Lung Tumor Motion Research Articles

1926: Surface and lung tumour motion in surface guided radiotherapy and effects of compression belt

1926: Surface and lung tumour motion in surface guided radiotherapy and effects of compression belt

A novel approach for estimating lung tumor motion based on dynamic features in 4D-CT

Due to the high expenses involved, 4D-CT data for certain patients may only include five respiratory phases (0%, 20%, 40%, 60%, and 80%). This limitation can affect the subsequent planning of radiotherapy due to the absence of lung tumor information for the remaining five respiratory phases (10%, 30%, 50%, 70%, and 90%). This study aims to develop an interpolation method that can automatically derive tumor boundary contours for the five omitted phases using the available 5-phase 4D-CT data. The dynamic mode decomposition (DMD) method is a data-driven and model-free technique that can extract dynamic information from high-dimensional data. It enables the reconstruction of long-term dynamic patterns using only a limited number of time snapshots. The quasi-periodic motion of a deformable lung tumor caused by respiratory motion makes it suitable for treatment using DMD. The direct application of the DMD method to analyze the respiratory motion of the tumor is impractical because the tumor is three-dimensional and spans multiple CT slices. To predict the respiratory movement of lung tumors, a method called uniform angular interval (UAI) sampling was developed to generate snapshot vectors of equal length, which are suitable for DMD analysis. The effectiveness of this approach was confirmed by applying the UAI-DMD method to the 4D-CT data of ten patients with lung cancer. The results indicate that the UAI-DMD method effectively approximates the lung tumor’s deformable boundary surface and nonlinear motion trajectories. The estimated tumor centroid is within 2 mm of the manually delineated centroid, a smaller margin of error compared to the traditional BSpline interpolation method, which has a margin of 3 mm. This methodology has the potential to be extended to reconstruct the 20-phase respiratory movement of a lung tumor based on dynamic features from 10-phase 4D-CT data, thereby enabling more accurate estimation of the planned target volume (PTV).

A 3D-printed phantom for stereotactic body radiation therapy simulation.

In modern radiation therapy for lung cancer, examining the uncertainty between tumor motion and beam delivery is vitally important. To lower the radiation dose delivery to the patient's normal tissue, narrowing the irradiation field margin to hit the tumor accurately is critical. Thus we proposed a phantom that simulates the thorax and lung tumor's motions by employing a 3D printing technique. The lung tumor is controlled by a linear miniature Delta robot arm, with a maximum displacement of 20 mm in each direction. When we simulated the thoracic breathing movements at 12 mm in A-P (Anterior-Posterior), the control errors were within 10%. The average tracking errors of the prosthetic tumor were within 1.1 mm. Therefore, the 3D-printed phantom with a robot arm can provide a reliable simulation for training and dosimetry measurement before lung radiotherapy, especially SBRT.

Treatment Plan Creation and Delivery with and without BgRT for Static and Motion Trajectories

In this work we try to validate the motion tracking capabilities of BgRT for periodic and step motion trajectories. SBRT plans that matches the corresponding BgRT plans are created and delivered to the same phantom with and without motion and results are evaluated. Using BgRT based SBRT plans eliminates any user bias and creates SBRT plans that would represent treatment delivery scenarios that could have happened if the PET guided BgRT was not present for that treatment. To validate SBRT plans that matches the BgRT plans, we used three different types of motion patterns (1) static, (2) lung tumor motion and (3) one-centimeter step-shift. The lung tumor motion (∼25 mm in IEC-Y, ∼7 mm in IEC-X and ∼ 10 mm in IEC-Z) was used as it represents a continuous motion of the target for the entire length of the study while the step-shift case corresponds to the patient or tumor shifting between the localization CT and the start of treatment. First, a 10 Gy per fraction BgRT plan was created for each of the three experiments based on the corresponding PET image. Then, the BgRT plans were delivered to the corresponding targets with and without motion and results are evaluated. To perform a comparative study that assess the performance of BgRT and traditional SBRT (planning and delivery methods), the exact same plan fluence of BgRT plan for each experiment was used to create the corresponding SBRT plans. The newly created SBRT plans were delivered to the corresponding phantom experiments and were compared against BgRT delivery in terms of dose coverage and target margin loss using radiochromic film that moves with the target. The margin loss was calculated as the difference between the distance from the CTV contour to the 97% isodose contour in the treatment plan and the CTV contour to the 97% isodose contour on the film. Dosimetric coverage was on the other hand calculated as the percentage of the voxels within the CTV that lies within 97% and 130% of the prescribed dose. The results showed that the margin loss for BgRT is less than 3 mm, while for the SBRT plans were more than 3 mm when target motion is present. The dosimetric coverage for BgRT was 100% for all three cases, however less than 100% for the SBRT cases with motion. Table showing margin loss for the various experiments for a prescription dose of 10 Gy. The results shows that BgRT is capable of tracking the tumor motion and delivering the prescribed dose to the moving target.

Evaluation of tumour motion and internal/External Correlation in lung SABR.

This study aims to analyse lung tumour motion and to investigate the correlation between the internal tumour motion acquired from four-dimensional computed tomography (4DCT) and the motion of an external surrogate. A dataset of 363 4DCT images was analysed. Tumours were classified based on their anatomical lobes. The recorded gross tumour volume (GTV) information included the centroid GTV motion in the superior-inferior (SI), anteroposterior (AP) and left-right (LR) directions, and in three-dimensions (3D). For the internal/external correlation, the RPM surrogate breathing signals of 260 patients were analysed via an in-house script. The external motion was correlated with the 3D centroid motion, and the maximum tumour motion via Spearman's correlation. The effect of tumour volume on the amount of motion was evaluated. The greatest 3D tumour amplitude was found for tumours located in the lower part of the lung, with a maximum of 26.7 mm. The Spearman's correlation of the internal 3D motion was weak in the upper (r = 0.21) and moderate in the middle (r = 0.51) and the lower (r = 0.52) lobes. There was no obvious difference in the correlation coefficients between the maximum tumour displacement and the centroid motion. No correlation was found between the tumour volume and the magnitude of motion. Our results suggest that tumour location can be a good predictor of its motion. However, tumour size is a poor predictor of the motion. This knowledge of the distribution of tumour motion throughout the thorax will be valuable for research areas where motion management is still in its infancy.

Association of Internal and External Motion Based on Cine MR Images Acquired During Real-Time Treatment on MRI–Guided Linear Accelerator for Patients With Lung Cancer

With the recent clinical implementation of magnetic resonance imaging (MRI)-guided linear accelerators, a large number of real-time planar MR images has been acquired during lung cancer treatment as a standard of care. In this study, associations among lung tumor, diaphragm, and external skin movement were studied based on MR cine imaging during the entire duration of each treatment fraction. This retrospective study used 181,798 planar MRI frames acquired over 55 treatment/imaging sessions of 13 patients with lung cancer treated on 2 MRI-guided linear accelerators. From each planar MR image frame, in-house software automatically extracted 9 features: the superior-interior (SI) and posterior-anterior (PA) positions of a lung tumor; the area of the lung (Lung_Area); the posterior (Dia_Post), dome/apex (Dia_Dome), and anterior (Dia_Ant) points of a diaphragmatic curve; the diaphragm curve point (Dia_Max); and the chest (Chest) and belly (Belly) skin points experienced the maximum range of motions. Correlation analyses were performed among the 9 features for every session. Lung tumor motion range and standard deviations were calculated based on positions obtained in cine images and compared with motion ranges obtained from 4-dimensional computed tomography images. In the study, 177,009 frames of images were successfully analyzed. For all patients, correlation coefficients were as follows: 0.91 ± 0.10 between any 2 features among Lung_Area, Dia_Post, Dia_Dome, and Dia_Max; 0.82 ± 0.21 between SI and any feature among Lung_Area, Dia_Post, Dia_Dome, and Dia_Max; 0.75 ± 0.24 between SI and Belly. Six of 13 patients were considered large amplitude motion (patients with lung tumor SI motion standard deviation >5 mm). Furthermore, 92,956 frames of images were analyzed for the 6 large-amplitude motion patients. For this set, correlation coefficients were 0.93 ± 0.07 between any 2 features among Lung_Area, Dia_Post, Dia_Dome, and Dia_Max; 0.94 ± 0.06 between SI and any feature among Lung_Area, Dia_Post, Dia_Dome, and Dia_Max; and 0.90 ± 0.09 between SI and Belly. Both belly and diaphragmatic motions as assessed by cine MRI are highly correlated with large amplitude lung tumor motion in the longitudinal axis.

Endobronchially Implanted Real-Time Electromagnetic Transponder Beacon–Guided, Respiratory-Gated SABR for Moving Lung Tumors: A Prospective Phase 1/2 Cohort Study

Endobronchial electromagnetic transponder beacons (EMT) provide real-time, precise positional data of moving lung tumors. We report results of a phase 1/2, prospective, single-arm cohort study evaluating the treatment planning effects of EMT-guided SABR for moving lung tumors. Eligible patients were adults, Eastern Cooperative Oncology Group 0 to 2, with T1-T2N0 non-small cell lung cancer or pulmonary metastasis ≤4 cm with motion amplitude ≥5 mm. Three EMTs were endobronchially implanted using navigational bronchoscopy. Four-dimensional free-breathing computed tomography simulation scans were obtained, and end-exhalation phases were used to define the gating window internal target volume. A 3-mm expansion of gating window internal target volume defined the planning target volume (PTV). EMT-guided, respiratory-gated (RG) SABR was delivered (54 Gy/3 fractions or 48 Gy/4 fractions) using volumetric modulated arc therapy. For each RG-SABR plan, a 10-phase image-guided SABR plan was generated for dosimetric comparison. PTV/organ-at-risk (OAR) metrics were tabulated and analyzed using the Wilcoxon signed-rank pair test. Treatment outcomes were evaluated using RECIST (Response Evaluation Criteria in Solid Tumours; version 1.1). Of 41 patients screened, 17 were enrolled and 2 withdrew from the study. Median age was 73 years, with 7 women. Sixty percent had T1/T2 non-small cell lung cancer and 40% had M1 disease. Median tumor diameter was 1.9 cm with 73% of targets located peripherally. Mean respiratory tumor motion was 1.25 cm (range, 0.53-4.04 cm). Thirteen tumors were treated with EMT-guided SABR and 47% of patients received 48 Gy in 4 fractions while 53% received 54 Gy in 3 fractions. RG-SABR yielded an average PTV reduction of 46.9% (P < .005). Lung V5, V10, V20, and mean lung dose had mean relative reductions of 11.3%, 20.3%, 31.1%, and 20.3%, respectively (P < .005). Dose to OARs was significantly reduced (P < .05) except for spinal cord. At 6 months, mean radiographic tumor volume reduction was 53.5% (P < .005). EMT-guided RG-SABR significantly reduced PTVs of moving lung tumors compared with image-guided SABR. EMT-guided RG-SABR should be considered for tumors with large respiratory motion amplitudes or those located in close proximity to OARs.

Real-time respiratory motion prediction using photonic reservoir computing

Respiration induced motion is a well-recognized challenge in many clinical practices including upper body imaging, lung tumor motion tracking and radiation therapy. In this work, we present a recurrent neural network algorithm that was implemented in a photonic delay-line reservoir computer (RC) for real-time respiratory motion prediction. The respiratory motion signals are quasi-periodic waveforms subject to a variety of non-linear distortions. In this work, we demonstrated for the first time that RC can be effective in predicting short to medium range of respiratory motions within practical timescales. A double-sliding window technology is explored to enable the real-time establishment of an individually trained model for each patient and the real-time processing of live-streamed respiratory motion data. A breathing dataset from a total of 76 patients with breathing speeds ranging from 3 to 20 breaths per minute (BPM) is studied. Motion prediction of look-ahead times of 66.6, 166.6, and 333 ms are investigated. With a 333 ms look-ahead time, the real-time RC model achieves an average normalized mean square error (NMSE) of 0.025, an average mean absolute error (MAE) of 0.34 mm, an average root mean square error (RMSE) of 0.45 mm, an average therapeutic beam efficiency (TBE) of 94.14% for an absolute error (AE) < 1 mm, and 99.89% for AE < 3 mm. This study demonstrates that real-time RC is an efficient computing framework for high precision respiratory motion prediction.

Machine learning for predicting accuracy of lung and liver tumor motion tracking using radiomic features.

Internal tumor motion is commonly predicted using external respiratory signals. However, the internal/external correlation is complex and patient-specific. The purpose of this study was to develop various models based on the radiomic features of computed tomography (CT) images to predict the accuracy of tumor motion tracking using external surrogates and to find accurate and reliable tracking algorithms. Images obtained from a total of 108 and 71 patients pathologically diagnosed with lung and liver cancers, respectively, were examined. Real-time position monitoring motion was fitted to tumor motion, and samples with fitting errors greater than 2 mm were considered positive. Radiomic features were extracted from internal target volumes of average intensity projections, and cross-validation least absolute shrinkage and selection operator (LassoCV) was used to conduct feature selection. Based on the radiomic features, a total of 26 separate models (13 for the lung and 13 for the liver) were trained and tested. Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to assess performance. Relative standard deviation was used to assess stability. Thirty-three and 22 radiomic features were selected for the lung and liver, respectively. For the lung, the AUC varied from 0.848 (decision tree) to 0.941 [support vector classifier (SVC), logistic regression]; sensitivity varied from 0.723 (extreme gradient boosting) to 0.848 [linear support vector classifier (linearSVC)]; specificity varied from 0.834 (gaussian naive bayes) to 0.936 [multilayer perceptron (MLP), wide and deep (W&D)]; and MLP and W&D had better performance and stability than the median. For the liver, the AUC varied from 0.677 [light gradient boosting machine (Light)] to 0.892 (logistic regression); sensitivity varied from 0.717 (W&D) to 0.862 (MLP); specificity varied from 0.566 (Light) to 0.829 (linearSVC); and logistic regression, MLP, and SVC had better performance and stability than the median. Respiratory-sensitive radiomic features extracted from CT images of lung and liver tumors were proved to contain sufficient information to establish an external/internal motion relationship. We developed a rapid and accurate method based on radiomics to classify the accuracy of monitoring a patient's external surface for lung and liver tumor tracking. Several machine learning algorithms-in particular, MLP-demonstrated excellent classification performance and stability.

Evaluation of the four-dimensional motion of lung tumors during end-exhalation breath-hold conditions using volumetric cine computed tomography images

Background and purposeThis study was performed to evaluate the four-dimensional motion of lung tumors during end-exhalation (EE) breath-holding (BH) using cine computed tomography (CT) and investigate the correlation between tumor and surrogate marker motions. Materials and methodsThis study included 28 patients who underwent stereotactic body radiation therapy at our institution and were capable of 15–20 s of EE BH within a ±1.5-mm gating window with external markers. During EE BH with cine CT, 21 s of continuous data were acquired using 320-row multislice CT. Displacements in the tumor position during EE BH were assessed in the left–right (LR), anterior–posterior (AP), and superior–inferior (SI) directions. Pearson’s correlation coefficient (r) between tumor motions during EE BH and diaphragm/external marker motions was also determined. ResultsThe mean absolute maximum displacements of the tumor position during EE BH were 1.3 (range: 0.2–4.0), 1.9 (range: 0.3–12.0), and 1.3 (range: 0.1–7.2) mm in the LR, AP, and SI directions, respectively. The displacement of the tumor position in the AP direction was weakly correlated (|r| < 0.4) with the external marker and diaphragm displacements in many cases (proportions of 50% and 46%, respectively). ConclusionWe found some cases showing substantial displacement in lung tumor positions during EE BH, especially in the AP direction. Because these tumor position displacements did not correlate with surrogate markers and were difficult to detect, we recommend pretreatment evaluation of the four-dimensional motions of tumors during BH using cine CT.

Quantification of Lung Tumor Motion and Optimization of Treatment.

Mobility of lung tumors is induced by respiration and causes inadequate dose coverage. This study quantified lung tumor motion, velocity, and stability for small (≤5 cm) and large (>5 cm) tumors to adapt radiation therapy techniques for lung cancer patients. In this retrospective study, 70 patients with lung cancer were included that 50 and 20 patients had a small and large gross tumor volume (GTV). To quantify the tumor motion and velocity in the upper lobe (UL) and lower lobe (LL) for the central region (CR) and a peripheral region (PR), the GTV was contoured in all ten respiratory phases, using 4D-CT. The amplitude of tumor motion was greater in the LL, with motion in the superior-inferior (SI) direction compared to the UL, with an elliptical motion for small and large tumors. Tumor motion was greater in the CR, rather than in the PR, by 63% and 49% in the UL compared to 50% and 38% in the LL, for the left and right lung. The maximum tumor velocity for a small GTV was 44.1 mm/s in the LL (CR), decreased to 4 mm/s for both ULs (PR), and a large GTV ranged from 0.4 to 9.4 mm/s. The tumor motion and velocity depend on the tumor localization and the greater motion was in the CR for both lobes due to heart contribution. The tumor velocity and stability can help select the best technique for motion management during radiation therapy.

Lung Tumor Motion and its Impact on Deep Learning Prediction of Local Recurrence

<h3>Purpose/Objective(s)</h3> In order for deep learning (DL) models to successfully predict local recurrence of lung tumors from image-based features, uncertainties of the model must be quantified. One potential source of uncertainty for the DL model is lung tumor motion. We aimed to evaluate the association of motion magnitude with the prediction accuracy of the DL model. We hypothesized that knowledge of motion will help quantify the uncertainties of prediction and guide the use of individualized risk predictions for lung radiotherapy. <h3>Materials/Methods</h3> Physician delineated gross tumor volume (GTV) of 19 patients were propagated to their corresponding 10 breathing phases of the 4DCT images using a commercial treatment planning system. A programming environment code was used to extract the contours and determine the centroid and volume bounded by the contours. Motion was determined from the displacement of the GTV centroid. The Euclidean distance was calculated and used as an aggregate measure of tumor motion magnitude. The 4DCT, free-breathing CT (FBCT) and maximum-intensity projection (MIP) images of the 18 patients were used as input to a pre-trained DL model. The 8-layer DL model was previously trained to predict local recurrence using FBCT images of 933 lung patients. Correlation between motion magnitude and prediction accuracy was calculated for 4DCT images in each respiratory phase, FBCT and MIP images. <h3>Results</h3> Tumor movement with a mean exertion of 1 cm [IQR: 0.72-1.53] was observed from the cohort with 47.4 % of patients subjected to abdominal compression, and 57.9% of patients had peripheral lung tumors. The standard deviation of DL scores obtained from each 4DCT image correlated with the magnitude of tumor motion (R² =0.45, p=0.005). Higher uncertainty in DL scores was attributed to the larger tumor motion. The average DL score obtained from the 10 phases of the 4DCT images of each patient was (i) highly associated with the DL scores obtained from the FBCT images (r = 0.99; p<0.0001), and (ii) closest to the DL score obtained with the end-inspiration images. In comparing the prediction performance across image acquisition types, MIP images yields a higher DL score compared to FBCT (<i>p</i><0.0001) or 4DCT images (<i>p</i> =<0.0001). <h3>Conclusion</h3> The impact of tumor motion on the range of DL scores for prediction of local recurrence was reported for the first time. Standard deviations of the DL scores increased with motion magnitude. However, when DL score was measured and averaged across the 10 phases of the 4DCT images, DL score correlated well with those obtained from the FBCT images. This preliminary finding suggests that despite the increased variation with larger motion, the DL score, when averaged across the sinusoidal breathing trajectory, correlates with the DL score obtained from the FBCT images that were used for treatment planning. However, caution should be exercised when using MIP images for local recurrence prediction since a higher DL score than the FBCT images used for planning will be observed.

Endobronchial Implanted Real-Time Radiofrequency (RF) Transponder Beacon Guided, Respiratory-Gated, Stereotactic Body Radiotherapy for Moving Lung Tumors: Interim Analysis of a Prospective Phase I/II Cohort Study

<h3>Purpose/Objective(s)</h3> Endobronchially implanted real-time tracking system (technology company) radiofrequency (RF) transponder beacons provide real-time, high precision, positional data of moving lung tumors. We report interim results of a Phase I/II prospective single arm prospective cohort study evaluating feasibility and dosimetric impact of real-time tracking system beacons for patients undergoing SBRT for moving lung tumors. <h3>Materials/Methods</h3> Eligible patients were adults, ECOG 0-2, with T1-T2N0 Non-small cell lung cancer (NSCLC) or pulmonary metastasis ≤4cm of the right middle/lower lobe, or lingula. Upper lobe tumors were eligible if they moved ≥5mm. Three real-time tracking system beacons were endobronchially implanted at prespecified peritumoral locations using SuperDimension™ navigational bronchoscopy (Medtronic, USA). Four-dimensional free-breathing CT simulation scans were obtained and end-exhalation phases were selected to define a gating window (GW). A 3mm expansion of the ITV_GW defined the PTV. Real-time tracking system-guided, respiratory phase-gated, SBRT (GW-SBRT) was delivered using 10MV VMAT photon arcs at 2400MU/min to total doses of 54Gy/3# or 48Gy/4#. For each GW-SBRT plan, a corresponding 10-phase plan was generated for comparison to standard image-guided (IG)SBRT. PTV, and OAR metrics were tabulated and differences between GW-SBRT and IG-SBRT plans analyzed using non-parametric Wilcoxon Signed-Rank pair test. Treatment related toxicity was graded using the Common Terminology Criteria for Adverse Events (CTCAE) version 4.0. <h3>Results</h3> From November 2017 to December 2021, 41 patients were screened and 17 patients consented to participate. Two patients did not undergo beacon implant: one had tumor progression; another withdrew consent. Of the 15 patients with beacon implants, median age was 73, with 7 females. 47% were T1 NSCLC, 40% were M1 and remaining 13% were T2 NSCLC. Median tumor dimension was 1.9cm. 73% of targets were located peripherally, and 27% centrally with a median respiratory tumor motion of 1.25 cm (range 0.53 cm to 4.04 cm). No beacon migration was observed between CT simulation scan and the completion of SBRT treatments. Of the N=12 tumor targets were treated with GW-SBRT, 47% of patients received 48Gy/4# and 53% received 54Gy/3#. GW-SBRT yielded an average relative reduction of PTV of 46.9% (p<0.005) compared with IG-SBRT. Lung V5, V10, V20 and D2 had mean relative reductions of 11.3%, 20.3%, 31.1% and 15.5% respectively (p<0.005). Dose to OARs was significantly reduced (p<0.05) except for spinal cord. At 6 months follow-up, mean radiographic tumor volume reduction was 53.5% (p<0.005); No treatment related grade 3 toxicity was observed. <h3>Conclusion</h3> Endobronchial RF beacons are safe and effective at reducing SBRT treatment volumes for patients with moving lung tumors and can be considered for tumors with large motion amplitude or those located in close proximity to organs at risk. This study has the ClinicalTrials.gov identifier NCT03322072.

Statistical breathing curve sampling to quantify interplay effects of moving lung tumors in a 4D Monte Carlo dose calculation framework

PurposeThe interplay between respiratory tumor motion and dose application by intensity modulated radiotherapy (IMRT) techniques can potentially lead to undesirable and non-intuitive deviations from the planned dose distribution. We developed a 4D Monte Carlo (MC) dose recalculation framework featuring statistical breathing curve sampling, to precisely simulate the dose distribution for moving target volumes aiming at a comprehensive assessment of interplay effects. MethodsWe implemented a dose accumulation tool that enables dose recalculations of arbitrary breathing curves including the actual breathing curve of the patient. This MC dose recalculation framework is based on linac log-files, facilitating a high temporal resolution up to 0.1 s. By statistical analysis of 128 different breathing curves, interplay susceptibility of different treatment parameters was evaluated for an exemplary patient case. To facilitate prospective clinical application in the treatment planning stage, in which patient breathing curves or linac log-files are not available, we derived a log-file free version with breathing curves generated by a random walk approach. Interplay was quantified by standard deviations σ in D5%, D50% and D95%. ResultsInterplay induced dose deviations for single fractions were observed and evaluated for IMRT and volumetric arc therapy (σD95% up to 1.3 %) showing a decrease with higher fraction doses and an increase with higher MU rates. Interplay effects for conformal treatment techniques were negligible (σ<0.1%). The log-file free version and the random walk generated breathing curves yielded similar results (deviations in σ< 0.1 %) and can be used as substitutes for interplay assessment. ConclusionIt is feasible to combine statistically sampled breathing curves with MC dose calculations. The universality of the presented framework allows comprehensive assessment of interplay effects in retrospective and prospective clinically relevant scenarios.

A new method for assessing lung tumor motion in radiotherapy using dynamic chest radiography.

Dynamic chest radiography (DCR) is a recent advanced modality to acquire dynamic and functional images. We developed a new method using DCR and the free analysis software, Kinovea, to assess lung tumor motion. This study aimed to demonstrate the usefulness of our method. Phantom and clinical studies were performed. In the phantom study, dynamic images of a moving lead sphere were acquired using DCR, and the motion of the phantom was tracked using Kinovea in a DCR video. The amplitude of phantom motion was measured and compared with a predetermined baseline amplitude. In a clinical study, DCR and respiratory‐gated four‐dimensional computed tomography (4D‐CT) were performed on 15 patients who underwent stereotactic body radiation therapy for lung tumors. The amplitudes of tumor motion in DCR and 4D‐CT were measured in the superior‐inferior (SI), left‐right (LR), and anterior‐posterior (AP) directions, and the square root of the sum of squares (SRSS) of the amplitude was calculated in all directions. Spearman's rank correlation and the Wilcoxon signed‐rank test were performed to determine the correlations of the amplitudes of tumor motion obtained using DCR and 4D‐CT. In the phantom study, the absolute mean error between the measured and predetermined amplitudes was 0.60 mm (range: 0.061.53 mm). In the clinical study, the amplitudes of tumor motion obtained using DCR correlated significantly with those of 4D‐CT in the SI and LR directions, as did the SRSS values. The median amplitudes for DCR were significantly higher than those for 4D‐CT in all (SI, LR, and AP) directions, as were the SRSS values. Our proposed method based on DCR and Kinovea is useful for assessing lung tumor motion, visually and quantitatively. Therefore, DCR has potential as a new modality for evaluating lung tumor motion in radiotherapy.

Dosimetric effects of respiratory motion during stereotactic body radiation therapy of lung tumors

Background Respiratory-induced lung tumor motion may affect the delivered dose in stereotactic body radiation therapy (SBRT). Previous studies are often based on phantom studies for one specific treatment technique. In this study, the dosimetric effect of tumor motion was quantified in real patient geometries for different modulated treatments and tumor motion amplitudes for lung-SBRT. Material and Methods A simulation method using deformable image registrations and 4-dimensional computed tomographies (4DCT) was developed to assess the dosimetric effects of tumor motion. The method was evaluated with ionization chamber and Gafchromic film measurements in a thorax phantom and used to simulate the effect for 15 patients with lung tumors moving 7.3–27.4 mm. Four treatment plans with different complexities were created for each patient and the motion-induced dosimetric effect to the gross tumor volume (GTV) was simulated. The difference between the planned dose to the static tumor and the simulated delivered dose to the moving tumor was quantified for the near minimum (D98%), near maximum (D2%) and mean dose (Dmean) to the GTV as well as the largest observed local difference within the GTV (Maxdiff). Results No correlation was found between the dose differences and the tumor motion amplitude or plan complexity. However, the largest deviations were observed for tumors moving >15.0 mm. The simulated delivered dose was within 2.5% from the planned dose for D98% (tumors moving <15 mm) and within 3.3% (tumors moving >15 mm). The corresponding values were 1.7% vs. 6.4% (D2%); 1.7% vs. 2.4% (Dmean) and 8.9% vs. 35.2% (Maxdiff). Using less complex treatment techniques minimized Maxdiff for tumors moving >15.0 mm. Conclusion The dosimetric effects of respiratory-induced motion during lung SBRT are patient and plan specific. The magnitude of the dosimetric effect cannot be assessed solely based upon tumor motion amplitude or plan complexity.

Correlation of Optical Surface Respiratory Motion Signal and Internal Lung and Liver Tumor Motion: A Retrospective Single-Center Observational Study.

Purpose: Surface-guided radiation therapy (SGRT) application has limitations. This study aimed to explore the relationship between patient characteristics and their external/internal correlation to qualitatively assess the external/internal correlation in a particular patient. Methods: Liver and lung cancer patients treated with radiotherapy in our institution were retrospectively analyzed. The external/internal correlation were calculated with Spearman correlation coefficient (SCC) and SCC after support vector regression (SVR) fitting (SCCsvr). The relationship between the external/internal correlation and magnitudes of motion of the tumor and external marker (Ai, Ae), tumor volume Vt, patient age, gender, and tumor location were explored. Results: The external/internal motions of liver and lung cancer patients were strongly correlated in the S-I direction, with mean SCCsvr values of 0.913 and 0.813. The correlation coefficients between the external/internal correlations and the patients’ characteristics (Ai, Ae, Vt, and age) were all smaller than 0.5; Ai, Ae and liver tumor volumes were positively correlated with the strength of the external/internal correlation, while lung tumor volumes and patient age were negative. The external/internal correlations in males and females were roughly equal, and the external/internal correlations in patients with peripheral lung cancers were stronger than those in patients with central lung cancers. Conclusion: The external/internal correlation shows great individual differences. The effects of Ai, Ae, Vt, and age are weakly to moderately correlated. Our results suggest the necessity of individualized assessment of patient's external/internal motion correlation prior to the application of SGRT technique for breath motion monitoring.

Machine Learning Radiomics Model for External and Internal Respiratory Motion Correlation Prediction in Lung Tumor.

Objectives: The complexity and specificity of lung tumor motion render it necessary to determine the external and internal correlation individually before applying indirect tumor tracking. However, the correlation cannot be determined from patient respiratory and tumor clinical characteristics before treatment. The purpose of this study is to present a machine learning model for an external/internal correlation prediction that is based on computed tomography (CT) radiomic features. Methods: 4-dimensional computed tomography (4DCT) images of 67 patients were collected retrospectively, and the external/internal correlation of lung tumor was calculated based on Spearman's rank correlation coefficient. Radiomic features were extracted from average intensity projection and the light gradient boosting machine (LightGBM)-based cross-validation (the recursive elimination method) was used for feature selection. The LightGBM framework forecasting models with classification thresholds 0.7, 0.8, and 0.9 are established using stratified 5-fold cross-validation. Model performance was assessed using receiver operating characteristics, sensitivity, and specificity. Results: There were 16, 18, and 13 features selected for models 0.7, 0.8, and 0.9, respectively. Texture features are of great importance in external/internal correlation prediction compared to other features in all models. The sensitivities of the predictions in models 0.7, 0.8, and 0.9 were 0.800 ± 0.126, 0.829 ± 0.140, and 0.864 ± 0.086, respectively. The specificities were 0.771 ± 0.114, 0.936 ± 0.0581, and 0.839 ± 0.101, whereas the area under the curve (AUC) was 0.837, 0.946, and 0.877, respectively. Conclusions: Our findings indicate that radiomics is an effective tool for respiratory motion correlation prediction, which can extract tumor motion characteristics. We proposed a machine learning framework for correlation prediction in the motion management strategy for lung tumor patients.

Four-Dimensional Computed Tomography-Based Correlation of Respiratory Motion of Lung Tumors With Implanted Fiducials and an External Surrogate

PurposeOur purpose was to assess the suitability of airway-implanted internal fiducial markers and an external surrogate of respiratory motion for motion management during radiation therapy of lung tumors. Methods and MaterialsWe analyzed 4-dimensional computed tomography scans acquired during radiation therapy simulation for 28 patients with lung tumors who had anchored fiducial markers bronchoscopically implanted inside small airways in or near the tumor in a prospective trial. We used a linear mixed model to build population-based correlative models of tumor and surrogate motion. The first 24 of the 28 patients were used to build correlative models, and 4 of the 28 consecutive patients were excluded and used as an internal validation cohort. Of the 24 patients from the model building cohort, all were used for the models based on the internal fiducial. The external surrogate was completely visualized in 11 patients from the model building cohort, so only those were used for the models based on the external surrogate. Furthermore, we determined the predicted residual error sum of squares for our correlative models, which may serve as benchmarks for future research. ResultsThe motion of the internal fiducials was significantly associated with the tumor motion in the anterior-posterior (P < .0001) and superior-inferior (SI) directions (P < .0001). We also observed a strong correlation of the external surrogate anterior-posterior motion to the tumor dominant SI motion (P < .0001). In the validation cohort, the internal fiducial SI motion was the only reliable predictor of lung tumor motion. ConclusionsThe internal fiducials appear to be more reliable predictors of lung tumor motion than the external surrogate. The suitability of such airway-implanted internal fiducial markers for advanced motion management techniques should be further investigated. Although the external surrogate seems to be less reliable, its wide availability and noninvasive application support its clinical utility, albeit the greater uncertainty will need to be compensated for.

Prediction of Large Change in Lung Tumor Motion During Treatment Course: An Ensemble Learning Method With Enhanced Positive Predictive Values

During lung cancer radiotherapy, tumor motion magnitude may change, resulting in either inadequate margins or non-ideal dose conformality (margins are unnecessarily too big). To predict large motion change using only patient-specific clinical information and the simulation 4DCT images, we proposed an ensemble learning model (ELM) with robust feature selection (FS). For this specific study, we minimized the false negative prediction so that we will not miss patients who might have a subsequent large change in tumor motion. Thus, we employed positive predictive values (PPV) as the evaluation metric instead of commonly used accuracy scores.Seventeen features were collected including both clinical factors and imaging features. The motion change is defined by motion difference in SI direction between the simulation 4DCT and mid-course repeat 4DCT with the clinical threshold set as 3 mm. The dataset consisted of 140 patients, where 31 showed large tumor motion change. Four hundred seventy-two sets of 4DCT images were analyzed in this study. The ELM adopts 5 conventional predictive models (logistic regression (LR), decision tree (DT), support vector machine (SVM), random forest (RF), and XGBoost (XGB)) as base predictors. Then, the results are employed as inputs for a two-layer neural network to obtain a final prediction. To enhance the feature sensitivity and to reduce data noise, we developed a robust FS strategy with sequential backward selection. Each criterion score is an average from 5-fold cross-valuation, and the target feature of each round is based on 1000 repeated experiments. The peak of the criterion score after sequential removal of the least sensitive features was used to select the optimal feature set.By employing PPV as the criterion function, all the base predictors ranked initial SI tumor motion as the most important feature. ROC curve with selected sensitive features consistently outperformed the one with all features. For ELM, the AUCs (mean std. ± dev.) were 0.63 ± 0.04 when all features were included and increased to 0.72 ± 0.02 for PPV-based selected features only. The prediction comparisons were performed for all base predictors and ELM with 100 repetitions. The PPV results (Table 1) demonstrated the proposed ELM obtained superior performance than each base predictor.We proposed an ELM to identify patients with potential large tumor motion change using only information prior to the first treatment. The ELM showed superior performance with PPV-driven metrics. We also developed a feature selection strategy for each base predictor, and the consistent superiority was demonstrated by ROC results. In future work, additional information from on-treatment evaluation CTs may further improve the prediction.