Search

Background and purposeMotion management is essential to reduce normal tissue exposure and maintain adequate tumor dose in lung stereotactic body radiation therapy (SBRT). Lung SBRT using an articulated robotic arm allows dynamic tracking during radiation dose delivery. Two stereoscopic X-ray tracking modes are available - fiducial-based and fiducial-free tracking. Although X-ray detection of implanted fiducials is robust, the implantation procedure is invasive and inapplicable to some patients and tumor locations. Fiducial-free tracking relies on tumor contrast, which challenges the existing tracking algorithms for small (e.g., <15 mm) and/or tumors obscured by overlapping anatomies. To markedly improve the performance of fiducial-free tracking, we proposed a deep learning-based template matching algorithm - Deep Match.MethodDeep Match consists of four self-definable stages - training-free feature extractor, similarity measurements for location proposal, local refinements, and uncertainty level prediction for constructing a more trustworthy and versatile pipeline. Deep Match was validated on a 10 (38 fractions; 2661 images) patient cohort whose lung tumor was trackable on one X-ray view, while the second view did not offer sufficient conspicuity for tumor tracking using existing methods. The patient cohort was stratified into subgroups based on tumor sizes (<10 mm, 10-15 mm, and >15 mm) and tumor locations (with/without thoracic anatomy overlapping).ResultsOn X-ray views that conventional methods failed to track the lung tumor, Deep Match achieved robust performance as evidenced by >80 % 3 mm-Hit (detection within 3 mm superior/inferior margin from ground truth) for 70 % of patients and <3 mm superior/inferior distance (SID) ∼1 mm standard deviation for all the patients.ConclusionDeep Match is a zero-shot learning network that explores the intrinsic neural network benefits without training on patient d

PurposeMegavoltage computed tomography (MVCT) has been implemented on many radiation therapy treatment machines as a tomographic imaging modality that allows for three-dimensional visualization and localization of patient anatomy. Yet MVCT images exhibit lower contrast and greater noise than its kilovoltage CT (kVCT) counterpart. In this work, we sought to improve these disadvantages of MVCT images through an image-to-image-based machine learning transformation of MVCT and kVCT images. We demonstrated that by learning the style of kVCT images, MVCT images can be converted into high-quality synthetic kVCT (skVCT) images with higher contrast and lower noise, when compared to the original MVCT.MethodsKilovoltage CT and MVCT images of 120 head and neck (H&N) cancer patients treated on an Accuray TomoHD system were retrospectively analyzed in this study. A cycle-consistent generative adversarial network (CycleGAN) machine learning, a variant of the generative adversarial network (GAN), was used to learn Hounsfield Unit (HU) transformations from MVCT to kVCT images, creating skVCT images. A formal mathematical proof is given describing the interplay between function sensitivity and input noise and how it applies to the error variance of a high-capacity function trained with noisy input data. Finally, we show how skVCT shares distributional similarity to kVCT for various macro-structures found in the body.ResultsSignal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were improved in skVCT images relative to the original MVCT images and were consistent with kVCT images. Specifically, skVCT CNR for muscle-fat, bone-fat, and bone-muscle improved to 14.8 ± 0.4, 122.7 ± 22.6, and 107.9 ± 22.4 compared with 1.6 ± 0.3, 7.6 ± 1.9, and 6.0 ± 1.7, respectively, in the original MVCT images and was more consistent with kVCT CNR values of 15.2 ± 0.8, 124.9 ± 27.0, and 109.7 ± 26.5, resp

Deep learning algorithms have recently been developed that utilize patient anatomy and raw imaging information to predict radiation dose, as a means to increase treatment planning efficiency and improve radiotherapy plan quality. Current state-of-the-art techniques rely on convolutional neural networks (CNNs) that use pixel-to-pixel loss to update network parameters. However, stereotactic body radiotherapy (SBRT) dose is often heterogeneous, making it difficult to model using pixel-level loss. Generative adversarial networks (GANs) utilize adversarial learning that incorporates image-level loss and is better suited to learn from heterogeneous labels. However, GANs are difficult to train and rely on compromised architectures to facilitate convergence. This study suggests an attention-gated generative adversarial network (DoseGAN) to improve learning, increase model complexity, and reduce network redundancy by focusing on relevant anatomy. DoseGAN was compared to alternative state-of-the-art dose prediction algorithms using heterogeneity index, conformity index, and various dosimetric parameters. All algorithms were trained, validated, and tested using 141 prostate SBRT patients. DoseGAN was able to predict more realistic volumetric dosimetry compared to all other algorithms and achieved statistically significant improvement compared to all alternative algorithms for the V100 and V120 of the PTV, V60 of the rectum, and heterogeneity index.

Deep learning algorithms have recently been developed that utilize patient anatomy and raw imaging information to predict radiation dose, as a means to increase treatment planning efficiency and improve radiotherapy plan quality. Current state-of-the-art techniques rely on convolutional neural networks (CNNs) that use pixel-to-pixel loss to update network parameters. However, stereotactic body radiotherapy (SBRT) dose is often heterogeneous, making it difficult to model using pixel-level loss. Generative adversarial networks (GANs) utilize adversarial learning that incorporates image-level loss and is better suited to learn from heterogeneous labels. However, GANs are difficult to train and rely on compromised architectures to facilitate convergence. This study suggests an attention-gated generative adversarial network (DoseGAN) to improve learning, increase model complexity, and reduce network redundancy by focusing on relevant anatomy. DoseGAN was compared to alternative state-of-the-art dose prediction algorithms using heterogeneity index, conformity index, and various dosimetric parameters. All algorithms were trained, validated, and tested using 141 prostate SBRT patients. DoseGAN was able to predict more realistic volumetric dosimetry compared to all other algorithms and achieved statistically significant improvement compared to all alternative algorithms for the V100 and V120 of the PTV, V60 of the rectum, and heterogeneity index.

Purpose/objectivesFor lung stereotactic body radiation therapy (SBRT), real-time tumor tracking (RTT) allows for less radiation to normal lung compared to the internal target volume (ITV) method of respiratory motion management. To quantify the advantage of RTT, we examined the difference in radiation pneumonitis risk between these two techniques using a normal tissue complication probability (NTCP) model.Materials/method20 lung SBRT treatment plans using RTT were replanned with the ITV method using respiratory motion information from a 4D-CT image acquired at the original simulation. Risk of symptomatic radiation pneumonitis was calculated for both plans using a previously derived NTCP model. Features available before treatment planning that identified significant increase in NTCP with ITV versus RTT plans were identified.ResultsPrescription dose to the planning target volume (PTV) ranged from 22 to 60 Gy in 1-5 fractions. The median tumor diameter was 3.5 cm (range 2.1-5.5 cm) with a median volume of 14.5 mL (range 3.6-59.9 mL). The median increase in PTV volume from RTT to ITV plans was 17.1 mL (range 3.5-72.4 mL), and the median increase in PTV/lung volume ratio was 0.46% (range 0.13-1.98%). Mean lung dose and percentage dose-volumes were significantly higher in ITV plans at all levels tested. The median NTCP was 5.1% for RTT plans and 8.9% for ITV plans, with a median difference of 1.9% (range 0.4-25.5%, pairwise P < 0.001). Increases in NTCP between plans were best predicted by increases in PTV volume and PTV/lung volume ratio.ConclusionsThe use of RTT decreased the risk of radiation pneumonitis in all plans. However, for most patients the risk reduction was minimal. Differences in plan PTV volume and PTV/lung volume ratio may identify patients who would benefit from RTT technique before completing treatment planning.

Purpose/objectivesFor lung stereotactic body radiation therapy (SBRT), real-time tumor tracking (RTT) allows for less radiation to normal lung compared to the internal target volume (ITV) method of respiratory motion management. To quantify the advantage of RTT, we examined the difference in radiation pneumonitis risk between these two techniques using a normal tissue complication probability (NTCP) model.Materials/method20 lung SBRT treatment plans using RTT were replanned with the ITV method using respiratory motion information from a 4D-CT image acquired at the original simulation. Risk of symptomatic radiation pneumonitis was calculated for both plans using a previously derived NTCP model. Features available before treatment planning that identified significant increase in NTCP with ITV versus RTT plans were identified.ResultsPrescription dose to the planning target volume (PTV) ranged from 22 to 60 Gy in 1-5 fractions. The median tumor diameter was 3.5 cm (range 2.1-5.5 cm) with a median volume of 14.5 mL (range 3.6-59.9 mL). The median increase in PTV volume from RTT to ITV plans was 17.1 mL (range 3.5-72.4 mL), and the median increase in PTV/lung volume ratio was 0.46% (range 0.13-1.98%). Mean lung dose and percentage dose-volumes were significantly higher in ITV plans at all levels tested. The median NTCP was 5.1% for RTT plans and 8.9% for ITV plans, with a median difference of 1.9% (range 0.4-25.5%, pairwise P < 0.001). Increases in NTCP between plans were best predicted by increases in PTV volume and PTV/lung volume ratio.ConclusionsThe use of RTT decreased the risk of radiation pneumonitis in all plans. However, for most patients the risk reduction was minimal. Differences in plan PTV volume and PTV/lung volume ratio may identify patients who would benefit from RTT technique before completing treatment planning.

Treatment plans for prostate cancer patients undergoing stereotactic body radiation therapy (SBRT) are often challenging due to the proximity of organs at risk. Today, there are no objective criteria to determine whether an optimal treatment plan has been achieved, and physicians rely on their personal experience to evaluate the plan's quality. In this study, we propose a method for determining rectal and bladder dose constraints achievable for a given patient's anatomy. We expect that this method will improve the overall plan quality and consistency, and facilitate comparison of clinical outcomes across different institutions. The 3D proximity of the organs at risk to the target is quantified by means of the expansion-intersection volume (EIV), which is defined as the intersection volume between the target and the organ at risk expanded by 5 mm. We determine a relationship between EIV and relevant dosimetric parameters, such as the volume of bladder and rectum receiving 75% of the prescription dose (V75%). This relationship can be used to establish institution-specific criteria to guide the treatment planning and evaluation process. A database of 25 prostate patients treated with CyberKnife SBRT is used to validate this approach. There is a linear correlation between EIV and V75% of bladder and rectum, confirming that the dose delivered to rectum and bladder increases with increasing extension and proximity of these organs to the target. This information can be used during the planning stage to facilitate the plan optimization process, and to standardize plan quality and consistency. We have developed a method for determining customized dose constraints for prostate patients treated with robotic SBRT. Although the results are technology specific and based on the experience of a single institution, we expect that the application of this method by other institutions will result in improved standardization of clinical practice.

Treatment plans for prostate cancer patients undergoing stereotactic body radiation therapy (SBRT) are often challenging due to the proximity of organs at risk. Today, there are no objective criteria to determine whether an optimal treatment plan has been achieved, and physicians rely on their personal experience to evaluate the plan's quality. In this study, we propose a method for determining rectal and bladder dose constraints achievable for a given patient's anatomy. We expect that this method will improve the overall plan quality and consistency, and facilitate comparison of clinical outcomes across different institutions. The 3D proximity of the organs at risk to the target is quantified by means of the expansion-intersection volume (EIV), which is defined as the intersection volume between the target and the organ at risk expanded by 5 mm. We determine a relationship between EIV and relevant dosimetric parameters, such as the volume of bladder and rectum receiving 75% of the prescription dose (V75%). This relationship can be used to establish institution-specific criteria to guide the treatment planning and evaluation process. A database of 25 prostate patients treated with CyberKnife SBRT is used to validate this approach. There is a linear correlation between EIV and V75% of bladder and rectum, confirming that the dose delivered to rectum and bladder increases with increasing extension and proximity of these organs to the target. This information can be used during the planning stage to facilitate the plan optimization process, and to standardize plan quality and consistency. We have developed a method for determining customized dose constraints for prostate patients treated with robotic SBRT. Although the results are technology specific and based on the experience of a single institution, we expect that the application of this method by other institutions will result in improved standardization of clinical practice.

Stereotactic body radiation therapy is a well-tolerated modality for the treatment of primary and metastatic liver lesions, and fiducials are often used as surrogates for tumor tracking during treatment. We evaluated respiratory-induced liver deformation by measuring the rigidity of the fiducial configuration during the breathing cycle. Seventeen patients, with 18 distinct treatment courses, were treated with stereotactic body radiosurgery using multiple fiducials. Liver deformation was empirically quantified by measuring the intrafiducial distances at different phases of respiration. Data points were collected at the 0%, 50%, and 100% inspiration points, and the distance between each pair of fiducials was measured at the 3 phases. The rigid body error was calculated as the maximum difference in the intrafiducial distances. Liver disease was calculated with Child-Pugh score using laboratory values within 3 months of initiation of treatment. A peripheral fiducial was defined as within 1.5 cm of the liver edge, and all other fiducials were classified as central. For 5 patients with only peripheral fiducials, the fiducial configuration had more deformation (average maximum rigid body error 7.11 mm, range: 1.89-11.35 mm) when compared to patients with both central and peripheral and central fiducials only (average maximum rigid body error 3.36 mm, range: 0.5-9.09 mm, P = .037). The largest rigid body errors (11.3 and 10.6 mm) were in 2 patients with Child-Pugh class A liver disease and multiple peripheral fiducials. The liver experiences internal deformation, and the fiducial configuration should not be assumed to act as a static structure. We observed greater deformation at the periphery than at the center of the liver. In our small data set, we were not able to identify cirrhosis, which is associated with greater rigidity of the liver, as predictive for deformation. Treatment planning based only on fiducial localization must take potential intraorgan deformation into

Stereotactic body radiation therapy is a well-tolerated modality for the treatment of primary and metastatic liver lesions, and fiducials are often used as surrogates for tumor tracking during treatment. We evaluated respiratory-induced liver deformation by measuring the rigidity of the fiducial configuration during the breathing cycle. Seventeen patients, with 18 distinct treatment courses, were treated with stereotactic body radiosurgery using multiple fiducials. Liver deformation was empirically quantified by measuring the intrafiducial distances at different phases of respiration. Data points were collected at the 0%, 50%, and 100% inspiration points, and the distance between each pair of fiducials was measured at the 3 phases. The rigid body error was calculated as the maximum difference in the intrafiducial distances. Liver disease was calculated with Child-Pugh score using laboratory values within 3 months of initiation of treatment. A peripheral fiducial was defined as within 1.5 cm of the liver edge, and all other fiducials were classified as central. For 5 patients with only peripheral fiducials, the fiducial configuration had more deformation (average maximum rigid body error 7.11 mm, range: 1.89-11.35 mm) when compared to patients with both central and peripheral and central fiducials only (average maximum rigid body error 3.36 mm, range: 0.5-9.09 mm, P = .037). The largest rigid body errors (11.3 and 10.6 mm) were in 2 patients with Child-Pugh class A liver disease and multiple peripheral fiducials. The liver experiences internal deformation, and the fiducial configuration should not be assumed to act as a static structure. We observed greater deformation at the periphery than at the center of the liver. In our small data set, we were not able to identify cirrhosis, which is associated with greater rigidity of the liver, as predictive for deformation. Treatment planning based only on fiducial localization must take potential intraorgan deformation into

This study compares conventional and robotic intensity modulated radiation therapy (IMRT) plans for prostate boost treatments and provides clinical insight into the strengths and weaknesses of each. The potential for dose escalation with robotic IMRT is further investigated using the "critical volume tolerance" method proposed by Roach et al. Three clinically acceptable treatment plans were generated for 10 prostate boost patients: (1) a robotic IMRT plan using fixed cones, (2) a robotic IMRT plan using the Iris variable aperture collimator, and (3) a conventional linac based IMRT (c-IMRT) plan. Target coverage, critical structure doses, homogeneity, conformity, dose fall-off, and treatment time, were compared across plans. The average bladder and rectum V75 was 17.1%, 20.0%, and 21.4%, and 8.5%, 11.9%, and 14.1% for the Iris, fixed, and c-IMRT plans, respectively. On average the conformity index (nCI) was 1.20, 1.30, and 1.46 for the Iris, fixed, and c-IMRT plans. Differences between the Iris and the c-IMRT plans were statistically significant for the bladder V75 (P= .016), rectum V75 (P= .0013), and average nCI (P =.002). Dose to normal tissue in terms of R50 was 4.30, 5.87, and 8.37 for the Iris, fixed and c-IMRT plans, respectively, with statistically significant differences between the Iris and c-IMRT (P = .0013) and the fixed and c-IMRT (P = .001) plans. In general, the robotic IMRT plans generated using the Iris were significantly better compared to c-IMRT plans, and showed average dose gains of up to 34% for a critical rectal volume of 5%.

The purpose of this study was to evaluate the performance of a commercially available CyberKnife system with a multileaf collimator (CK-MLC) for stereotactic body radiotherapy (SBRT) and standard fractionated intensity-modulated radiotherapy (IMRT) applications. Ten prostate and ten intracranial cases were planned for the CK-MLC. Half of these cases were compared with clinically approved SBRT plans generated for the CyberKnife with circular collimators, and the other half were compared with clinically approved standard fractionated IMRT plans generated for conventional linacs. The plans were compared on target coverage, conformity, homogeneity, dose to organs at risk (OAR), low dose to the surrounding tissue, total monitor units (MU), and treatment time. CK-MLC plans generated for the SBRT cases achieved more homogeneous dose to the target than the CK plans with the circular collimators, for equivalent coverage, conformity, and dose to OARs. Total monitor units were reduced by 40% to 70% and treatment time was reduced by half. The CK-MLC plans generated for the standard fractionated cases achieved prescription isodose lines between 86% and 93%, which was 2%-3% below the plans generated for conventional linacs. Compared to standard IMRT plans, the total MU were up to three times greater for the prostate (whole pelvis) plans and up to 1.4 times greater for the intracranial plans. Average treatment time was 25 min for the whole pelvis plans and 19 min for the intracranial cases. The CK-MLC system provides significant improvements in treatment time and target homogeneity compared to the CK system with circular collimators, while maintaining high conformity and dose sparing to critical organs. Standard fractionated plans for large target volumes (>100 cm3) were generated that achieved high prescription isodose levels. The CK-MLC system provides more efficient SRS and SBRT treatments and, in select clinical cases, might be a potential alternative for standard fractiona

The purpose of this study was to evaluate the performance of a commercially available CyberKnife system with a multileaf collimator (CK-MLC) for stereotactic body radiotherapy (SBRT) and standard fractionated intensity-modulated radiotherapy (IMRT) applications. Ten prostate and ten intracranial cases were planned for the CK-MLC. Half of these cases were compared with clinically approved SBRT plans generated for the CyberKnife with circular collimators, and the other half were compared with clinically approved standard fractionated IMRT plans generated for conventional linacs. The plans were compared on target coverage, conformity, homogeneity, dose to organs at risk (OAR), low dose to the surrounding tissue, total monitor units (MU), and treatment time. CK-MLC plans generated for the SBRT cases achieved more homogeneous dose to the target than the CK plans with the circular collimators, for equivalent coverage, conformity, and dose to OARs. Total monitor units were reduced by 40% to 70% and treatment time was reduced by half. The CK-MLC plans generated for the standard fractionated cases achieved prescription isodose lines between 86% and 93%, which was 2%-3% below the plans generated for conventional linacs. Compared to standard IMRT plans, the total MU were up to three times greater for the prostate (whole pelvis) plans and up to 1.4 times greater for the intracranial plans. Average treatment time was 25 min for the whole pelvis plans and 19 min for the intracranial cases. The CK-MLC system provides significant improvements in treatment time and target homogeneity compared to the CK system with circular collimators, while maintaining high conformity and dose sparing to critical organs. Standard fractionated plans for large target volumes (>100 cm3) were generated that achieved high prescription isodose levels. The CK-MLC system provides more efficient SRS and SBRT treatments and, in select clinical cases, might be a potential alternative for standard frac

Purpose/objectiveDose calculation in treatment planning must account for tissue heterogeneity, especially for tumors within low-density lung tissues. While Monte Carlo (MC) calculation methods are the most accurate, Ray Tracing (RT) methods are also commonly employed. We evaluated dose calculation differences between the RT and MC algorithms in central and peripheral lung tumors treated with CyberKnife SBRT to determine which planning parameters may predict dose differences. We also examined clinical outcomes of local-regional control (LRC) and long-term treatment-related toxicity as a function of calculation method.Materials/methodsA retrospective series of 70 patient plans (19 central and 51 peripheral lung lesions) treated between 2009 and 2011 were analyzed. Among those, 33 were primary lung cancer and 37 were metastatic lesions. Thirty-three treatment plans were developed with the RT method, and 37 plans used MC. Groups were recalculated with the reciprocal method for dose comparison. Parameters examined to quantify dose differences between the two algorithms included: dose delivered to 95% (D95) of the planning target volume (PTV), dose heterogeneity, and dose to organs at risk (OAR). Dose differences were analyzed as a function of target volume, distance to soft tissue, and fraction of target overlap with soft tissue. For the subset of primary lung tumors, LRC was assessed radiographically at a median follow-up of 19 months (mo) (range, 2 to 41 mo).ResultsCompared to MC, the RT algorithm largely overestimated the dose delivered to the PTV. The dose difference between RT and MC plans correlated to the volume of PTV overlapping with soft tissue; the smaller the overlap volume, the larger the dose differences between RT and MC. Compared to MC, the RT algorithm overestimated the dose delivered to 10% of the ipsilateral lung (D10%). Evidence of local progression was noted in only one of the 31 patients treated for primary lung malignancy. DFS and OS were not signi