Markerless Lung Tumor Tracking Research Articles

Robust Real-Time Cancer Tracking via Dual-Panel X-Ray Images for Precision Radiotherapy

Respiratory-induced tumor motion presents a critical challenge in lung cancer radiotherapy, potentially impacting treatment precision and efficacy. This study introduces an innovative, deep learning-based approach for real-time, markerless lung tumor tracking utilizing orthogonal X-ray projection images. It incorporates three key components: (1) a sophisticated data augmentation technique combining a hybrid deformable model with 3D thin-plate spline transformation, (2) a state-of-the-art Transformer-based segmentation network for precise tumor boundary delineation, and (3) a CNN regression network for accurate 3D tumor position estimation. We rigorously evaluated this approach using both patient data from The Cancer Imaging Archive and dynamic thorax phantom data, assessing performance across various noise levels and comparing it with current leading algorithms. For TCIA patient data, the average DSC and HD95 values were 0.9789 and 1.8423 mm, respectively, with an average centroid localization deviation of 0.5441 mm. On CIRS phantoms, DSCs were 0.9671 (large tumor) and 0.9438 (small tumor) with corresponding HD95 values of 1.8178 mm and 1.9679 mm. The 3D centroid localization accuracy was consistently below 0.33 mm. The processing time averaged 90 ms/frame. Even under high noise conditions (S2 = 25), errors for all data remained within 1 mm with tracking success rates mostly at 100%. In conclusion, the proposed markerless tracking method demonstrates superior accuracy, noise robustness, and real-time performance for lung tumor localization during radiotherapy. Its potential to enhance treatment precision, especially for small tumors, represents a significant step toward improving radiotherapy efficacy and personalizing cancer treatment.

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

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. To introduce a novel method for markerless kV image-based tracking of lung tumors via deep learning-based target decomposition. 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. 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±0.7mm in the superior-inferior (SI) direction and 0.9±0.8mm in the in-plane left-right (IPLR) direction. The percentage of successful tracking, defined as a tracking error less than 2mm in the SI direction, is 92.2% on the 4312 tested images. The patient-specific model took approximately 12h to train. During testing, it took approximately 35ms to generate one sDTI, and 13ms to perform the tumor tracking using template matching. 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.

Simultaneous object detection and segmentation for patient-specific markerless lung tumor tracking in simulated radiographs with deep learning.

Real-time tumor tracking is one motion management method to address motion-induced uncertainty. To date, fiducial markers are often required to reliably track lung tumors with X-ray imaging, which carries risks of complications and leads to prolonged treatment time. A markerless tracking approach is thus desirable. Deep learning-based approaches have shown promise for markerless tracking, but systematic evaluation and procedures to investigate applicability in individual cases are missing. Moreover, few efforts have been made to provide bounding box prediction and mask segmentation simultaneously, which could allow either rigid or deformable multi-leaf collimatortracking. The purpose of this study was to implement a deep learning-based markerless lung tumor tracking model exploiting patient-specific training which outputs both a bounding box and a mask segmentation simultaneously. We also aimed to compare the two kinds of predictions and to implement a specific procedure to understand the feasibility of markerless tracking on individualcases. We first trained a Retina U-Net baseline model on digitally reconstructed radiographs (DRRs) generated from a public dataset containing 875 CT scans and corresponding lung nodule annotations. Afterwards, we used an independent cohort of 97 lung patients to develop a patient-specific refinement procedure. In order to determine the optimal hyperparameters for automatic patient-specific training, we selected 13 patients for validation where the baseline model predicted a bounding box on planning CT (PCT)-DRR with intersection over union (IoU) with the ground-truth higher than 0.7. The final test set contained the remaining 84 patients with varying PCT-DRR IoU. For each testing patient, the baseline model was refined on the PCT-DRR to generate a patient-specific model, which was then tested on a separate 10-phase 4DCT-DRR to mimic the intrafraction motion during treatment. A template matching algorithm served as benchmark model. The testing results were evaluated by four metrics: the center of mass (COM) error and the Dice similarity coefficient (DSC) for segmentation masks, and the center of box (COB) error and the DSC for bounding box detections. Performance was compared to the benchmark model including statistical testing forsignificance. A PCT-DRR IoU value of 0.2 was shown to be the threshold dividing inconsistent (68%) and consistent (100%) success (defined as mean bounding box DSC > 0.6) of PS models on 4DCT-DRRs. Thirty-seven out of the eighty-four testing cases had a PCT-DRR IoU above 0.2. For these 37 cases, the mean COM error was 2.6 mm, the mean segmentation DSC was 0.78, the mean COB error was 2.7 mm, and the mean box DSC was 0.83. Including the validation cases, the model was applicable to 50 out of 97 patients when using the PCT-DRR IoU threshold of 0.2. The inference time per frame was 170 ms. The model outperformed the benchmark model on all metrics, and the comparison was significant (p < 0.001) over the 37 PCT-DRR IoU > 0.2 cases, but not over the undifferentiated 84 testingcases. The implemented patient-specific refinement approach based on a pre-trained baseline model was shown to be applicable to markerless tumor tracking in simulated radiographs for lungcases.

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

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. 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 bonystructures. 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% forvalidation. 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% forRTR. 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 iswarranted.

PO-1889 Feasibility of markerless lung tumor tracking on radiographs with Retina U-Net

PO-1889 Feasibility of markerless lung tumor tracking on radiographs with Retina U-Net

Real-time Markerless Tracking of Lung Tumors based on 2-D Fluoroscopy Imaging using Convolutional LSTM.

To investigate the feasibility of tracking targets in 2D fluor images using a novel deep learning network. Our model design aims to capture the consistent motion of tumors in fluoroscopic images by neural network. Specifically, the model is trained by generative adversarial methods. The network is a coarse-to-fine architecture design. Convolutional LSTM (Long Short-term Memory) modules are introduced to account for the time correlation between different frames of the fluoroscopic images. The model was trained and tested on a digital X-CAT phantom in two studies. Series of coherent 2D fluoroscopic images representing the full respiration cycle were fed into the model to predict the localized tumor regions. In first study to test on massive scenarios, phantoms of different scales, tumor positions, sizes, and respiration amplitudes were generated to evaluate the accuracy of the model comprehensively. In second study to test on specific sample, phantoms were generated with fixed body and tumor sizes but different respiration amplitudes to investigate the effects of motion amplitude on the tracking accuracy. The tracking accuracy was quantitatively evaluated using intersection over union (IOU), tumor area difference, and centroid of mass difference (COMD). In the first comprehensive study, the mean IOU and dice coefficient achieved 0.93±0.04 and 0.96±0.02. The mean tumor area difference was 4.34%±4.04%. And the COMD was 0.16 cm and 0.07 cm on average in SI (superior-interior) and LR (left-right) directions, respectively. In the second amplitude study, the mean IOU and dice coefficient achieved 0.98 and 0.99. The mean tumor difference was 0.17%. And the COMD was 0.03cm and 0.01 cm on average in SI and LR directions, respectively. Results demonstrated the robustness of our model against breathing variations. Our study showed the feasibility of using deep learning to track targets in x-ray fluoroscopic projection images without the aid of markers. The technique can be valuable for both pre- and during-treatment real-time target verification using fluoroscopic imaging in lung SBRT treatments.

Siamese-Based Deep Learning for Markerless Lung Tumor Tracking During Stereotactic Radiotherapy

<h3>Purpose/Objective(s)</h3> During stereotactic lung radiotherapy we want to monitor the target position to ensure it remains inside the planning target volume (PTV). This ensures accurate treatment delivery and may allow for margin reduction. Many LINAC systems have a kilo-voltage (kV) imaging system mounted orthogonally to the MV beam. This can acquire images during volumetric modulated arc therapy delivery. The 2D-kV images can be used to identify the tumor position, e.g., using template matching and triangulation (TMT). However, small lung targets are difficult to track, due to e.g., low tumor contrast, occlusion (e.g., by spine), or noisy images. We investigated deep learning (DL) as an alternative method for lung tumor tracking. <h3>Materials/Methods</h3> Clinical data from 6 patients (P1-P6) with small lung tumors (0.5-3 cm diameter) and a 3D-printed anthropomorphic phantom (P0), including a low-density lung tumor, was used. For each patient, data included 4D-CT scans, fluoroscopic kV images and breathing-related surface motion (Real-Time Position Management, RPM). For the phantom, a 3D-CT scan and kV images taken with a static and moving couch (regular and irregular motion) were available. Due to lack of ground truth tumor locations for the kV images, a patient-specific DL model is trained on Digitally Reconstructed Radiographs (DRRs), generated from the planning CT scans. To enhance the tumor's visual diversity in DRRs, we augmented the training data with locally deformed CT scans. A Siamese-based tracking by similarity method is hypothesized to be better suited for the tumor tracking task than other DL methods, due to its more localized search space and the use of previous frames (temporal information). <h3>Results</h3> Table 1 shows the superior-inferior (SI) direction results obtained by the Siamese model and TMT, on all kV images. For the patient data, the <b>Correlation coefficient</b> between estimated tumor trajectory and RPM was computed, due to lack of ground truth locations. For the phantom, the <b>Mean Absolute Distance</b> (MAD) between detected and ground truth center coordinates was computed. For all 6 patients and the phantom, the Siamese model outperformed TMT. <h3>Conclusion</h3> A novel approach for real-time markerless lung tumor tracking is presented, based on deep Siamese networks. The model compares favorably to the template matching/triangulation-based technique and merits further investigation. The current analysis presents only SI tracking. Reliable 3D tracking, with sub-mm accuracy, is the ultimate goal. Further work is needed to achieve this.

Scatter imaging during lung stereotactic body radiation therapy characterized with phantom studies

By collecting photons scattered out of the therapy beam, scatter imaging creates images of the treated volume. Two phantoms were used to assess the possible application of scatter imaging for markerless tracking of lung tumors during stereotactic body radiation therapy (SBRT) treatment. A scatter-imaging camera was assembled with a CsI flat-panel detector and a 5 mm diameter pinhole collimator. Scatter images were collected during the irradiation of phantoms with megavoltage photons. To assess scatter image quality, spherical phantom lung tumors of 2.1–2.8 cm diameters were placed inside a static, anthropomorphic phantom. To show the efficacy of the technique with a moving target (3 cm diameter), the position of a simulated tumor was tracked in scatter images during sinusoidal motion (15 mm amplitude, 0.25 Hz frequency) in a dynamic lung phantom in open-field, dynamic conformal arc (DCA), and volumetric modulated arc therapy (VMAT) deliveries. Anatomical features are identifiable on static phantom scatter images collected with 10 MU of delivered dose (2.1 cm diameter lung tumor contrast-to-noise ratio of 4.4). The contrast-to-noise ratio increases with tumor size and delivered dose. During dynamic motion, the position of the 3.0 cm diameter lung tumor was identified with a root-mean-square error of 0.8, 1.2, and 2.9 mm for open field (0.3 s frame integration), DCA (0.5 s), and VMAT (0.5 s), respectively. Based on phantom studies, scatter imaging is a potential technique for markerless lung tumor tracking during SBRT without additional imaging dose. Quality scatter images may be collected at low, clinically relevant doses (10 MU). Scatter images are capable of sub-millimeter tracking precision, but modulation decreases accuracy.

Automated MV markerless tumor tracking for VMAT

Tumor tracking during radiotherapy treatment can improve dose accuracy, conformity and sparing of healthy tissue. Many methods have been introduced to tackle this challenge utilizing multiple imaging modalities, including a template matching based approach using the megavoltage (MV) on-board portal imager demonstrated on 3D conformal treatments. However, the complexity of treatments is evolving with the introduction of VMAT and IMRT, and successful motion management is becoming more important due to a trend towards hypofractionation.We have developed a markerless lung tumor tracking algorithm, utilizing the electronic portal imager (EPID) of the treatment machine. The algorithm has been specifically adapted to track during complex treatment deliveries with gantry and MLC motion. The core of the algorithm is an adaptive template matching method that relies on template stability metrics and local relative orientations to perform multiple feature tracking simultaneously. Only a single image is required to initialize the algorithm and features are automatically added, modified or removed in response to the input images. This algorithm was evaluated against images collected during VMAT arcs of a dynamic thorax phantom. Dynamic phantom images were collected during radiation delivery for multiple lung SBRT breathing traces and an example patient data set. The tracking error was 1.34 mm for the phantom data and 0.68 mm for the patient data.A multi-region, markerless tracking algorithm has been developed, capable of tracking multiple features simultaneously without requiring any other a priori information. This novel approach delivers robust target localization during complex treatment delivery. The reported tracking error is similar to previous reports for 3D conformal treatments.

A Novel Markerless Lung Tumor-Tracking Method Using Treatment MV Beam Imaging

A novel method was developed to track lung tumor motion in real time during radiation therapy with the purpose to allow target radiation dose escalation while simultaneously reducing the dose to sensitive structures, thereby increasing local control without increasing toxicity. This method analyzes beam’s eye view radiation therapy treatment megavoltage (MV) images with simulated digitally reconstructed radiographs (DRRs) as references. Instead of comparing global DRRs with projection images, this method incorporates a technique that divides the global composite DRR and the corresponding MV projection into sub-images called tiles. Registration is performed independently on tile pairs in order to reduce the effects of global discrepancies due to scattering or imaging modality differences. This algorithm was evaluated by phantom studies while simulated tumors were controlled to move with various patterns in a complex humanoid torso. Approximately 15,000 phantom MV images were acquired at nine gantry angles, with different tumors moving within ranges between 10 and 20 mm. Tumors were successfully identified on every projection with a total maximum/average error of 1.84/0.98 mm. This algorithm was also applied to over 5,000 frames of MV projections acquired during radiation therapy of five lung cancer patients. This tumor-tracking methodology is capable of accurately locating lung tumors during treatment without implanting any internal fiducial markers nor delivering extra imaging radiation doses.

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

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

Markerless Respiratory Tumor Motion Prediction Using an Adaptive Neuro-fuzzy Approach

Accurate delivery of the prescribed dose to moving lung tumors is a key challenge in radiation therapy. Tumor tracking involves real-time specifying the target and correcting the geometry to compensate for the respiratory motion, that's why tracking the tumor requires caution. This study aims to develop a markerless lung tumor tracking method with a high accuracy. In this study, four-dimensional computed tomography (4D-CT) images of 10 patients were used, and all the slices which contained the tumor were contoured for all patients. The first four phases of 4D-CT images which contained tumors were selected as input of the software, and the next six phases were considered as the output. A hybrid intelligent method, adaptive neuro-fuzzy inference system (ANFIS), was used to evaluate motion of lung tumor. The root mean square error (RMSE) was used to investigate the accuracy of ANFIS performance for tumor motion prediction. For predicting the positions of contoured tumors, the averages of RMSE for each patient were calculated for all the patients. The results showed that the RMSE did not have a major variation. The data in the 4D-CT images were used for motion tracking instead of using markers that lead to more information of tumor motion with respect to methods based on marker location.

TH-AB-202-01: Daily Lung Tumor Motion Characterization On EPIDs Using a Markerless Tiling Model

Purpose: Tracking lung tumor motion in real time allows for target dose escalation while simultaneously reducing dose to sensitive structures, thus increasing local control without increasing toxicity. We present a novel intra-fractional markerless lung tumor tracking algorithm using MV treatment beam images acquired during treatment delivery. Strong signals superimposed on the tumor significantly reduced the soft tissue resolution; while different imaging modalities involved introduce global imaging discrepancies. This reduced the comparison accuracies. A simple yet elegant Tiling algorithm is reported to overcome the aforementioned issues. Methods: MV treatment beam images were acquired continuously in beam's eye view (BEV) by an electronic portal imaging device (EPID) during treatment and analyzed to obtain tumor positions on every frame. Every frame of the MV image was simulated by a composite of two components with separate digitally reconstructed radiographs (DRRs): all non-moving structures and the tumor. This Titling algorithm divides the global composite DRR and the corresponding MV projection into sub-images called tiles. Rigid registration is performed independently on tile-pairs in order to improve local soft tissue resolution. This enables the composite DRR to be transformed accurately to match the MV projection and attain a high correlation value through a pixel-based linear transformation. The highest cumulative correlation for all tile-pairs achieved over a user-defined search range indicates the 2-D coordinates of the tumor location on the MV projection. Results: This algorithm was successfully applied to cine-mode BEV images acquired during two SBRT plans delivered five times with different motion patterns to each of two phantoms. Approximately 15000 beam's eye view images were analyzed and tumor locations were successfully identified on every projection with a maximum/average error of 1.8 mm / 1.0 mm. Conclusion: Despite the presence of strong anatomical signal overlapping with tumor images, this markerless detection algorithm accurately tracks intrafractional lung tumor motions. This project is partially supported by an Elekta research grant

Real‐time markerless lung tumor tracking in fluoroscopic video: Handling overlapping of projected structures

Fluoroscopic imaging is a well-suited technique for online visualization of tumor motion in the thoracic region. Template-based approaches for tumor tracking in such images are commonly used. However, overlapping of different structures, mainly bones, can lead to limited visibility of the projected tumor shape, which in turn can negatively affect the performance of the tracking method. In this study, a method based on multiple-template matching was developed, providing fast and robust detection of tumor motion even under the influence of occurring tumor overlaps. A cohort of 14 patients with varying tumor sizes and locations was investigated. Image data from eight of these patients were used for evaluation. Based on the requirement of tumor visibility, the remaining datasets did not qualify for tracking. Generation of multiple templates was improved by implementation of an algorithm for automated selection of reference images containing the most characteristic tumor appearances. Various measures were taken to ensure real-time capability of the algorithm. A prematching step was introduced in order to reduce dispensable comparison operations by selecting the most appropriate template. Subsequent matching was further optimized by using prior knowledge about likely tumor motion to effectively limit necessary matching tasks. Tracking accuracy of the developed multiple-template method was compared with that of single-template. Mean errors of the multiple-template approach were 0.6 ± 0.6 mm in left-right and 0.9 ± 0.9 mm in superior-inferior direction in the isocenter plane. The single-template approach achieved mean errors of 0.7 ± 0.7 mm in left-right and 1.5 ± 1.3 mm in superior-inferior direction. These results derive from evaluation against manual tumor tracking performed by four expert observers. Computational times needed for tumor detection in a single fluoroscopic frame ranged between 1 and 29 ms depending on the tumor size and motion amplitude. This study shows that in case of tumor overlapping with dense structures, multiple-template tracking provides more accurate results than a single-template approach. The developed algorithm shows promising results in terms of suitability for real-time application and robustness against frequently changing overlapping.

Registration of clinical volumes to beams-eye-view images for real-time tracking.

The authors combine the registration of 2D beam's eye view (BEV) images and 3D planning computed tomography (CT) images, with relative, markerless tumor tracking to provide automatic absolute tracking of physician defined volumes such as the gross tumor volume (GTV). During treatment of lung SBRT cases, BEV images were continuously acquired with an electronic portal imaging device (EPID) operating in cine mode. For absolute registration of physician-defined volumes, an intensity based 2D/3D registration to the planning CT was performed using the end-of-exhale (EoE) phase of the four dimensional computed tomography (4DCT). The volume was converted from Hounsfield units into electron density by a calibration curve and digitally reconstructed radiographs (DRRs) were generated for each beam geometry. Using normalized cross correlation between the DRR and an EoE BEV image, the best in-plane rigid transformation was found. The transformation was applied to physician-defined contours in the planning CT, mapping them into the EPID image domain. A robust multiregion method of relative markerless lung tumor tracking quantified deviations from the EoE position. The success of 2D/3D registration was demonstrated at the EoE breathing phase. By registering at this phase and then employing a separate technique for relative tracking, the authors are able to successfully track target volumes in the BEV images throughout the entire treatment delivery. Through the combination of EPID/4DCT registration and relative tracking, a necessary step toward the clinical implementation of BEV tracking has been completed. The knowledge of tumor volumes relative to the treatment field is important for future applications like real-time motion management, adaptive radiotherapy, and delivered dose calculations.

Markerless Tracking of Lung Tumors on Continuous kV Images

Markerless Tracking of Lung Tumors on Continuous kV Images

Evaluation of a Template-Based Algorithm for Markerless Lung Tumor Tracking on Single Energy and Dual Energy kV Images

Evaluation of a Template-Based Algorithm for Markerless Lung Tumor Tracking on Single Energy and Dual Energy kV Images

TH‐E‐17A‐10: Markerless Lung Tumor Tracking Based On Beams Eye View EPID Images

Purpose:Dynamic tumor tracking or motion compensation techniques have proposed to modify beam delivery following lung tumor motion on the flight. Conventional treatment plan QA could be performed in advance since every delivery may be different. Markerless lung tumor tracking using beams eye view EPID images provides a best treatment evaluation mechanism. The purpose of this study is to improve the accuracy of the online markerless lung tumor motion tracking method.Methods:The lung tumor could be located on every frame of MV images during radiation therapy treatment by comparing with corresponding digitally reconstructed radiograph (DRR). A kV‐MV CT corresponding curve is applied on planning kV CT to generate MV CT images for patients in order to enhance the similarity between DRRs and MV treatment images. This kV‐MV CT corresponding curve was obtained by scanning a same CT electron density phantom by a kV CT scanner and MV scanner (Tomotherapy) or MV CBCT. Two sets of MV DRRs were then generated for tumor and anatomy without tumor as the references to tracking the tumor on beams eye view EPID images.Results:Phantom studies were performed on a Varian TrueBeam linac. MV treatment images were acquired continuously during each treatment beam delivery at 12 gantry angles by iTools. Markerless tumor tracking was applied with DRRs generated from simulated MVCT. Tumors were tracked on every frame of images and compared with expected positions based on programed phantom motion. It was found that the average tracking error were 2.3 mm.Conclusion:This algorithm is capable of detecting lung tumors at complicated environment without implanting markers. It should be noted that the CT data has a slice thickness of 3 mm. This shows the statistical accuracy is better than the spatial accuracy.This project has been supported by a Varian Research Grant.

Suitability of markerless EPID tracking for tumor position verification in gated radiotherapy

To maximize the benefits of respiratory gated radiotherapy (RGRT) of lung tumors real-time verification of the tumor position is required. This work investigates the feasibility of markerless tracking of lung tumors during beam-on time in electronic portal imaging device (EPID) images of the MV therapeutic beam. EPID movies were acquired at ∼2 fps for seven lung cancer patients with tumor peak-to-peak motion ranges between 7.8 and 17.9 mm (mean: 13.7 mm) undergoing stereotactic body radiotherapy. The external breathing motion of the abdomen was synchronously measured. Both datasets were retrospectively analyzed in PortalTrack, an in-house developed tracking software. The authors define a three-step procedure to run the simulations: (1) gating window definition, (2) gated-beam delivery simulation, and (3) tumor tracking. First, an amplitude threshold level was set on the external signal, defining the onset of beam-on/-off signals. This information was then mapped onto a sequence of EPID images to generate stamps of beam-on/-hold periods throughout the EPID movies in PortalTrack, by obscuring the frames corresponding to beam-off times. Last, tumor motion in the superior-inferior direction was determined on portal images by the tracking algorithm during beam-on time. The residual motion inside the gating window as well as target coverage (TC) and the marginal target displacement (MTD) were used as measures to quantify tumor position variability. Tumor position monitoring and estimation from beam's-eye-view images during RGRT was possible in 67% of the analyzed beams. For a reference gating window of 5 mm, deviations ranging from 2% to 86% (35% on average) were recorded between the reference and measured residual motion. TC (range: 62%-93%; mean: 77%) losses were correlated with false positives incidence rates resulting mostly from intra-/inter-beam baseline drifts, as well as sudden cycle-to-cycle fluctuations in exhale positions. Both phenomena can lead to considerable deviations (with MTD values up to a maximum of 7.8 mm) from the intended tumor position, and in turn may result in a marginal miss. The difference between tumor traces determined within the gating window against ground truth trajectory maps was 1.1 ± 0.7 mm on average (range: 0.4-2.3 mm). In this retrospective analysis of motion data, it is demonstrated that the system is capable of determining tumor positions in the plane perpendicular to the beam direction without the aid of fiducial markers, and may hence be suitable as an online verification tool in RGRT. It may be possible to use the tracking information to enable on-the-fly corrections to intra-/inter-beam variations by adapting the gating window by means of a robotic couch.

Real-time Tracking of Markerless Lung Tumors During SBRT With Continuous MV Imaging

Purpose/Objective(s): Accurate treatment verification is of particular importance when delivering high doses per fraction, as in lung SBRT. In this study, we characterize and validate the performance of a real-time markerless lung tumor-tracking algorithm, using continuous MV portal imaging. MV portal imaging is advantageous, as beam’s-eye-view, images allow motion capture in both directions of steep dose fall-off, and the patient is not exposed to additional imaging dose. Furthermore, a markerless tracking system avoids the risk associated with implanting fiducial markers. Materials/Methods: We retrospectively analyzed the delivery of 9 lung SBRT treatments carried out at our institution. Radiation therapy was delivered with a 6 MV beam in 3 fractions to 54 Gy or in 5 fractions to 60 Gy, using 9-11 beams, including non-coplanar geometries. Treatments were monitored by continuous acquisition of portal images with a frame rate of 2 Hz. Soft tissue motion was tracked on the portal images with a multi-region algorithm developed for this purpose. For each field and each fraction a set of landmark candidates was automatically defined on the first image. The tracker then identified this set on each subsequent image by means of a similarity measure and calculated a centroid trajectory. In this way, the images were analyzed in a prospective manner to simulate in-treatment real-time analysis. The first 40 images of 54 fractions from 34 beam angles were used for comparison with expert human examiners. To minimize bias, the images were presented to the examiner in random sequence and each image was shown 3 times. Tracking error in a realistic phantom was determined as a baseline. Computation time was measured for real-time processing of the images. Results: In-treatment EPID images were successfully acquired for 9 lung SBRT patients with 3 or 5 fractions each (19,942 portal images), including non-coplanar geometries. By comparing with the manual tracking, the RMS tracking accuracy of the automatic marker-less algorithm was found to be (2.1 1.7) mm. Excluding the worst 9 series (out of 54) reduced the RMSE to (1.5 1.1) mm. If we define tracking success as having a RMSE <3 mm, the success rate in our data was 86%. Without any tracking, the error would have been (3.9 2.7) mm. For the phantom study, the tracking error was <1 mm at all times, with a RMSE of (0.8 0.2) mm. The latency of the current implementation is 70-80 ms. Conclusions: In order to verify geometric fidelity during lung SBRT treatments at our institution, we have developed and tested a robust, prospective, real-time algorithm to track lung tumors on portal image sequences without the use of fiducial markers or user intervention. This algorithm can be implemented as a clinical tool for treatment verification, to derive delivered dose, or to drive a real-time motion compensation protocol. Author Disclosure: J. Rottmann: None. Y. Yue: None. A. Chen: None. D. Kozono: None. R. Mak: None. F. Hacker: None. R.I. Berbeco: None.