Knowledge-based adaptive planning quality assurance using dosimetric indicators for stereotactic adaptive radiotherapy for pancreatic cancer.

INTRODUCTION: We aimed to develop knowledge-based tools for robust adaptive radiotherapy (ART) planning to determine on-table adaptive DVH metric variations or planning process errors for stereotactic pancreatic ART. We developed volume-based dosimetric identifiers to identify deviations of ART plans from simulation plans. MATERIALS AND METHODS: Two patient cohorts who were treated on MR-Linac for pancreas cancer were included in this retrospective study; a training cohort and a validation cohort. All patients received 50 Gy in 5 fractions. PTV-OPT was generated by subtracting the critical organs plus a 5 mm-margin from PTV. Several metrics that potentially can identify failure-modes were calculated including PTV & PTV_OPT V95% and PTV & PTV_OPT D95%/D5%. The difference between each DVH metric in each adaptive plan with the DVH metric in simulation plan was calculated. The 95% confidence interval (CI) of the variations in each DVH metric was calculated for the patient training cohort. Variations in DVH metrics that exceeded the 95% CI for all fractions in training and validation cohort were flagged for retrospective investigation for root-cause analysis to determine their predictive power for identifying failure-modes. RESULTS: The CIs for the PTV & PTV_OPT V95% and PTV & PTV_OPT D95%/D5% were ± 13%, ± 5%, ± 0.1, ± 0.03, respectively. We estimated the positive predictive value and negative predictive value of our method to be 77% and 89%, respectively, for the training cohort, and 80% for both in the validation cohort. DISCUSSION: We developed dosimetric indicators for ART planning QA to identify population-based deviations or planning errors during online adaptive process for stereotactic pancreatic ART. This technology may be useful as an ART clinical trial QA tool and improve overall ART quality at an institution.

A clinical and time savings evaluation of a deep learning automatic contouring algorithm.

Automatic contouring algorithms may streamline clinical workflows by reducing normal organ-at-risk (OAR) contouring time. Here we report the first comprehensive quantitative and qualitative evaluation, along with time savings assessment for a prototype deep learning segmentation algorithm from Siemens Healthineers. The accuracy of contours generated by the prototype were evaluated quantitatively using the Sorensen-Dice coefficient (Dice), Jaccard index (JC), and Hausdorff distance (Haus). Normal pelvic and head and neck OAR contours were evaluated retrospectively comparing the automatic and manual clinical contours in 100 patient cases. Contouring performance outliers were investigated. To quantify the time savings, a certified medical dosimetrist manually contoured de novo and, separately, edited the generated OARs for 10 head and neck and 10 pelvic patients. The automatic, edited, and manually generated contours were visually evaluated and scored by a practicing radiation oncologist on a scale of 1-4, where a higher score indicated better performance. The quantitative comparison revealed high (> 0.8) Dice and JC performance for relatively large organs such as the lungs, brain, femurs, and kidneys. Smaller elongated structures that had relatively low Dice and JC values tended to have low Hausdorff distances. Poor performing outlier cases revealed common anatomical inconsistencies including overestimation of the bladder and incorrect superior-inferior truncation of the spinal cord and femur contours. In all cases, editing contours was faster than manual contouring with an average time saving of 43.4% or 11.8 minutes per patient. The physician scored 240 structures with > 95% of structures receiving a score of 3 or 4. Of the structures reviewed, only 11 structures needed major revision or to be redone entirely. Our results indicate the evaluated auto-contouring solution has the potential to reduce clinical contouring time. The algorithm's performance is promising, but human review and some editing is required prior to clinical use.

A motion prediction confidence estimation framework for prediction-based radiotherapy gating.

PURPOSE: Motion prediction can compensate for latency in image-guided radiotherapy and has been an active area of research. However, motion predictions are subject to error and variations. We have developed and evaluated a novel motion prediction confidence estimation framework to improve the efficacy and robustness of prediction-based radiotherapy gating decision-making. The specific scenario of adaptive gating in magnetic resonance imaging (MRI)-guided radiotherapy is studied as an example, but the method generalizes to other modalities and motion management setups. METHODS: The proposed prediction confidence estimator is based on a generic training/testing paradigm and consists of a weighted combination of three components: the prediction model's goodness of fit, variation in the prediction using a leave-one-out process and the velocity of the tracked target. Roughly, these terms quantify respectively the consistency between prediction and the training data, the robustness of model inference, and the stability due to target speed. The weight parameters and the action level in triggering beam-off decision are optimized. The method is assessed and validated in 8 healthy volunteer and 13 patient studies using a 0.35T MRI-guided radiotherapy system predicting 0.25-0.33 s ahead. The effect of the action level on the predicted gating decision accuracy, beam-on positive predictive value (PPV) and median distance between the predicted and ground-truth target centroids were evaluated. Statistical significance was evaluated using a paired t-test. The tradeoff between these performance metrics and gating duty cycle was assessed. RESULTS: Use of the confidence estimator threshold increased gating accuracy by up to 2.42%, increased PPV by up to 3.00%, and reduced the median centroid distance up to 0.28 mm. The confidence estimator threshold on average increased gating accuracy to 96.5% (P = 2.08 × 10-4 ), increased PPV to 96.7% (P = 1.46 × 10-5 ), reduced the median centroid distance to 0.54 mm (P = 1.71 × 10-5 ) at the cost of reducing the gating duty cycle by 14.3% to 48.5%. Hyperparameter tuning revealed that contrary to intuition, the velocity term offered only minimal performance improvement in some cases but also introduced potential stability issues. The combination of goodness of fit and leave-one-out prediction variation provided the most effective confidence estimator, yielding universally better performance in gating decisions. CONCLUSION: Confidence estimation utilizing prediction model fitness criterion and validation principles can complement prediction methods to guide MRI-guided radiotherapy gating. Results from both volunteer and patient studies showed improved gating quality.

An image regression motion prediction technique for MRI-guided radiotherapy evaluated in single-plane cine imaging.

PURPOSE: To develop and evaluate a novel motion prediction method for magnetic resonance image (MRI)-guided radiotherapy applications. This method, which we deem "image regression," predicts future tissue motion based on a weighted combination of previously observed motion states. Motion predictions are derived from a sliding window of recent motion states which are defined by a temporal sequence of images. A key advantage of this method compared to other motion prediction methods is that its computational complexity scales weekly with the number of spatial points predicted. Applications of gating latency reduction and improvement in deformable registration-based target tracking are demonstrated. METHODS: The image regression (IR) motion prediction method was developed and evaluated using 26.9 h of real-time imaging acquired from eight healthy volunteers and 13 patients using a 0.35 T MRI-guided radiotherapy system. Motion predictions were performed 0.25-0.33 s into the future using a weighted sum of previously observed motion states with image similarity-derived weights. The set of previously observed motion states were continuously updated to incorporate the changes in breathing patterns. The accuracy of the predicted radiotherapy gating decision, beam-on positive predictive value (PPV), and predicted vs ground-truth target centroid position errors are reported. The IR technique was compared against no prediction, linear extrapolation, and an established autoregressive linear prediction algorithm. The usage of IR to initialize the deformable registration and enhance the target tracking was demonstrated in the healthy volunteer studies. Deformable registration with IR initialization was compared to the initialization performed by current clinical software: no initialization, previous image registration initialization and linear motion extrapolation initialization. RESULTS: The average IR-predicted radiation beam gating decision accuracy was 95.8%, with a PPV of 95.7%, and median and 95th percentile centroid position errors of 0.63 and 2.08 mm, respectively. Compared to the autoregressive linear prediction method, gating accuracy was 1.15% greater, PPV was 1.61% greater, and median and 95th percentile centroid distances were 0.21 and 0.23 mm smaller. The IR-initialized registration on average converged within 0.50 mm of the ground-truth position in fewer than 10 iterations whereas the next best initialization method required more than 25 iterations. CONCLUSIONS: Image regression motion prediction has the potential to reduce the gating latencies and improve the speed and accuracy of deformable registration-based target tracking in MRI-guided radiotherapy.

Multislice motion modeling for MRI-guided radiotherapy gating.

PURPOSE: On-board magnetic resonance imaging (MRI) greatly enhances real-time target tracking capability during radiotherapy treatments. However, multislice and volumetric MRI techniques are frame rate limited and introduce unacceptable latency between the target moving out of position and the beam being turned off. We present a technique to estimate continuous volumetric tissue motion using motion models built from a repeated acquisition of a stack of MR slices. Applications including multislice target visualization and out-of-slice motion estimation during MRI-guided radiotherapy are demonstrated. METHODS: Eight healthy volunteer studies were performed using a 0.35 T MRI-guided radiotherapy system. Images were acquired at three frames per second in an interleaved fashion across ten adjacent sagittal slice positions covering 4.5 cm using a balanced steady-state-free precession sequence. A previously published five-dimensional (5D) linear motion model used for MRI-guided radiotherapy gating was extended to include multiple slices. This model utilizes an external respiratory bellows signal recorded during imaging to simultaneously estimate motion across all imaged slices. For comparison to an image-based approach, the manifold learning technique local linear embedding (LLE) was used to derive a respiratory surrogate for motion modeling. Manifolds for every slice were aligned during LLE in a group-wise fashion, enabling motion estimation outside the current imaged slice using a motion model, a process which we denote as mSGA. Additionally, a method is developed to evaluate out-of-slice motion estimates. The multislice motion model was evaluated in a single slice with each newly acquired image using a leave-one-out approach. Model-generated gating decision accuracy and beam-on positive predictive value (PPV) are reported along with the median and 95th percentile distance between model and ground truth target centroids. RESULTS: The average model gating decision accuracy and PPV across all volunteer studies was 93.7% and 92.8% using the 5D model, and 96.8% and 96.1% using the mSGA model, respectively. The median and 95th percentile distance between model and ground truth target centroids was 0.91 and 2.90 mm, respectively, using the 5D model and 0.58 and 1.49 mm using the mSGA model, averaged over all eight subjects. The mSGA motion model provided a statistically significant improvement across all evaluation metrics compared to the external surrogate-based 5D model. CONCLUSION: The proposed techniques for out-of-slice target motion estimation demonstrated accuracy likely sufficient for clinical use. Results indicate the mSGA model may provide higher accuracy, however, the external surrogate-based model allows for unbiased in vivo accuracy evaluation.

Model-Interpolated Gating for Magnetic Resonance Image-Guided Radiation Therapy.

PURPOSE: To develop and validate a technique for radiation therapy gating using slow (≤1 frame per second) magnetic resonance imaging (MRI) and a motion model. Proposed uses of the technique include radiation therapy gating using T2-weighted images and conducting additional imaging studies during gated treatments. METHODS AND MATERIALS: The technique uses a physiologically guided breathing motion model to interpolate deformed target position between 2-dimensional (2D) MRI images acquired every 1 to 3 seconds. The model is parameterized by a 1-dimensional respiratory bellows surrogate and is continuously updated with the most recently acquired 2D images. A phantom and 8 volunteers were imaged with a 0.35T MRI-guided radiation therapy system. A balanced steady-state free precession sequence with a 2D frame rate of 3 frames per second was used to evaluate the technique. The accuracy and beam-on positive predictive value (PPV) of the model-based gating decisions were evaluated using the gating decisions derived from imaging as a ground truth. A T2-weighted gating offline proof-of-concept study using a half-Fourier, single-shot, turbo-spin echo sequence is reported. RESULTS: Model-interpolated gating accuracy, beam-on PPV, and median absolute distances between model and image-tracked target centroids were, on average, 98.3%, 98.4%, and 0.33 mm, respectively, in the balanced steady-state free precession phantom studies and 93.7%, 92.1%, and 0.86 mm, respectively, in the volunteer studies. T2 model-interpolated gating in 6 volunteers yielded an average accuracy and PPV of 94.3% and 92.5%, respectively, and the mean absolute median distance between modeled and imaged target centroids was 0.86 mm. CONCLUSIONS: This work demonstrates the concept of model-interpolated gating for MRI-guided radiation therapy. The technique was found to be potentially sufficiently accurate for clinical use. Further development is needed to accommodate out-of-plane motion and the use of an internal MR-based respiratory surrogate.

Dosimetric validation of a magnetic resonance image gated radiotherapy system using a motion phantom and radiochromic film.

PURPOSE: Magnetic resonance image (MRI) guided radiotherapy enables gating directly on the target position. We present an evaluation of an MRI-guided radiotherapy system's gating performance using an MRI-compatible respiratory motion phantom and radiochromic film. Our evaluation is geared toward validation of our institution's clinical gating protocol which involves planning to a target volume formed by expanding 5 mm about the gross tumor volume (GTV) and gating based on a 3 mm window about the GTV. METHODS: The motion phantom consisted of a target rod containing high-contrast target inserts which moved in the superior-inferior direction inside a body structure containing background contrast material. The target rod was equipped with a radiochromic film insert. Treatment plans were generated for a 3 cm diameter spherical planning target volume, and delivered to the phantom at rest and in motion with and without gating. Both sinusoidal trajectories and tumor trajectories measured during MRI-guided treatments were used. Similarity of the gated dose distribution to the planned, motion-frozen, distribution was quantified using the gamma technique. RESULTS: Without gating, gamma pass rates using 4%/3 mm criteria were 22-59% depending on motion trajectory. Using our clinical standard of repeated breath holds and a gating window of 3 mm with 10% target allowed outside the gating boundary, the gamma pass rate was 97.8% with 3%/3 mm gamma criteria. Using a 3 mm window and 10% allowed excursion, all of the patient tumor motion trajectories at actual speed resulting in at least 95% gamma pass rate at 4%/3 mm. CONCLUSIONS: Our results suggest that the device can be used to compensate respiratory motion using a 3 mm gating margin and 10% allowed excursion results in conjunction with repeated breath holds. Full clinical validation requires a comprehensive evaluation of tracking performance in actual patient images, outside the scope of this study.

Characterization of spatial distortion in a 0.35 T MRI-guided radiotherapy system.

Spatial distortion results in image deformation that can degrade accurate targeting and dose calculations in MRI-guided adaptive radiotherapy. The authors present a comprehensive assessment of a 0.35 T MRI-guided radiotherapy system's spatial distortion using two commercially-available phantoms with regularly spaced markers. Images of the spatial integrity phantoms were acquired using five clinical protocols on the MRI-guided radiotherapy machine with the radiotherapy gantry positioned at various angles. Software was developed to identify and localize all phantom markers using a template matching approach. Rotational and translational corrections were implemented to account for imperfect phantom alignment. Measurements were made to assess uncertainties arising from susceptibility artifacts, image noise, and phantom construction accuracy. For a clinical 3D imaging protocol with a 1.5 mm reconstructed slice thickness, 100% of spheres within a 50 mm radius of isocenter had a 3D deviation of 1 mm or less. Of the spheres within 100 mm of isocenter, 99.9% had a 3D deviation less than 1 mm. 94.8% and 100% of the spheres within 175 mm were found to be within 1 mm and 2 mm of the expected positions in 3D respectively. Maximum 3D distortions within 50 mm, 100 mm and 175 mm of isocenter were 0.76 mm, 1.15 mm and 1.88 mm respectively. Distortions present in images acquired using the real-time imaging sequence were less than 1 mm for 98.1% and 95.0% of the cylinders within 50 mm and 100 mm of isocenter. The corresponding maximum distortion in these regions was 1.10 mm and 1.67 mm. These results may be used to inform appropriate planning target volume (PTV) margins for 0.35 T MRI-guided radiotherapy. Observed levels of spatial distortion should be explicitly considered when using PTV margins of 3 mm or less or in the case of targets displaced from isocenter by more than 50 mm.