Abstract Objective . Deep-learning (DL)-based dose engines have been developed to alleviate the intrinsic compromise between the calculation accuracy and efficiency of the traditional dose calculation algorithms. However, current DL-based engines typically possess high computational complexity and require powerful computing devices. Therefore, to mitigate their computational burdens and broaden their applicability to a clinical setting where resource-limited devices are available, we proposed a compact dose engine via knowledge distillation (KD) framework that offers an ultra-fast calculation speed with high accuracy for prostate Volumetric Modulated Arc Therapy (VMAT). Approach . The KD framework contains two sub-models: a large pre-trained teacher and a small to-be-trained student. The student receives knowledge transferred from the teacher for better generalization. The trained student serves as the final engine for dose calculation. The model input is patient computed tomography and VMAT dose in water, and the output is DL-calculated patient dose. The ground-truth \dose was computed by the Monte Carlo module of the Monaco treatment planning system. Twenty and ten prostate cases were included for model training and assessment, respectively. The model’s performance (teacher/student/student-only) was evaluated by Gamma analysis and inference efficiency. Main results . The dosimetric comparisons (input/DL-calculated/ground-truth doses) suggest that the proposed engine can effectively convert low-accuracy doses in water to high-accuracy patient doses. The Gamma passing rate (2%/2 mm, 10% threshold) between the DL-calculated and ground-truth doses was 98.64 ± 0.62% (teacher), 98.13 ± 0.76% (student), and 96.95 ± 1.02% (student-only). The inference time was 16 milliseconds (teacher) and 11 milliseconds (student/student-only) using a graphics processing unit device, while it was 936 milliseconds (teacher) and 374 milliseconds (student/student-only) using a central processing unit device. Significance . With the KD framework, a compact dose engine can achieve comparable accuracy to that of a larger one. Its compact size reduces the computational burdens and computing device requirements, and thus such an engine can be more clinically applicable.
more »
« less
A polar‐coordinate‐based pencil beam algorithm for VMAT dose computation with high‐resolution gantry angle sampling
Most commercially available treatment planning systems (TPSs) approximate the continuous delivery of volumetric modulated arc therapy (VMAT) plans with a series of discretized static beams for treatment planning, which can make VMAT dose computation extremely inefficient. In this study, we developed a polar‐coordinate‐based pencil beam (PB) algorithm for efficient VMAT dose computation with high‐resolution gantry angle sampling that can improve the computational efficiency and reduce the dose discrepancy due to the angular under‐sampling effect.
6 MV pencil beams were simulated on a uniform cylindrical phantom under an EGSnrc Monte Carlo (MC) environment. The MC‐generated PB kernels were collected in the polar coordinate system for each bixel on a fluence map and subsequently fitted via a series of Gaussians. The fluence was calculated using a detectors’ eye view with off‐axis and MLC transmission factors corrected. Doses of VMAT arc on the phantom were computed by summing the convolution results between the corresponding PB kernels and fluence for each bixel in the polar coordinate system. The convolution was performed using fast Fourier transform to expedite the computing speed. The calculated doses were converted to the Cartesian coordinate system and compared with the reference dose computed by a collapsed cone convolution (CCC) algorithm of the TPS. A heterogeneous phantom was created to study the heterogeneity corrections using the proposed algorithm. Ten VMAT arcs were included to evaluate the algorithm performance. Gamma analysis and computation complexity theory were used to measure the dosimetric accuracy and computational efficiency, respectively.
The dosimetric comparisons on the homogeneous phantom between the proposed PB algorithm and the CCC algorithm for 10 VMAT arcs demonstrate that the proposed algorithm can achieve a dosimetric accuracy comparable to that of the CCC algorithm with average gamma passing rates of 96% (2%/2mm) and 98% (3%/3mm). In addition, the proposed algorithm can provide better computational efficiency for VMAT dose computation using a PC equipped with a 4‐core processor, compared to the CCC algorithm utilizing a dual 10‐core server. Moreover, the computation complexity theory reveals that the proposed algorithm has a great advantage with regard to computational efficiency for VMAT dose computation on homogeneous medium, especially when a fine angular sampling rate is applied. This can support a reduction in dose errors from the angular under‐sampling effect by using a finer angular sampling rate, while still preserving a practical computing speed. For dose calculation on the heterogeneous phantom, the proposed algorithm with heterogeneity corrections can still offer a reasonable dosimetric accuracy with comparable computational efficiency to that of the CCC algorithm.
We proposed a novel polar‐coordinate‐based pencil beam algorithm for VMAT dose computation that enables a better computational efficiency while maintaining clinically acceptable dosimetric accuracy and reducing dose error caused by the angular under‐sampling effect. It also provides a flexible VMAT dose computation structure that allows adjustable sampling rates and direct dose computation in regions of interest, which makes the algorithm potentially useful for clinical applications such as independent dose verification for VMAT patient‐specific QA.
- Award ID(s):
- 2016571
- NSF-PAR ID:
- 10446540
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Medical Physics
- Volume:
- 49
- Issue:
- 6
- ISSN:
- 0094-2405
- Page Range / eLocation ID:
- p. 4026-4042
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Purpose As a challenging but important optimization problem, the inverse planning for volumetric modulated arc therapy (VMAT) has attracted much research attention. The column generation (CG) type method is so far one of the most effective solution schemes. However, it often relies on simplifications leading to significant gaps between the output and the actual feasible plan. This paper presents a novel column generation (NCG) approach to push the planning results substantially closer to practice.
Methods The proposed NCG algorithm is equipped with multiple new quality‐enhancing and computation‐facilitating modules as below: (1) Flexible constraints are enabled on both dose rates and treatment time to adapt to machine capabilities as well as planner's preferences, respectively; (2) a cross‐control‐point intermediate aperture simulation is incorporated to better conform to the underlying physics; (3) new pricing and pruning subroutines are adopted to achieve better optimization outputs. To evaluate the effectiveness of this NCG, five VMAT plans, that is, three prostate cases and two head‐and‐neck cases, were computed using proposed NCG. The planning results were compared with those yielded by a historical benchmark planning scheme.
Results The NCG generated plans of significantly better quality than the benchmark planning algorithm. For prostate cases, NCG plans satisfied all planning target volume (PTV) criteria whereas CG plans failed on D10% criteria of PTVs for over 9 Gy or more on all cases. For head‐and‐neck cases, again, NCG plans satisfied all PTVs criteria while CG plans failed on D10% criteria of PTVs for over 3 Gy or more on all cases as well as the max dose criteria of both cord and brain stem for over 13 Gy on one case. Moreover, the pruning scheme was found to be effective in enhancing the optimization quality.
Conclusions The proposed NCG inherits the computational advantages of the traditional CG, while capturing a more realistic characterization of the machine capability and underlying physics. The output solutions of the NCG are substantially closer to practical implementation.
-
more » « less
Abstract Background In order to accurately accumulate delivered dose for head and neck cancer patients treated with the Adapt to Position workflow on the 1.5T magnetic resonance imaging (MRI)‐linear accelerator (MR‐linac), the low‐resolution T2‐weighted MRIs used for daily setup must be segmented to enable reconstruction of the delivered dose at each fraction.
Purpose In this pilot study, we evaluate various autosegmentation methods for head and neck organs at risk (OARs) on on‐board setup MRIs from the MR‐linac for off‐line reconstruction of delivered dose.
Methods Seven OARs (parotid glands, submandibular glands, mandible, spinal cord, and brainstem) were contoured on 43 images by seven observers each. Ground truth contours were generated using a simultaneous truth and performance level estimation (STAPLE) algorithm. Twenty total autosegmentation methods were evaluated in ADMIRE: 1–9) atlas‐based autosegmentation using a population atlas library (PAL) of 5/10/15 patients with STAPLE, patch fusion (PF), random forest (RF) for label fusion; 10–19) autosegmentation using images from a patient's 1–4 prior fractions (individualized patient prior [IPP]) using STAPLE/PF/RF; 20) deep learning (DL) (3D ResUNet trained on 43 ground truth structure sets plus 45 contoured by one observer). Execution time was measured for each method. Autosegmented structures were compared to ground truth structures using the Dice similarity coefficient, mean surface distance (MSD), Hausdorff distance (HD), and Jaccard index (JI). For each metric and OAR, performance was compared to the inter‐observer variability using Dunn's test with control. Methods were compared pairwise using the Steel‐Dwass test for each metric pooled across all OARs. Further dosimetric analysis was performed on three high‐performing autosegmentation methods (DL, IPP with RF and 4 fractions [IPP_RF_4], IPP with 1 fraction [IPP_1]), and one low‐performing (PAL with STAPLE and 5 atlases [PAL_ST_5]). For five patients, delivered doses from clinical plans were recalculated on setup images with ground truth and autosegmented structure sets. Differences in maximum and mean dose to each structure between the ground truth and autosegmented structures were calculated and correlated with geometric metrics.
Results DL and IPP methods performed best overall, all significantly outperforming inter‐observer variability and with no significant difference between methods in pairwise comparison. PAL methods performed worst overall; most were not significantly different from the inter‐observer variability or from each other. DL was the fastest method (33 s per case) and PAL methods the slowest (3.7–13.8 min per case). Execution time increased with a number of prior fractions/atlases for IPP and PAL. For DL, IPP_1, and IPP_RF_4, the majority (95%) of dose differences were within ± 250 cGy from ground truth, but outlier differences up to 785 cGy occurred. Dose differences were much higher for PAL_ST_5, with outlier differences up to 1920 cGy. Dose differences showed weak but significant correlations with all geometric metrics (
R 2 between 0.030 and 0.314).Conclusions The autosegmentation methods offering the best combination of performance and execution time are DL and IPP_1. Dose reconstruction on on‐board T2‐weighted MRIs is feasible with autosegmented structures with minimal dosimetric variation from ground truth, but contours should be visually inspected prior to dose reconstruction in an end‐to‐end dose accumulation workflow.
-
more » « less
Abstract Purpose To determine the optimal dose‐volume constraint for laryngeal sparing using three commonly employed intensity modulated radiation therapy (IMRT) approaches in patients with oropharyngeal cancer treated to the bilateral neck.
Materials and methods Thirty patients with stage II‐IVA oropharynx cancers received definitive radiotherapy with split‐field IMRT (SF‐IMRT) to the bilateral neck between 2008 and 2013. Each case was re‐planned using whole‐field IMRT (WF‐IMRT) and volumetric modulated arc therapy (VMAT) and plan quality metrics and dose to laryngeal structures was evaluated. Two larynx volumes were defined and compared on the current study: the Radiation Therapy Oncology Group (RTOG) larynx as defined per the RTOG 1016 protocol and the MDACC larynx defined as the components of the larynx bounded by the superior and inferior extent of the thyroid cartilage.
Results Target coverage, conformity, and heterogeneity indices were similar in all techniques. The RTOG larynx mean dose was lower with WF‐IMRT than SF‐IMRT (22.1 vs 25.8 Gy;
P < 0.01). The MDACC larynx mean dose was 17.5 Gy ± 5.4 Gy with no differences between the 3 techniques. WF‐IMRT and VMAT plans were associated with lower mean doses to the supraglottic larynx (42.1 vs 41.2 vs 54.8 Gy;P < 0.01) and esophagus (18.1 vs 18.2 vs 36 Gy;P < 0.01).Conclusions Modern whole field techniques can provide effective laryngeal sparing in patients receiving radiotherapy to the bilateral neck for advanced oropharyngeal cancers.
Summary We evaluated laryngeal dose in patients with locally advanced oropharyngeal cancer treated to the bilateral neck using split‐field IMRT (SF‐IMRT), whole‐field IMRT (WF‐IMRT) and volumetric arc therapy (VMAT). All three techniques provided good sparing of laryngeal structures and were able to achieve a mean larynx dose < 33 Gy. There were no significant differences in dose to target structures or non‐laryngeal organs at risk among techniques.
-
more » « less
Abstract Purpose The radiobiological benefits afforded by spatially fractionated (GRID) radiation therapy pairs well with the dosimetric advantages of proton therapy. Inspired by the emergence of energy‐layer specific collimators in pencil beam scanning (PBS), this work investigates how the spot spacing and collimation can be optimized to maximize the therapeutic gains of a GRID treatment while demonstrating the integration of a dynamic collimation system (DCS) within a commercial beamline to deliver GRID treatments and experimentally benchmark Monte Carlo calculation methods.
Methods GRID profiles were experimentally benchmarked using a clinical DCS prototype that was mounted to the nozzle of the IBA‐dedicated nozzle system. Integral depth dose (IDD) curves and lateral profiles were measured for uncollimated and GRID‐collimated beamlets. A library of collimated GRID dose distributions were simulated by placing beamlets within a specified uniform grid and weighting the beamlets to achieve a volume‐averaged tumor cell survival equivalent to an open field delivery. The healthy tissue sparing afforded by the GRID distribution was then estimated across a range of spot spacings and collimation widths, which were later optimized based on the radiosensitivity of the tumor cell line and the nominal spot size of the PBS system. This was accomplished by using validated models of the IBA universal and dedicated nozzles.
Results Excellent agreement was observed between the measured and simulated profiles. The IDDs matched above 98.7% when analyzed using a 1%/1‐mm gamma criterion with some minor deviation observed near the Bragg peak for higher beamlet energies. Lateral profile distributions predicted using Monte Carlo methods agreed well with the measured profiles; a gamma passing rate of 95% or higher was observed for all in‐depth profiles examined using a 3%/2‐mm criteria. Additional collimation was shown to improve PBS GRID treatments by sharpening the lateral penumbra of the beamlets but creates a trade‐off between enhancing the valley‐to‐peak ratio of the GRID delivery and the dose‐volume effect. The optimal collimation width and spot spacing changed as a function of the tumor cell radiosensitivity, dose, and spot size. In general, a spot spacing below 2.0 cm with a collimation less than 1.0 cm provided a superior dose distribution among the specific cases studied.
Conclusions The ability to customize a GRID dose distribution using different collimation sizes and spot spacings is a useful advantage, especially to maximize the overall therapeutic benefit. In this regard, the capabilities of the DCS, and perhaps alternative dynamic collimators, can be used to enhance GRID treatments. Physical dose models calculated using Monte Carlo methods were experimentally benchmarked in water and were found to accurately predict the respective dose distributions of uncollimated and DCS‐collimated GRID profiles.
