Predicting liver SBRT eligibility and plan quality for VMAT and 4π plans

Optimal use of limited proton resources for liver cancer patients in combined proton-photon treatments

Objective. Liver cancer patients may benefit from proton therapy through increase of the tumor control probability (TCP). However, proton therapy is a limited resource and may not be available for all patients. We consider combined proton-photon liver SBRT treatments (CPPT) where only some fractions are delivered with protons. It is investigated how limited proton fractions can be used best for individual patients and optimally allocated within a patient group.Approach. Photon and proton treatment plans were created for five liver cancer patients. In CPPT, limited proton fractions may be optimally exploited by increasing the fraction dose compared to the photon fraction dose. To determine a patient's optimal proton and photon fraction doses, we maximize the target biologically effective dose (BED) while constraining the mean normal liver BED, which leads to an up- or downscaling of the proton and photon plan, respectively. The resulting CPPT balances the benefits of fractionation in the normal liver versus exploiting the superior proton dose distributions. After converting the target BED to TCP, the optimal number of proton fractions per patient is determined by maximizing the overall TCP of the patient group.Main results. For the individual patient, a CPPT treatment that delivers a higher fraction dose with protons than photons allows for dose escalation in the target compared to delivering the same proton and photon fraction dose. On the level of a patient group, CPPT may allow to distribute limited proton slots over several patients. Through an optimal use and allocation of proton fractions, CPPT may increase the average patient group TCP compared to a proton patient selection strategy where patients receive single-modality proton or photon treatments.Significance. Limited proton resources can be optimally exploited via CPPT by increasing the target dose in proton fractions and allocating available proton slots to patients with the highest TCP increase.

Advances in Automated Treatment Planning

Treatment planning in radiation therapy has progressed enormously over the past several decades. Such advancements came in the form of innovative hardware and algorithms, giving rise to modalities such as intensity-modulated radiation therapy and volume modulated arc therapy, greatly improving patient outcome and quality of life. While these developments have improved the overall plan quality, they have also given rise to higher treatment planning complexity. This has resulted in increased treatment planning time and higher variability in the final approved plan quality. Radiation oncology, as an already technologically advanced field, has much research and implementation involving the use of AI. The field has begun to show the efficacy of using such technologies in many of its sub-areas, such as in diagnosis, imaging, segmentation, treatment planning, quality assurance, treatment delivery, and follow-up. Some AI technologies have already been clinically implemented by commercial systems. In this article, we will provide an overview to methods involved with treatment planning in radiation therapy. In particular, we will review the recent research and literature related to automation of the treatment planning process, leading to potentially higher efficiency and higher quality plans. We will then present the current and future challenges, as well as some future perspectives.

Can reducing planning safety margins broaden the inclusion criteria for lung stereotactic ablative body radiotherapy?

INTRODUCTION

Stereotactic ablative body radiotherapy (SABR) is currently indicated for inoperable, early-stage non-small cell lung carcinoma (NSCLC). Advancements in image-guidance technology continue to improve treatment precision and enable reductions in planning safety margins. We investigated the dosimetric benefits of margin reduction, its potential to extend SABR to more NSCLC patients and the factors influencing plan acceptability.

METHODS

This retrospective analysis included 61 patients (stage IA-IIIA) treated with conventional radiotherapy. Patients were ineligible for SABR due to tumour size or proximity to organs at risk (OAR). Using Pinnacle auto-planning, three SABR plans were generated for each patient: a regular planning target volume margin plan, a reduced margin plan (gross tumour volume GTV+3 mm) and a non-margin plan. Targets were planned to 48Gy/4 or 50Gy/5 fractions depending on location. Plans were compared in terms of target coverage, OAR doses and dosimetric acceptability based on local guidelines. Predictors of acceptability were investigated using logistic regression analysis.

RESULTS

Compared to regular margin plans, both reduced margin and non-margin plans resulted in significant reductions to almost all dose constraints. Dose conformity was significantly worse in non-margin plans (P < 0.05) and strongly correlated with targets' surface area/volume ratio (R2  = 0.9, P < 0.05). 26% of reduced margin plans were acceptable, compared to 54% of non-margin plans. GTV overlap with OARs significantly affected plan acceptability (OR 0.008, 95% CI 0.001-0.073).

CONCLUSION

Margin reduction significantly reduced OAR doses enabling acceptable plans to be achieved for patients previously excluded from SABR. Indications for lung SABR may broaden as treatment accuracy continues to improve; further work is needed to identify patients most likely to benefit.

Knowledge-based radiation treatment planning: A data-driven method survey

This paper surveys the data-driven dose prediction methods investigated for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories-traditional KBP methods and deep-learning (DL) methods-according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best-matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data-driven KBP methods to dose prediction.

Dosimetric comparison of coplanar and noncoplanar beam arrangements for radiotherapy of patients with lung cancer: A meta-analysis

Purpose

Radiotherapy plays an important role in the treatment of lung cancer, and both coplanar beam arrangements (CBA) and noncoplanar beam arrangements (NCBA) are adopted in clinic practice. The aim of this study is to answer the question whether NCBA are dosimetrically superior to CBA.

Methods

Search of publications were performed in PubMed, Web of Science, and the Cochran Library till March 2020. The searching terms were as following: ((noncoplanar) or ("non coplanar") or ("4pi") or ("4π")) AND (("lung cancer") or ("lung tumor") or ("lung carcinoma")) AND ((radiotherapy) or ("radiation therapy")). The included studies and extracted data were manually screened. All forest and funnel plots were carried out with RevMan software, and the Egger’s regression asymmetry tests were conducted with STATA software.

Results

Nine studies were included and evaluated in the meta‐analysis and treatment plans were designed with both CBA and NCBA. For the planning target volumes (PTV), D98%, D2%, the conformity index (CI), and the gradient index (GI) had no statistically significant difference. For organs‐at‐risk (OAR), V20 of the whole lung and the maximum dose of the spinal cord were significantly reduced in NCBA plans compared with CBA ones. But V10, V5, and mean dose of the whole lung, the maximum dose of the heart, and the maximum dose of the esophagus exhibited no significant difference when the two types of beam arrangements were compared.

Conclusion

After combining multicenter results, NCBA plans have significant advantages in reducing V20 of the whole lung and max dose of spinal cord.

A comparison of Monte Carlo dropout and bootstrap aggregation on the performance and uncertainty estimation in radiation therapy dose prediction with deep learning neural networks

Recently, artificial intelligence technologies and algorithms have become a major focus for advancements in treatment planning for radiation therapy. As these are starting to become incorporated into the clinical workflow, a major concern from clinicians is not whether the model is accurate, but whether the model can express to a human operator when it does not know if its answer is correct. We propose to use Monte Carlo Dropout (MCDO) and the bootstrap aggregation (bagging) technique on deep learning (DL) models to produce uncertainty estimations for radiation therapy dose prediction. We show that both models are capable of generating a reasonable uncertainty map, and, with our proposed scaling technique, creating interpretable uncertainties and bounds on the prediction and any relevant metrics. Performance-wise, bagging provides statistically significant reduced loss value and errors in most of the metrics investigated in this study. The addition of bagging was able to further reduce errors by another 0.34% for [Formula: see text] and 0.19% for [Formula: see text] on average, when compared to the baseline model. Overall, the bagging framework provided significantly lower mean absolute error (MAE) of 2.62, as opposed to the baseline model's MAE of 2.87. The usefulness of bagging, from solely a performance standpoint, does highly depend on the problem and the acceptable predictive error, and its high upfront computational cost during training should be factored in to deciding whether it is advantageous to use it. In terms of deployment with uncertainty estimations turned on, both methods offer the same performance time of about 12 s. As an ensemble-based metaheuristic, bagging can be used with existing machine learning architectures to improve stability and performance, and MCDO can be applied to any DL models that have dropout as part of their architecture.

Offline Quality Assurance for Intensity Modulated Radiation Therapy Treatment Plans for NRG-HN001 Head and Neck Clinical Trial Using Knowledge-Based Planning

PURPOSE

This study aimed to investigate whether a disease site-specific, multi-institutional knowledge based-planning (KBP) model can improve the quality of intensity modulated radiation therapy treatment planning for patients enrolled in the head and neck NRG-HN001clinical trial and to establish a threshold of improvements of treatment plans submitted to the clinical trial.

METHODS AND MATERIALS

Fifty treatment plans for patients enrolled in the NRG-HN001 clinical trial were used to build a KBP model; the model was then used to reoptimize 50 other plans. We compared the dosimetric parameters of the submitted and KBP reoptimized plans. We compared differences between KBP and submitted plans for single- and multi-institutional treatment plans.

RESULTS

Mean values for the dose received by 95% of the planning target volume (PTV_6996) and for the maximum dose (D0.03cc) of PTV_6996 were 0.5 Gy and 2.1 Gy higher in KBP plans than in the submitted plans, respectively. Mean values for D0.03cc to the brain stem, spinal cord, optic nerve_R, optic nerve_L, and chiasm were 2.5 Gy, 1.9 Gy, 6.4 Gy, 6.6 Gy, and 5.7 Gy lower in the KBP plans than in the submitted plans. Mean values for Dmean to parotid_R and parotid_L glands were 2.2 Gy and 3.8 Gy lower in KBP plans, respectively. In 33 out of 50 KBP plans, we observed improvements in sparing of at least 7 organs at risk (OARs) (brain stem, spinal cord, optic nerves (R & L), chiasm, and parotid glands [R & L]). A threshold of improvement of OARs sparing of 5% of the prescription dose was established for providing the quality assurance results back to the treating institution.

CONCLUSIONS

A disease site-specific, multi-institutional, clinical trial-based KBP model improved sparing of OARs in a large number of reoptimized plans submitted to the NRG-HN001 clinical trial, and the model is being used as an offline quality assurance tool.

An Automated Workflow to Improve Efficiency in Radiation Therapy Treatment Planning by Prioritizing Organs at Risk

PURPOSE

Manual delineation (MD) of organs at risk (OAR) is time and labor intensive. Auto-delineation (AD) can reduce the need for MD, but because current algorithms are imperfect, manual review and modification is still typically used. Recognizing that many OARs are sufficiently far from important dose levels that they do not pose a realistic risk, we hypothesize that some OARs can be excluded from MD and manual review with no clinical effect. The purpose of this study was to develop a method that automatically identifies these OARs and enables more efficient workflows that incorporate AD without degrading clinical quality.

METHODS AND MATERIALS

Preliminary dose map estimates were generated for n = 10 patients with head and neck cancers using only prescription and target-volume information. Conservative estimates of clinical OAR objectives were computed using AD structures with spatial expansion buffers to account for potential delineation uncertainties. OARs with estimated dose metrics below clinical tolerances were deemed low priority and excluded from MD and/or manual review. Final plans were then optimized using high-priority MD OARs and low-priority AD OARs and compared with reference plans generated using all MD OARs. Multiple different spatial buffers were used to accommodate different potential delineation uncertainties.

RESULTS

Sixty-seven out of 201 total OARs were identified as low-priority using the proposed methodology, which permitted a 33% reduction in structures requiring manual delineation/review. Plans optimized using low-priority AD OARs without review or modification met all planning objectives that were met when all MD OARs were used, indicating clinical equivalence.

CONCLUSIONS

Prioritizing OARs using estimated dose distributions allowed a substantial reduction in required MD and review without affecting clinically relevant dosimetry.

Artificial intelligence in radiotherapy: a technological review

Radiation therapy (RT) is widely used to treat cancer. Technological advances in RT have occurred in the past 30 years. These advances, such as three-dimensional image guidance, intensity modulation, and robotics, created challenges and opportunities for the next breakthrough, in which artificial intelligence (AI) will possibly play important roles. AI will replace certain repetitive and labor-intensive tasks and improve the accuracy and consistency of others, particularly those with increased complexity because of technological advances. The improvement in efficiency and consistency is important to manage the increasing cancer patient burden to the society. Furthermore, AI may provide new functionalities that facilitate satisfactory RT. The functionalities include superior images for real-time intervention and adaptive and personalized RT. AI may effectively synthesize and analyze big data for such purposes. This review describes the RT workflow and identifies areas, including imaging, treatment planning, quality assurance, and outcome prediction, that benefit from AI. This review primarily focuses on deep-learning techniques, although conventional machine-learning techniques are also mentioned.

A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity-modulated radiation therapy

PURPOSE

Beam orientation selection, whether manual or protocol-based, is the current clinical standard in radiation therapy treatment planning, but it is tedious and can yield suboptimal results. Many algorithms have been designed to optimize beam orientation selection because of its impact on treatment plan quality, but these algorithms suffer from slow calculation of the dose influence matrices of all candidate beams. We propose a fast beam orientation selection method, based on deep learning neural networks (DNN), capable of developing a plan comparable to those developed by the state-of-the-art column generation (CG) method. Our model's novelty lies in its supervised learning structure (using CG to teach the network), DNN architecture, and ability to learn from anatomical features to predict dosimetrically suitable beam orientations without using dosimetric information from the candidate beams. This may save hours of computation.

METHODS

A supervised DNN is trained to mimic the CG algorithm, which iteratively chooses beam orientations one-by-one by calculating beam fitness values based on Karush-Kush-Tucker optimality conditions at each iteration. The DNN learns to predict these values. The dataset contains 70 prostate cancer patients - 50 training, 7 validation, and 13 test patients - to develop and test the model. Each patient's data contains 6 contours: PTV, body, bladder, rectum, and left and right femoral heads. Column generation was implemented with a GPU-based Chambolle-Pock algorithm, a first-order primal-dual proximal-class algorithm, to create 6270 plans. The DNN trained over 400 epochs, each with 2500 steps and a batch size of 1, using the Adam optimizer at a learning rate of 1 × 10-5 and a sixfold cross-validation technique.

RESULTS

The average and standard deviation of training, validation, and testing loss functions among the six folds were 0.62 ± 0.09%, 1.04 ± 0.06%, and 1.44 ± 0.11%, respectively. Using CG and supervised DNN, we generated two sets of plans for each scenario in the test set. The proposed method took at most 1.5 s to select a set of five beam orientations and 300 s to calculate the dose influence matrices for 5 beams and finally 20 s to solve the fluence map optimization (FMO). However, CG needed around 15 h to calculate the dose influence matrices of all beams and at least 400 s to solve both the beam orientation selection and FMO problems. The differences in the dose coverage of PTV between plans generated by CG and by DNN were 0.2%. The average dose differences received by organs at risk were between 1 and 6 percent: Bladder had the smallest average difference in dose received (0.956 ± 1.184%), then Rectum (2.44 ± 2.11%), Left Femoral Head (6.03 ± 5.86%), and Right Femoral Head (5.885 ± 5.515%). The dose received by Body had an average difference of 0.10 ± 0.1% between the generated treatment plans.

CONCLUSIONS

We developed a fast beam orientation selection method based on a DNN that selects beam orientations in seconds and is therefore suitable for clinical routines. In the training phase of the proposed method, the model learns the suitable beam orientations based on patients' anatomical features and omits time intensive calculations of dose influence matrices for all possible candidate beams. Solving the FMO to get the final treatment plan requires calculating dose influence matrices only for the selected beams.

Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose-volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy

PURPOSE

We propose a novel domain-specific loss, which is a differentiable loss function based on the dose-volume histogram (DVH), and combine it with an adversarial loss for the training of deep neural networks. In this study, we trained a neural network for generating Pareto optimal dose distributions, and evaluate the effects of the domain-specific loss on the model performance.

METHODS

In this study, three loss functions - mean squared error (MSE) loss, DVH loss, and adversarial (ADV) loss - were used to train and compare four instances of the neural network model: (a) MSE, (b) MSE + ADV, (c) MSE + DVH, and (d) MSE + DVH+ADV. The data for 70 prostate patients, including the planning target volume (PTV), and the organs at risk (OAR) were acquired as 96 × 96 × 24 dimension arrays at 5 mm3 voxel size. The dose influence arrays were calculated for 70 prostate patients, using a 7 equidistant coplanar beam setup. Using a scalarized multicriteria optimization for intensity-modulated radiation therapy, 1200 Pareto surface plans per patient were generated by pseudo-randomizing the PTV and OAR tradeoff weights. With 70 patients, the total number of plans generated was 84 000 plans. We divided the data into 54 training, 6 validation, and 10 testing patients. Each model was trained for a total of 100,000 iterations, with a batch size of 2. All models used the Adam optimizer, with a learning rate of 1 × 10-3 .

RESULTS

Training for 100 000 iterations took 1.5 days (MSE), 3.5 days (MSE+ADV), 2.3 days (MSE+DVH), and 3.8 days (MSE+DVH+ADV). After training, the prediction time of each model is 0.052 s. Quantitatively, the MSE+DVH+ADV model had the lowest prediction error of 0.038 (conformation), 0.026 (homogeneity), 0.298 (R50), 1.65% (D95), 2.14% (D98), and 2.43% (D99). The MSE model had the worst prediction error of 0.134 (conformation), 0.041 (homogeneity), 0.520 (R50), 3.91% (D95), 4.33% (D98), and 4.60% (D99). For both the mean dose PTV error and the max dose PTV, Body, Bladder and rectum error, the MSE+DVH+ADV outperformed all other models. Regardless of model, all predictions have an average mean and max dose error <2.8% and 4.2%, respectively.

CONCLUSION

The MSE+DVH+ADV model performed the best in these categories, illustrating the importance of both human and learned domain knowledge. Expert human domain-specific knowledge can be the largest driver in the performance improvement, and adversarial learning can be used to further capture nuanced attributes in the data. The real-time prediction capabilities allow for a physician to quickly navigate the tradeoff space for a patient, and produce a dose distribution as a tangible endpoint for the dosimetrist to use for planning. This is expected to considerably reduce the treatment planning time, allowing for clinicians to focus their efforts on the difficult and demanding cases.

Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future

Treatment planning is an essential step of the radiotherapy workflow. It has become more sophisticated over the past couple of decades with the help of computer science, enabling planners to design highly complex radiotherapy plans to minimize the normal tissue damage while persevering sufficient tumor control. As a result, treatment planning has become more labor intensive, requiring hours or even days of planner effort to optimize an individual patient case in a trial-and-error fashion. More recently, artificial intelligence has been utilized to automate and improve various aspects of medical science. For radiotherapy treatment planning, many algorithms have been developed to better support planners. These algorithms focus on automating the planning process and/or optimizing dosimetric trade-offs, and they have already made great impact on improving treatment planning efficiency and plan quality consistency. In this review, the smart planning tools in current clinical use are summarized in 3 main categories: automated rule implementation and reasoning, modeling of prior knowledge in clinical practice, and multicriteria optimization. Novel artificial intelligence-based treatment planning applications, such as deep learning-based algorithms and emerging research directions, are also reviewed. Finally, the challenges of artificial intelligence-based treatment planning are discussed for future works.

4π Radiotherapy Using a Linear Accelerator: A Misnomer in Violation of the Solid Geometric Boundary Conditions in Three-Dimensional Euclidean Space

Purpose:

The concept of 4π^c radiotherapy is a radiotherapy planning technique receiving much attention in recent times. The aim of this article is to disprove the feasibility of the 4π radiotherapy using a cantilever-type linear accelerator or any other external-beam delivery machines.

Materials and Methods:

A surface integral-based mathematical derivation for the maximum achievable solid angle for a linear accelerator was carried out respecting the rotational boundary conditions for gantry and couch in three-dimensional Euclidean space. The allowed movements include a gantry rotation of 0–2π^c and a table rotation of .

Results:

Total achievable solid angle by cantilever-type linear accelerator (or any teletherapy machine employing a cantilever design) is , which is applicable only for the foot and brain radiotherapy where the allowed table rotation is 90°–0°–270°. For other sites such as pelvis, thorax, or abdomen, achievable solid angle as the couch rotation comes down significantly. Practically, only suitable couch angle is 0° by avoiding gantry–couch–patient collision.

Conclusions:

Present cantilever design of linear accelerator prevents achieving a 4π radian solid angle at any point in the patient. Even the most modern therapy machines like CyberKnife which has a robotic arm also cannot achieve 4π geometry. Maximum achievable solid angle under the highest allowable boundary condition(s) cannot exceed 2π^c, which is restricted for only extremities such as foot and brain radiotherapy. For other parts of the body such as pelvis, thorax, and abdomen, the solid angle is reduced to 1/5^th (maximum value) of the 4π^c. To obtain a 4π^c solid angle in a three-dimensional Euclidean space, the patient has to be a zero-dimensional point and X-ray head of the linear accelerator has a freedom to rotate in every point of a hypothetical sphere of radius 1 m. This article establishes geometrically why it is not possible to achieve a 4π^c solid angle.

Automated 4π radiotherapy treatment planning with evolving knowledge-base

PURPOSE

Non-coplanar 4π radiotherapy generalizes intensity modulated radiation therapy (IMRT) to automate beam geometry selection but requires complicated hyperparameter tuning to attain superior plan quality, which can be tedious and inconsistent. In this study, a fully automated 4π treatment planning was developed using evolving knowledge-base (EKB) planning guided by dose prediction.

METHODS

Twenty 4π lung and twenty 4π head and neck (HN) cases were included. A statistical voxel dose learning model was initially trained on low-quality plans created using generic hyperparameter templates without manual tuning. To improve the automated plan quality without being limited by the training data quality, a new 4π optimization problem was formulated to include a one-sided penalty on the organ-at-risk (OAR) dose deviation from the predicted dose. This directional OAR penalty encourages superior OAR sparing. The fast iterative shrinkage-thresholding algorithm (FISTA) was used to solve the large-scale beam orientation optimization problem. With the improved plans, new predictions were created to guide the next loop of EKB planning for a total of 10 loops. Plan quality was evaluated using a plan quality metric (PQM) points system based on clinical dose constraints and compared with automated planning approaches guided by manual high-quality plans using all non-coplanar beams, automated plans using individually evolved targeted dose, and manually created 4π plans.

RESULTS

For the lung cases, the final EKB plans had significantly higher PQM than manually created 4π (+2.60%). The improvements plateaued after the third loop. The final HN EKB plans and manually created 4π plans had comparable PQMs, but had lower PQM compared to automated plans using a high-quality training set (-3.00% and -4.44%, respectively). The PQM consistently increased up to the sixth loop. Individually evolved plans were able to improve the plan quality from initial condition due to the one-sided cost function but the 60% of them were trapped in undesired local minima that were substantially worse than their corresponding EKB plans.

CONCLUSION

Evolving knowledge-base planning is a novel automated planning technique guided by the predicted three-dimensional dose distribution, which can evolve from low-quality plans. EKB allows new beams to be used in the automated planning workflow for superior plan quality.

MRI-based treatment planning for liver stereotactic body radiotherapy: validation of a deep learning-based synthetic CT generation method

OBJECTIVE

The purpose of this work is to develop and validate a learning-based method to derive electron density from routine anatomical MRI for potential MRI-based SBRT treatment planning.

METHODS

We proposed to integrate dense block into cycle generative adversarial network (GAN) to effectively capture the relationship between the CT and MRI for CT synthesis. A cohort of 21 patients with co-registered CT and MR pairs were used to evaluate our proposed method by the leave-one-out cross-validation. Mean absolute error, peak signal-to-noise ratio and normalized cross-correlation were used to quantify the imaging differences between the synthetic CT (sCT) and CT. The accuracy of Hounsfield unit (HU) values in sCT for dose calculation was evaluated by comparing the dose distribution in sCT-based and CT-based treatment planning. Clinically relevant dose-volume histogram metrics were then extracted from the sCT-based and CT-based plans for quantitative comparison.

RESULTS

The mean absolute error, peak signal-to-noise ratio and normalized cross-correlation of the sCT were 72.87 ± 18.16 HU, 22.65 ± 3.63 dB and 0.92 ± 0.04, respectively. No significant differences were observed in the majority of the planning target volume and organ at risk dose-volume histogram metrics ( p  >  0.05). The average pass rate of γ analysis was over 99% with 1%/1 mm acceptance criteria on the coronal plane that intersects with isocenter.

CONCLUSION

The image similarity and dosimetric agreement between sCT and original CT warrant further development of an MRI-only workflow for liver stereotactic body radiation therapy.

ADVANCES IN KNOWLEDGE

This work is the first deep-learning-based approach to generating abdominal sCT through dense-cycle-GAN. This method can successfully generate the small bony structures such as the rib bones and is able to predict the HU values for dose calculation with comparable accuracy to reference CT images.

Recent developments in non-coplanar radiotherapy

This paper gives an overview of recent developments in non-coplanar intensity modulated radiotherapy (IMRT) and volumetric modulated arc therapy (VMAT). Modern linear accelerators are capable of automating motion around multiple axes, allowing efficient delivery of highly non-coplanar radiotherapy techniques. Novel techniques developed for C-arm and non-standard linac geometries, methods of optimization, and clinical applications are reviewed. The additional degrees of freedom are shown to increase the therapeutic ratio, either through dose escalation to the target or dose reduction to functionally important organs at risk, by multiple research groups. Although significant work is still needed to translate these new non-coplanar radiotherapy techniques into the clinic, clinical implementation should be prioritized. Recent developments in non-coplanar radiotherapy demonstrate that it continues to have a place in modern cancer treatment.

Comparison of 2 methods for prediction of liver dosimetric indices in hepatocellular cancer IMRT planning

To evaluate the performance of 2 methods predicting liver dosimetric indices for hepatocellular cancer patients treated with intensity modulated radiation therapy (IMRT). Two predicting methods were implemented to build correlation between geometric and dosimetric information of hepatocellular cancer IMRT plans. One method used Principle Component Analysis method to simplify information and Support Vector Machine (SVM) regression method to build correlation. The other method used a simple linear function to map volumes of certain regions to dosimetic indices. Thirty eight hepatocellular cancer IMRT plans were randomly selected to train the 2 methods. The effectiveness of the 2 methods was validated using another 8 plans. Liver dosimetric indices V₁₀, V₂₀, V₃₀, and mean dose of the 8 plans in validation cohort were calculated using the predicting methods. The predicted indices were compared with the indices derived from the clinically accepted treatment plans. The absolute differences of V₁₀ calculated with the SVM method and the actual values of treatment plans had a mean value of 7.87%. And the values for V₂₀, V₃₀, and mean dose were 4.37%, 4.41%, and 4.20%, respectively. The absolute differences of V₁₀ calculated with the linear formulation method and the actual values of treatment plans had a mean value of 6.09%. And the values for V₂₀, V₃₀, and mean dose were 5.28%, 5.05%, and 5.92%, respectively. These 2 methods have similar accuracy in predicting dosimetric indices V₁₀, V₂₀, V₃₀ of livers. The predicting of V₃₀ and V₂₀ is more accurate than the predicting of V₁₀. The SVM method is more accurate in predicting mean liver dose.

A deep learning method for prediction of three-dimensional dose distribution of helical tomotherapy

PURPOSE

To develop a deep learning method for prediction of three-dimensional (3D) voxel-by-voxel dose distributions of helical tomotherapy (HT).

METHODS

Using previously treated HT plans as training data, a deep learning model named U-ResNet-D was trained to predict a 3D dose distribution. First, the contoured structures and dose volumes were converted from plan database to 3D matrix with a program based on a developed visualization toolkit (VTK), then transferred to U-ResNet-D for correlating anatomical features and dose distributions at voxel-level. One hundred and ninety nasopharyngeal cancer (NPC) patients treated by HT with multiple planning target volumes (PTVs) in different prescription patterns were studied. The model was typically trained from scratch with weights randomly initialized rather than using transfer-learning method, and used to predict new patient's 3D dose distributions. The predictive accuracy was evaluated with three methods: (a) The dose difference at the position r, δ(r, r) = D_c (r) - D_p (r), was calculated for each voxel. The mean (μ_δ(r,r) ) and standard deviation (σ_δ(r,r) ) of δ(r, r) were calculated to assess the prediction bias and precision; (b) The mean absolute differences of dosimetric indexes (DIs) including maximum and mean dose, homogeneity index, conformity index, and dose spillage for PTVs and organ at risks (OARs) were calculated and statistically analyzed with the paired-samples t test; (c) Dice similarity coefficients (DSC) between predicted and clinical isodose volumes were calculated.

RESULTS

The U-ResNet-D model predicted 3D dose distribution accurately. For twenty tested patients, the prediction bias ranged from -2.0% to 2.3% and prediction error varied from 1.5% to 4.5% (relative to prescription) for 3D dose differences. The mean absolute dose differences for PTVs and OARs are within 2.0% and 4.2%, and nearly all the DIs for PTVs and OARs had no significant differences. The averaged DSC ranged from 0.95 to 1 for different isodose volumes.

CONCLUSIONS

The study developed a new deep learning method for 3D voxel-by-voxel dose prediction, and shown to be able to produce accurately dose predictions for nasopharyngeal patients treated by HT. The predicted 3D dose map can be useful for improving radiotherapy planning design, ensuring plan quality and consistency, making clinical technique comparison, and guiding automatic treatment planning.

Performance Comparison of Knowledge-Based Dose Prediction Techniques Based on Limited Patient Data

Purpose:

The accuracy of dose prediction is essential for knowledge-based planning and automated planning techniques. We compare the dose prediction accuracy of 3 prediction methods including statistical voxel dose learning, spectral regression, and support vector regression based on limited patient training data.

Methods:

Statistical voxel dose learning, spectral regression, and support vector regression were used to predict the dose of noncoplanar intensity-modulated radiation therapy (4π) and volumetric-modulated arc therapy head and neck, 4π lung, and volumetric-modulated arc therapy prostate plans. Twenty cases of each site were used for k-fold cross-validation, with k = 4. Statistical voxel dose learning bins voxels according to their Euclidean distance to the planning target volume and uses the median to predict the dose of new voxels. Distance to the planning target volume, polynomial combinations of the distance components, planning target volume, and organ at risk volume were used as features for spectral regression and support vector regression. A total of 28 features were included. Principal component analysis was performed on the input features to test the effect of dimension reduction. For the coplanar volumetric-modulated arc therapy plans, separate models were trained for voxels within the same axial slice as planning target volume voxels and voxels outside the primary beam. The effect of training separate models for each organ at risk compared to all voxels collectively was also tested. The mean squared error was calculated to evaluate the voxel dose prediction accuracy.

Results:

Statistical voxel dose learning using separate models for each organ at risk had the lowest root mean squared error for all sites and modalities: 3.91 Gy (head and neck 4π), 3.21 Gy (head and neck volumetric-modulated arc therapy), 2.49 Gy (lung 4π), and 2.35 Gy (prostate volumetric-modulated arc therapy). Compared to using the original features, principal component analysis reduced the 4π prediction error for head and neck spectral regression (−43.9%) and support vector regression (−42.8%) and lung support vector regression (−24.4%) predictions. Principal component analysis was more effective in using all/most of the possible principal components. Separate organ at risk models were more accurate than training on all organ at risk voxels in all cases.

Conclusion:

Compared with more sophisticated parametric machine learning methods with dimension reduction, statistical voxel dose learning is more robust to patient variability and provides the most accurate dose prediction method.

Elective nodal irradiation with simultaneous integrated boost stereotactic body radiotherapy for pancreatic cancer: Analyses of planning feasibility and geometrically driven DVH prediction model

PURPOSE

We evaluate the feasibility of the elective nodal irradiation strategy in stereotactic body radiotherapy (SBRT) for pancreatic cancer.

METHODS

Three simultaneous integrated boost (SIB)-SBRT plans (Boost1, Boost2, and Boost3) were retrospectively generated for each of 20 different patients. Boost1 delivered 33 and 25 Gy to PTV1 and PTV2, respectively. Boost2 delivered 40, 33, and 25 Gy to boostCTV, PTV1, and PTV2, respectively. Boost3 delivered 33 and 25 Gy to PTV1 and PTV3, respectively. PTV1 covered the initial standard SBRT plan (InitPlan) gross tumor volume (GTV). PTV2 covered CTVgeom which was created by a 10-mm expansion (15 mm posterior) of GTV. PTV3 covered CTVprop which included elective nodal regions. The boostCTV included GTV as well as involved vasculature. The planning feasibility in each scenario and dose-volume histograms (DVHs) were analyzed and compared with the InitPlan (delivered 33 Gy only to PTV1) by paired t-test. Next, a novel DVH prediction model was developed and its performance was evaluated according to the prediction accuracy (AC) of planning violations. Then, the model was used to simulate the impacts of GTV-to-organs at risk (OAR) distance and gastrointestinal (GI) OAR volume variations on planning feasibility.

RESULTS

Significant dose increases were observed in GI-OARs in SIB-SBRT plans when compared with InitPlan. All dose constraints were met in 63% of cases in InitPlan, Boost1, and Boost2, whereas Boost3 developed DVH violations in all cases. Utilizing previous patient anatomy, the novel DVH prediction model achieved a high AC in the prediction of violations for GI-OARs; the positive predictive value, negative predictive value, and AC were 66%, 90%, and 84%, respectively. Experiments with the model demonstrated that the larger proximity volume of GI-OAR at the shorter distance substantially impacted on planning violations.

CONCLUSIONS

SIB-SBRT plan with geometrically defined prophylactic areas can be dosimetrically feasible, but including all nodal areas with 25 Gy in five fractions appears to be unrealistic.

A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient's PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks

The goal of this study is to demonstrate the feasibility of a novel fully-convolutional volumetric dose prediction neural network (DoseNet) and test its performance on a cohort of prostate stereotactic body radiotherapy (SBRT) patients. DoseNet is suggested as a superior alternative to U-Net and fully connected distance map-based neural networks for non-coplanar SBRT prostate dose prediction. DoseNet utilizes 3D convolutional downsampling with corresponding 3D deconvolutional upsampling to preserve memory while simultaneously increasing the receptive field of the network. DoseNet was implemented on 2 Nvidia 1080 Ti graphics processing units and utilizes a 3 phase learning protocol to help achieve convergence and improve generalization. DoseNet was trained, validated, and tested with 151 patients following Kaggle completion rules. The dosimetric quality of DoseNet was evaluated by comparing the predicted dose distribution with the clinically approved delivered dose distribution in terms of conformity index, heterogeneity index, and various clinically relevant dosimetric parameters. The results indicate that the DoseNet algorithm is a superior alternative to U-Net and fully connected methods for prostate SBRT patients. DoseNet required ~50.1 h to train, and ~0.83 s to make a prediction on a 128  ×  128  ×  64 voxel image. In conclusion, DoseNet is capable of making accurate volumetric dose predictions for non-coplanar SBRT prostate patients, while simultaneously preserving computational efficiency.

Automation in intensity modulated radiotherapy treatment planning-a review of recent innovations

Radiotherapy treatment planning of complex radiotherapy techniques, such as intensity modulated radiotherapy and volumetric modulated arc therapy, is a resource-intensive process requiring a high level of treatment planner intervention to ensure high plan quality. This can lead to variability in the quality of treatment plans and the efficiency in which plans are produced, depending on the skills and experience of the operator and available planning time. Within the last few years, there has been significant progress in the research and development of intensity modulated radiotherapy treatment planning approaches with automation support, with most commercial manufacturers now offering some form of solution. There is a rapidly growing number of research articles published in the scientific literature on the topic. This paper critically reviews the body of publications up to April 2018. The review describes the different types of automation algorithms, including the advantages and current limitations. Also included is a discussion on the potential issues with routine clinical implementation of such software, and highlights areas for future research.

[Stereotactic body radiation therapy for hepatic malignancies: Organs at risk, uncertainties margins, doses]

Stereotactic body radiation therapy for primary and metastatic hepatic malignancies can be performed in association and/or as an alternative to surgery and radiofrequency. The consequences of the great number of techniques available are heterogeneity in contouring, dose prescription and in determination of dose constraints for organs at risk. The objective of this paper is to improve the quality and safety and to help the diffusion of this technique for a majority of patients. In 2016, the French Society of Radiation Oncology (SFRO) published guidelines for external radiotherapy and brachytherapy ("Recorad"). This paper is an update of these recommendations considering recent publications.