 mm, 0.2 ± 1.0 mm, and -1.2 ± 1.5 mm along the superior-inferior, anterior-posterior, and left-right directions, respectively; resulting in a 3D displacement discrepancy of 2.0 ± 1.1 mm. Poor contrast around the tumor was the main contribution to registration uncertainties.

CONCLUSION

The combined MV/kV imaging system can provide real-time 3D localization of lung tumor, with comparable accuracy to the electromagnetic-based system when features of tumors are detectable. Careful design of a registration algorithm and a VMAT plan that maximizes the tumor visibility are key elements for a successful MV/KV localization strategy.

Variations of MRI-assessed peristaltic motions during radiation therapy

PURPOSE

Understanding complex abdominal organ motion is essential for motion management in radiation therapy (RT) of abdominal tumors. This study investigates abdominal motion induced by respiration and peristalsis, during various time durations relevant to RT, using various CT and MRI techniques acquired under free breathing (FB) and breath hold (BH).

METHODS

A series of CT and MRI images acquired with various techniques under free breathing and/or breath hold from 37 randomly-selected pancreatic or liver cancer patients were analyzed to assess the motion in various time frames. These data include FB 4DCT from 15 patients (for motion in time duration of 5 sec), FB 2D cine-MRI from 4 patients (time duration of 1.7 min, 1 second acquisition time per slice), FB cine-MRI acquired using MR-Linac from 6 patients in various fractions (acquisition time is less than 0.6 seconds per slice), FB 4DMRI from 2 patients (time duration of 2 min), respiration-gated T2 with gating at the end expiration (time duration of 3-5 min), and BH T1 with multiphase dynamic contrast in acquisition times of 17 seconds for each of five phases (pre-contrast, arterial, venous, portal venous and delayed post-contrast) from 10 patients. Motions of various organs including gallbladder (GB) and liver were measured based on these MRI data. The GB motion includes both respiration and peristalsis, while liver motion is primarily respiration. By subtracting liver motion (respiration) from GB motion (respiration and peristalsis), the peristaltic motion, along with small residual motion, was obtained.

RESULTS

From cine-MRI, the residual motion beyond the respiratory motion was found to be up to 0.6 cm in superior-inferior (SI) and 0.55 cm in anterior-posterior (AP) directions. From 2D cine-MRI acquired by the MR-Linac, different peristaltic motions were found from different fractions for each patient. The peristaltic motion was found to vary between 0.3-1 cm. From BH T1 phase images, the average motions that were primarily due to peristalsis movements were found to be 1.2 cm in SI, 0.7 cm in AP, and 0.9 cm in left-right (LR) directions. The average motions assessed from 4DCT were 1.0 cm in SI and 0.3 cm in AP directions, which were generally smaller than the motions assessed from cine-MRI, i.e., 1.8 cm in SI and 0.6 cm in AP directions, for the same patients. However, average motions from 4DMRI, which are coming from respiratory were measured to be 1.5, 0.5, and 0.4 cm in SI, AP, and LR directions, respectively.

CONCLUSION

The abdominal motion due to peristalsis can be similar in magnitude to respiratory motion as assessed. These motions can be irregular and persistent throughout the imaging and RT delivery procedures, and should be considered together with respiratory motion during RT for abdominal tumors.

Feasibility of markerless 3D position monitoring of the central airways using kilovoltage projection images: Managing the risks of central lung stereotactic radiotherapy

BACKGROUND AND PURPOSE

Central lung stereotactic body radiotherapy (SBRT) can cause proximal bronchial tree (PBT) toxicity. Information on PBT position relative to the high-dose could aid risk management. We investigated template matching + triangulation for high-frequency markerless 3D PBT position monitoring.

MATERIALS AND METHODS

Kilovoltage projections of a moving phantom (full-fan cone-beam CT [CBCT, 15 frames/second] without MV irradiation: 889 images/dataset + CBCT and 7 frames/second fluoroscopy with MV irradiation) and ten patients undergoing free-breathing stereotactic/hypofractionated lung irradiation (full-fan CBCT without MV irradiation, 470-500 images/dataset) were retrospectively analyzed. 2D PBT reference templates (1 filtered digitally reconstructed radiograph/°) were created from planning CT data. Using normalized cross-correlation, templates were matched to projection images for 2D position. Multiple registrations were triangulated for 3D position.

RESULTS

For the phantom, 2D right/left PBT position could be determined in 86.6/75.1% of the CBCT dataset without MV irradiation, and 3D position (excluding first 20° due to the minimum triangulation angle) in 84.7/72.7%. With MV irradiation, this was up to 2% less. For right/left PBT, root-mean-square errors of measured versus "known" position were 0.5/0.8, 0.4-0.5/0.7, and 0.4/0.5-0.6 mm for left-right, superior-inferior, and anterior-posterior directions, respectively. 2D PBT position was determined in, on average, 89.8% of each patient dataset (range: 79.4-99.2%), and 3D position (excluding first 20°) in 85.1% (range: 67.9-99.6%). Motion was mainly superior-inferior (range: 4.5-13.6 mm, average: 8.5 mm).

CONCLUSIONS

High-frequency 3D PBT position verification during free-breathing is technically feasible using markerless template matching + triangulation of kilovoltage projection images acquired during gantry rotation. Applications include organ-at-risk position monitoring during central lung SBRT.

Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy

Robustness to obstacles is the most important factor necessary to achieve accurate tumor tracking without fiducial markers. Some high-density structures, such as bone, are enhanced on X-ray fluoroscopic images, which cause tumor mistracking. Tumor tracking should be performed by controlling "importance recognition": the understanding that soft-tissue is an important tracking feature and bone structure is unimportant. We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control. The novelty of the proposed method is the combination of the devised random overlay method and supervised deep learning to induce the recognition of structures in tumor contouring as important or unimportant. This method can be used for tumor contouring because it uses deep learning to perform image segmentation. Our results from a simulated fluoroscopy model showed accurate tracking of a low-visibility tumor with an error of approximately 1 mm, even if enhanced bone structure acted as an obstacle. A high similarity of approximately 0.95 on the Jaccard index was observed between the segmented and ground truth tumor regions. A short processing time of 25 ms was achieved. The results of this simulated fluoroscopy model support the feasibility of robust real-time tumor contouring with fluoroscopy. Further studies using clinical fluoroscopy are highly anticipated.

Feasibility of using single photon counting X-ray for lung tumor position estimation based on 4D-CT

PURPOSE

In stereotactic body radiation therapy of lung tumors, reliable position estimation of the tumor is necessary in order to minimize normal tissue complication rate. While kV X-ray imaging is frequently used, continuous application during radiotherapy sessions is often not possible due to concerns about the additional dose. Thus, ultra low-dose (ULD) kV X-ray imaging based on a single photon counting detector is suggested. This paper addresses the lower limit of photons to locate the tumor reliably with an accuracy in the range of state-of-the-art methods, i.e. a few millimeters.

METHOD

18 patient cases with four dimensional CT (4D-CT), which serves as a-priori information, are included in the study. ULD cone beam projections are simulated from the 4D-CTs including Poisson noise. The projections from the breathing phases which correspond to different tumor positions are compared to the ULD projection by means of Poisson log-likelihood (PML) and correlation coefficient (CC), and template matching under these metrics.

RESULTS

The results indicate that in full thorax imaging five photons per pixel suffice for a standard deviation in tumor positions of less than half a breathing phase. Around 50 photons per pixel are needed to achieve this accuracy with the field of view restricted to the tumor region. Compared to CC, PML tends to perform better for low photon counts and shifts in patient setup. Template matching only improves the position estimation in high photon counts. The quality of the reconstruction is independent of the projection angle.

CONCLUSIONS

The accuracy of the proposed ULD single photon counting system is in the range of a few millimeters and therefore comparable to state-of-the-art tumor tracking methods. At the same time, a reduction in photons per pixel by three to four orders of magnitude relative to commercial systems with flatpanel detectors can be achieved. This enables continuous kV image-based position estimation during all fractions since the additional dose to the patient is negligible.

A Bayesian approach for three-dimensional markerless tumor tracking using kV imaging during lung radiotherapy

The ability to monitor tumor motion without implanted markers can potentially enable broad access to more accurate and precise lung radiotherapy. A major challenge is that kilovoltage (kV) imaging based methods are rarely able to continuously track the tumor due to the inferior tumor visibility on 2D kV images. Another challenge is the estimation of 3D tumor position based on only 2D imaging information. The aim of this work is to address both challenges by proposing a Bayesian approach for markerless tumor tracking for the first time. The proposed approach adopts the framework of the extended Kalman filter, which combines a prediction and measurement steps to make the optimal tumor position update. For each imaging frame, the tumor position is first predicted by a respiratory-correlated model. The 2D tumor position on the kV image is then measured by template matching. Finally, the prediction and 2D measurement are combined based on the 3D distribution of tumor positions in the past 10 s and the estimated uncertainty of template matching. To investigate the clinical feasibility of the proposed method, a total of 13 lung cancer patient datasets were used for retrospective validation, including 11 cone-beam CT scan pairs and two stereotactic ablative body radiotherapy cases. The ground truths for tumor motion were generated from the the 3D trajectories of implanted markers or beacons. The mean, standard deviation, and 95th percentile of the 3D tracking error were found to range from 1.6-2.9 mm, 0.6-1.5 mm, and 2.6-5.8 mm, respectively. Markerless tumor tracking always resulted in smaller errors compared to the standard of care. The improvement was the most pronounced in the superior-inferior (SI) direction, with up to 9.5 mm reduction in the 95th-percentile SI error for patients with  >10 mm 5th-to-95th percentile SI tumor motion. The percentage of errors with 3D magnitude  <5 mm was 96.5% for markerless tumor tracking and 84.1% for the standard of care. The feasibility of 3D markerless tumor tracking has been demonstrated on realistic clinical scenarios for the first time. The clinical implementation of the proposed method will enable more accurate and precise lung radiotherapy using existing hardware and workflow. Future work is focused on the clinical and real-time implementation of this method.

Analysis of components of variance determining probability of setup errors in CBCT-guided stereotactic radiotherapy of lung tumors

PURPOSE

Online tumor matching for SABR lung setup requires margins for inaccuracies due to intra-fraction variability of breathing-averaged tumor position (BATP) and CBCT image guidance. We studied intra-fraction variability during SABR delivery using VMAT, corrected these for measurement inaccuracies, and quantified the CBCT image-guidance uncertainties.

MATERIALS AND METHODS

For 193 fractions in 38 patients positioned without immobilization devices, CBCT scans were acquired before and after 2 arcs of a RapidArc treatment. A hidden marker test was performed to determine the accuracy of the CBCT system and an inter-observer test was performed to measure registration accuracy. Intra-fraction variability was calculated after correction for these components of variance, and the prediction interval for setup inaccuracies was determined.

RESULTS

Correction for measurement inaccuracies reduced the intra-fraction variability of the BATP from 1.9 to 1.6 mm in AP, from 1.7 to 1.4 mm in SI and from 1.5 to 1.1 mm in LR direction (1 SD). Intra-fraction variability in bony anatomy after correction was ≤ 1 mm (1 SD). The 95% prediction interval to account for CBCT image-guidance uncertainties and intra-fraction variability was determined, and was found to be within our institutional PTV margins of 5 mm.

CONCLUSIONS

Our findings show that it is essential to account for measurement and system inaccuracies when obtaining data for validating PTV margins from online CBCT image guidance.

Robust breathing signal extraction from cone beam CT projections based on adaptive and global optimization techniques

We present a study of extracting respiratory signals from cone beam computed tomography (CBCT) projections within the framework of the Amsterdam Shroud (AS) technique. Acquired prior to the radiotherapy treatment, CBCT projections were preprocessed for contrast enhancement by converting the original intensity images to attenuation images with which the AS image was created. An adaptive robust z-normalization filtering was applied to further augment the weak oscillating structures locally. From the enhanced AS image, the respiratory signal was extracted using a two-step optimization approach to effectively reveal the large-scale regularity of the breathing signals. CBCT projection images from five patients acquired with the Varian Onboard Imager on the Clinac iX System Linear Accelerator (Varian Medical Systems, Palo Alto, CA) were employed to assess the proposed technique. Stable breathing signals can be reliably extracted using the proposed algorithm. Reference waveforms obtained using an air bellows belt (Philips Medical Systems, Cleveland, OH) were exported and compared to those with the AS based signals. The average errors for the enrolled patients between the estimated breath per minute (bpm) and the reference waveform bpm can be as low as -0.07 with the standard deviation 1.58. The new algorithm outperformed the original AS technique for all patients by 8.5% to 30%. The impact of gantry rotation on the breathing signal was assessed with data acquired with a Quasar phantom (Modus Medical Devices Inc., London, Canada) and found to be minimal on the signal frequency. The new technique developed in this work will provide a practical solution to rendering markerless breathing signal using the CBCT projections for thoracic and abdominal patients.

Markerless tumor tracking using short kilovoltage imaging arcs for lung image-guided radiotherapy

The ability to monitor tumor motion without implanted markers is clinically advantageous for lung image-guided radiotherapy (IGRT). Existing markerless tracking methods often suffer from overlapping structures and low visibility of tumors on kV projection images. We introduce the short arc tumor tracking (SATT) method to overcome these issues. The proposed method utilizes multiple kV projection images selected from a nine-degree imaging arc to improve tumor localization, and respiratory-correlated 4D cone-beam CT (CBCT) prior knowledge to minimize the effects of overlapping anatomies. The 3D tumor position is solved as an optimization problem with prior knowledge incorporated via regularization. We retrospectively validated SATT on 11 clinical scans from four patients with central tumors. These patients represent challenging scenarios for markerless tumor tracking due to the inferior adjacent contrast. The 3D trajectories of implanted fiducial markers were used as the ground truth for tracking accuracy evaluation. In all cases, the tumors were successfully tracked at all gantry angles. Compared to standard pre-treatment CBCT guidance alone, trajectory errors were significantly smaller with tracking in all cases, and the improvements were the most prominent in the superior-inferior direction. The mean 3D tracking error ranged from 2.2-9.9 mm, which was 0.4-2.6 mm smaller compared to pre-treatment CBCT. In conclusion, we were able to directly track tumors with inferior visibility on kV projection images using SATT. Tumor localization accuracies are significantly better with tracking compared to the current standard of care of lung IGRT. Future work involves the prospective evaluation and clinical implementation of SATT.