•Deep learning can be used to contour organs at risk for numerous patients.•Deep learning outperforms atlas based auto-segmentation in head and neck organs at risk contouring.•Subjective analysis ...indicated no need manual corrections in many deep learning generated contours.•Deep learning auto-contouring has the potential to decrease the clinical burden.
Adequate head and neck (HN) organ-at-risk (OAR) delineation is crucial for HN radiotherapy and for investigating the relationships between radiation dose to OARs and radiation-induced side effects. The automatic contouring algorithms that are currently in clinical use, such as atlas-based contouring (ABAS), leave room for improvement. The aim of this study was to use a comprehensive evaluation methodology to investigate the performance of HN OAR auto-contouring when using deep learning contouring (DLC), compared to ABAS.
The DLC neural network was trained on 589 HN cancer patients. DLC was compared to ABAS by providing each method with an independent validation cohort of 104 patients, which had also been manually contoured. For each of the 22 OAR contours – glandular, upper digestive tract and central nervous system (CNS)-related structures – the dice similarity coefficient (DICE), and absolute mean and max dose differences (|Δmean-dose| and |Δmax-dose|) performance measures were obtained. For a subset of 7 OARs, an evaluation of contouring time, inter-observer variation and subjective judgement was performed.
DLC resulted in equal or significantly improved quantitative performance measures in 19 out of 22 OARs, compared to the ABAS (DICE/|Δmean dose|/|Δmax dose|: 0.59/4.2/4.1 Gy (ABAS); 0.74/1.1/0.8 Gy (DLC)). The improvements were mainly for the glandular and upper digestive tract OARs. DLC significantly reduced the delineation time for the inexperienced observer. The subjective evaluation showed that DLC contours were more often preferable to the ABAS contours overall, were considered to be more precise, and more often confused with manual contours. Manual contours still outperformed both DLC and ABAS; however, DLC results were within or bordering the inter-observer variability for the manual edited contours in this cohort.
The DLC, trained on a large HN cancer patient cohort, outperformed the ABAS for the majority of HN OARs.
In-room imaging is a prerequisite for adaptive proton therapy. The use of onboard cone-beam computed tomography (CBCT) imaging, which is routinely acquired for patient position verification, can ...enable daily dose reconstructions and plan adaptation decisions. Image quality deficiencies though, hamper dose calculation accuracy and make corrections of CBCTs a necessity. This study compared three methods to correct CBCTs and create synthetic CTs that are suitable for proton dose calculations. CBCTs, planning CTs and repeated CTs (rCT) from 33 H&N cancer patients were used to compare a deep convolutional neural network (DCNN), deformable image registration (DIR) and an analytical image-based correction method (AIC) for synthetic CT (sCT) generation. Image quality of sCTs was evaluated by comparison with a same-day rCT, using mean absolute error (MAE), mean error (ME), Dice similarity coefficient (DSC), structural non-uniformity (SNU) and signal/contrast-to-noise ratios (SNR/CNR) as metrics. Dosimetric accuracy was investigated in an intracranial setting by performing gamma analysis and calculating range shifts. Neural network-based sCTs resulted in the lowest MAE and ME (37/2 HU) and the highest DSC (0.96). While DIR and AIC generated images with a MAE of 44/77 HU, a ME of −8/1 HU and a DSC of 0.94/0.90. Gamma and range shift analysis showed almost no dosimetric difference between DCNN and DIR based sCTs. The lower image quality of AIC based sCTs affected dosimetric accuracy and resulted in lower pass ratios and higher range shifts. Patient-specific differences highlighted the advantages and disadvantages of each method. For the set of patients, the DCNN created synthetic CTs with the highest image quality. Accurate proton dose calculations were achieved by both DCNN and DIR based sCTs. The AIC method resulted in lower image quality and dose calculation accuracy was reduced compared to the other methods.
Roadmap: proton therapy physics and biology Paganetti, Harald; Beltran, Chris; Both, Stefan ...
Physics in medicine & biology,
02/2021, Letnik:
66, Številka:
5
Journal Article
Recenzirano
Odprti dostop
The treatment of cancer with proton radiation therapy was first suggested in 1946 followed by the first treatments in the 1950s. As of 2020, almost 200 000 patients have been treated with proton ...beams worldwide and the number of operating proton therapy (PT) facilities will soon reach one hundred. PT has long moved from research institutions into hospital-based facilities that are increasingly being utilized with workflows similar to conventional radiation therapy. While PT has become mainstream and has established itself as a treatment option for many cancers, it is still an area of active research for various reasons: the advanced dose shaping capabilities of PT cause susceptibility to uncertainties, the high degrees of freedom in dose delivery offer room for further improvements, the limited experience and understanding of optimizing pencil beam scanning, and the biological effect difference compared to photon radiation. In addition to these challenges and opportunities currently being investigated, there is an economic aspect because PT treatments are, on average, still more expensive compared to conventional photon based treatment options. This roadmap highlights the current state and future direction in PT categorized into four different themes, 'improving efficiency', 'improving planning and delivery', 'improving imaging', and 'improving patient selection'.
Purpose
Adaptive proton therapy (APT) of lung cancer patients requires frequent volumetric imaging of diagnostic quality. Cone‐beam CT (CBCT) can provide these daily images, but x‐ray scattering ...limits CBCT‐image quality and hampers dose calculation accuracy. The purpose of this study was to generate CBCT‐based synthetic CTs using a deep convolutional neural network (DCNN) and investigate image quality and clinical suitability for proton dose calculations in lung cancer patients.
Methods
A dataset of 33 thoracic cancer patients, containing CBCTs, same‐day repeat CTs (rCT), planning‐CTs (pCTs), and clinical proton treatment plans, was used to train and evaluate a DCNN with and without a pCT‐based correction method. Mean absolute error (MAE), mean error (ME), peak signal‐to‐noise ratio, and structural similarity were used to quantify image quality. The evaluation of clinical suitability was based on recalculation of clinical proton treatment plans. Gamma pass ratios, mean dose to target volumes and organs at risk, and normal tissue complication probabilities (NTCP) were calculated. Furthermore, proton radiography simulations were performed to assess the HU‐accuracy of sCTs in terms of range errors.
Results
On average, sCTs without correction resulted in a MAE of 34 ± 6 HU and ME of 4 ± 8 HU. The correction reduced the MAE to 31 ± 4HU (ME to 2 ± 4HU). Average 3%/3 mm gamma pass ratios increased from 93.7% to 96.8%, when the correction was applied. The patient specific correction reduced mean proton range errors from 1.5 to 1.1 mm. Relative mean target dose differences between sCTs and rCT were below ± 0.5% for all patients and both synthetic CTs (with/without correction). NTCP values showed high agreement between sCTs and rCT (<2%).
Conclusion
CBCT‐based sCTs can enable accurate proton dose calculations for APT of lung cancer patients. The patient specific correction method increased the image quality and dosimetric accuracy but had only a limited influence on clinically relevant parameters.
Moderately hypofractionated radiation therapy represents an effective treatment for localized prostate cancer (PC). Although large randomized trials have reported the efficacy of photon-based ...hypofractionated therapy, hypofractionated proton therapy (HFPT) has not been extensively studied. This study was performed to determine the clinical and patient-reported outcomes for patients with PC treated with HFPT.
Between 2010 and 2017, 184 men were enrolled on a trial of 70 Gy in 28 fractions of HFPT for low- to intermediate-risk PC. Acute and late toxicity was evaluated using National Cancer Institute Common Terminology Criteria for Adverse Events version 4.0. Patient-reported outcomes were measured by International Prostate Symptom Score, International Index of Erectile Function Questionnaire, and Expanded Prostate Cancer Index Composite scores.
Median follow-up was 49.2 months. Enrolled patients had low-risk (n = 18), favorable intermediate-risk (n = 78), and unfavorable intermediate-risk (n = 88) PC. Four-year rates of biochemical-clinical failure-free survival were 93.5% (95% confidence interval, 89%-98%), 94.4% (89%-100%), 92.5% (86%-100%), and 93.8% (88%-100%) in the overall group and the low-risk, favorable intermediate-risk, and unfavorable intermediate-risk cohorts, respectively (log-rank P > .4). The incidence of acute grade 2 or higher gastrointestinal (GI) and urologic toxicities were 3.8% and 12.5%, respectively. The 4-year incidence of late grade 2 or higher urologic and GI toxicity was 7.6% (4%-13%) and 13.6% (9%-20%), respectively. One late grade 3 GI toxicity was reported. All late toxicities were transient. Patient-reported International Prostate Symptom, International Index of Erectile Function, and Expanded Prostate Cancer Index Composite scores had no significant long-term changes after completion of HFPT (Supplementary Table 1, available at https://doi.org/10.1016/j.ijrobp.2019.05.069).
HFPT is associated with low rates of toxicity and does not appear to negatively affect 4-year patient reported urinary and bowel health. Further comparative analyses are warranted to better understand differences between proton and photon HFRT.
Reirradiation to the esophagus carries a significant risk of complications. Proton therapy may offer an advantage in the reirradiation setting due to the lack of exit dose and potential sparing of ...previously radiated normal tissues.
Between June 2010 and February 2014, 14 patients with a history of thoracic radiation and newly diagnosed or locally recurrent esophageal cancer began proton beam reirradiation on a prospective trial. Primary endpoints were feasibility and acute toxicity. Toxicity was graded according Common Toxicity Criteria version 4.0.
The median follow-up was 10 months (2-25 months) from the start of reirradiation. Eleven patients received concurrent chemotherapy. The median interval between radiation courses was 32 months (10-307 months). The median reirradiation prescription dose was 54.0 Gy (relative biological effectiveness RBE) (50.4-61.2 GyRBE), and the median cumulative prescription dose was 109.8 Gy (76-129.4 Gy). Of the 10 patients who presented with symptomatic disease, 4 patients had complete resolution of symptoms, and 4 had diminished or stable symptoms. Two patients had progressive symptoms. The median time to symptom recurrence was 10 months. Maximum acute nonhematologic toxicity attributable to radiation was grade 2 (64%, N=9), 3 (29%, N=4), 4 (0%), and 5 (7%, N=1). The acute grade 5 toxicity was an esophagopleural fistula more likely related to tumor progression than radiation. Grade 3 nonhematologic acute toxicities included dysphagia, dehydration, and pneumonia. There was 1 late grade 5 esophageal ulcer more likely related to tumor progression than radiation. There were 4 late grade 3 toxicities: heart failure, esophageal stenosis requiring dilation, esophageal ulceration from tumor, and percutaneous endoscopic gastrostomy tube dependence. The median time to local failure was 10 months, and the median overall survival was 14 months.
Our data demonstrate that proton reirradiation is feasible, with an encouraging symptom control rate, modest radiation-related toxicity, and favorable survival in this high-risk population.
The relative biological effectiveness (RBE) of protons is highly variable and difficult to quantify. However, RBE is related to the local ionization density, which can be related to the physical ...measurable dose weighted linear energy transfer (LETD). The aim of this study was to validate the LETD calculations for proton therapy beams implemented in a commercially available treatment planning system (TPS) using microdosimetry measurements and independent LETD calculations (Open-MCsquare (MCS)). The TPS (RayStation v6R) was used to generate treatment plans on the CIRS-731-HN anthropomorphic phantom for three anatomical sites (brain, nasopharynx, neck) for a spherical target (Ø = 5 cm) with uniform target dose to calculate the LETD distribution. Measurements were performed at the University Medical Center Groningen proton therapy center (Proteus Plus, IBA) using a µ+-probe utilizing silicon on insulator microdosimeters capable of detecting lineal energies as low as 0.15 keV µm−1 in tissue. Dose averaged mean lineal energy depth-profiles were measured for 70 and 130 MeV spots in water and for the three treatment plans in water and an anthropomorphic phantom. The measurements were compared to the LETD calculated in the TPS and MCS independent dose calculation engine. D · was compared to D · LETD in terms of a gamma-index with a distance-to-agreement criteria of 2 mm and increasing dose difference criteria to determine the criteria for which a 90% pass rate was accomplished. Measurements of D · were in good agreement with the D · LETD calculated in the TPS and MCS. The 90% passing rate threshold was reached at different D · LETD difference criteria for single spots (TPS: 1% MCS: 1%), treatment plans in water (TPS: 3% MCS: 6%) and treatment plans in an anthropomorphic phantom (TPS: 6% MCS: 1%). We conclude that D · LETD calculations accuracy in the RayStation TPS and open MCSquare are within 6%, and sufficient for clinical D · LETD evaluation and optimization. These findings remove an important obstacle in the road towards clinical implementation of D · LETD evaluation and optimization of proton therapy treatment plans. Novelty and significance The dose weighed linear energy transfer (LETD) distribution can be calculated for proton therapy treatment plans by Monte Carlo dose engines. The relative biological effectiveness (RBE) of protons is known to vary with the LETD distribution. Therefore, there exists a need for accurate calculation of clinical LETD distributions. Previous LETD validations have focused on general purpose Monte Carlo dose engines which are typically not used clinically. We present the first validation of mean lineal energy measurements of the LETD against calculations by the Monte Carlo dose engines of the Raystation treatment planning system and open MCSquare.
To determine the accuracy of a surface guided radiotherapy (SGRT) system for positioning of breast cancer patients in breath-hold (BH) with respect to cone-beam computed tomography (CBCT). Secondly, ...to evaluate the thorax position stability during BHs with SGRT, when using an air-volume guidance system.
Eighteen left-sided breast cancer patients were monitored with SGRT during CBCT and treatment, both in BH. CBCT scans were matched on the target volume and the patient surface. The setup error differences were evaluated, including with linear regression analysis. The intra-fraction variability and stability of the air-volume guided BHs were determined from SGRT measurements. The variability was determined from the maximum difference between the different BH levels within one treatment fraction. The stability was determined from the difference between the start and end position of each BH.
SGRT data correlated well with CBCT data. The correlation was stronger for surface-to-CBCT (0.61) than target volume-to-CBCT (0.44) matches. Systematic and random setup error differences were ≤ 2 mm in all directions. The 95% limits of agreement (mean ± 2SD) were 0.1 ± 3.0, 0.6 ± 4.1 and 0.4 ± 3.4 mm in the three orthogonal directions, for the surface-to-CBCT matches. For air-volume guided BHs, the variability detected with SGRT was 2.2, 2.8 and 2.3 mm, and the stability - 1.0, 2.1 and 1.5 mm, in three orthogonal directions. Furthermore, the SGRT system could detect unexpected patient movement, undetectable by the air-volume BH system.
With SGRT, left-sided breast cancer patients can be positioned and monitored continuously to maintain position errors within 5 mm. Low intra-fraction variability and good stability can be achieved with the air-volume BH system, however, additional patient position information is available with SGRT, that cannot be detected with air-volume BH systems.
To report on a universal bolus (UB) designed to replace the range shifter (RS); the UB allows the treatment of shallow tumors while keeping the pencil beam scanning (PBS) spot size small.
Ten ...patients with brain cancers treated from 2010 to 2011 were planned using the PBS technique with bolus and the RS. In-air spot sizes of the pencil beam were measured and compared for 4 conditions (open field, with RS, and with UB at 2- and 8-cm air gap) in isocentric geometry. The UB was applied in our clinic to treat brain tumors, and the plans with UB were compared with the plans with RS.
A UB of 5.5 cm water equivalent thickness was found to meet the needs of the majority of patients. By using the UB, the PBS spot sizes are similar with the open beam (P>.1). The heterogeneity index was found to be approximately 10% lower for the UB plans than for the RS plans. The coverage for plans with UB is more conformal than for plans with RS; the largest increase in sparing is usually for peripheral organs at risk.
The integrity of the physical properties of the PBS beam can be maintained using a UB that allows for highly conformal PBS treatment design, even in a simple geometry of the fixed beam line when noncoplanar beams are used.