Dynamic stochastic deep learning approaches for predicting geometric changes in head and neck cancer.

Modern radiotherapy stands to benefit from the ability to efficiently adapt plans during treatment in response to setup and geometric variations such as those caused by internal organ deformation or tumor shrinkage. A promising strategy is to develop a framework, which given an initial state defined by patient-attributes, can predict future states based on pre-learned patterns from a well-defined patient population.Here, we investigate the feasibility of predicting patient anatomical changes, defined as a joint state of volume and daily setup changes, across a fractionated treatment schedule using two approaches.

Quantum-inspired algorithm for radiotherapy planning optimization.

Purpose: Modern inverse radiotherapy treatment planning requires nonconvex, large-scale optimizations that must be solved within a clinically feasible timeframe. We have developed and tested a quantum-inspired, stochastic algorithm for intensity-modulated radiotherapy (IMRT): quantum tunnel annealing (QTA). By modeling the likelihood probability of accepting a higher energy solution after a particle tunneling through a potential energy barrier, QTA features an additional degree of freedom (the barrier width, w) not shared by traditional stochastic optimization methods such as Simulated Annealing (SA).

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.

Purpose: Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning.

Methods: A total of 118 NSCLC patients treated on prospective protocols with 32 cases of local progression and 20 cases of RP grade 2 or higher (RP2) were studied.

Priority-driven plan optimization in locally advanced lung patients based on perfusion SPECT imaging.

Purpose: Limits on mean lung dose (MLD) allow for individualization of radiation doses at safe levels for patients with lung tumors. However, MLD does not account for individual differences in the extent or spatial distribution of pulmonary dysfunction among patients, which leads to toxicity variability at the same MLD. We investigated dose rearrangement to minimize the radiation dose to the functional lung as assessed by perfusion single photon emission computed tomography (SPECT) and maximize the target coverage to maintain conventional normal tissue limits.

The big data effort in radiation oncology: Data mining or data farming?

Although large volumes of information are entered into our electronic health care records, radiation oncology information systems and treatment planning systems on a daily basis, the goal of extracting and using this big data has been slow to emerge. Development of strategies to meet this goal is aided by examining issues with a data farming instead of a data mining conceptualization. Using this model, a vision of key data elements, clinical process changes, technology issues and solutions, and role for professional societies is presented.

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis.

Background: In non-small-cell lung cancer radiotherapy, radiation pneumonitis≥grade 2 (RP2) depends on patients' dosimetric, clinical, biological and genomic characteristics.

Methods: We developed a Bayesian network (BN) approach to explore its potential for interpreting biophysical signaling pathways influencing RP2 from a heterogeneous dataset including single nucleotide polymorphisms, micro RNAs, cytokines, clinical data, and radiation treatment plans before and during the course of radiotherapy. Model building utilized 79 patients (21 with RP2) with complete data, and model testing used 50 additional patients with incomplete data.

Decreased Lung Perfusion After Breast/Chest Wall Irradiation: Quantitative Results From a Prospective Clinical Trial.

Purpose: To quantify lung perfusion changes after breast/chest wall radiation therapy (RT) using pre- and post-RT single photon emission computed tomography/computed tomography (SPECT/CT) attenuation-corrected perfusion scans; and correlate decreased perfusion with adjuvant RT dose for breast cancer in a prospective clinical trial.

Methods And Materials: As part of an institutional review board-approved trial studying the impact of RT technique on lung function in node-positive breast cancer, patients received breast/chest wall and regional nodal irradiation including superior internal mammary node RT to 50 to 52.2 Gy with a boost to the tumor bed/mastectomy scar.

FusionArc optimization: a hybrid volumetric modulated arc therapy (VMAT) and intensity modulated radiation therapy (IMRT) planning strategy.

Purpose: To introduce a hybrid volumetric modulated arc therapy/intensity modulated radiation therapy (VMAT/IMRT) optimization strategy called FusionArc that combines the delivery efficiency of single-arc VMAT with the potentially desirable intensity modulation possible with IMRT.

Methods: A beamlet-based inverse planning system was enhanced to combine the advantages of VMAT and IMRT into one comprehensive technique. In the hybrid strategy, baseline single-arc VMAT plans are optimized and then the current cost function gradients with respect to the beamlets are used to define a metric for predicting which beam angles would benefit from further intensity modulation.

Penalization of aperture complexity in inversely planned volumetric modulated arc therapy.

Purpose: Apertures obtained during volumetric modulated arc therapy (VMAT) planning can be small and irregular, resulting in dosimetric inaccuracies during delivery. Our purpose is to develop and integrate an aperture-regularization objective function into the optimization process for VMAT, and to quantify the impact of using this objective function on dose delivery accuracy and optimized dose distributions.

Methods: An aperture-based metric ("edge penalty") was developed that penalizes complex aperture shapes based on the ratio of MLC side edge length and aperture area.

Inverse-optimized 3D conformal planning: minimizing complexity while achieving equivalence with beamlet IMRT in multiple clinical sites.

Purpose: Inverse planned intensity modulated radiation therapy (IMRT) has helped many centers implement highly conformal treatment planning with beamlet-based techniques. The many comparisons between IMRT and 3D conformal (3DCRT) plans, however, have been limited because most 3DCRT plans are forward-planned while IMRT plans utilize inverse planning, meaning both optimization and delivery techniques are different. This work avoids that problem by comparing 3D plans generated with a unique inverse planning method for 3DCRT called inverse-optimized 3D (IO-3D) conformal planning.

The dosimetric impact of prostate rotations during electromagnetically guided external-beam radiation therapy.

Purpose: To study the impact of daily rotations and translations of the prostate on dosimetric coverage during radiation therapy (RT).

Methods And Materials: Real-time tracking data for 26 patients were obtained during RT. Intensity modulated radiation therapy plans meeting RTOG 0126 dosimetric criteria were created with 0-, 2-, 3-, and 5-mm planning target volume (PTV) margins.

Evaluation of multiple breathing states using a multiple instance geometry approximation (MIGA) in inverse-planned optimization for locoregional breast treatment.

Purpose: Although previous work demonstrated superior dose distributions for left-sided breast cancer patients planned for intensity-modulated radiation therapy (IMRT) at deep inspiration breath hold compared with conventional techniques with free-breathing, such techniques are not always feasible to limit the impact of respiration on treatment delivery. This study assessed whether optimization based on multiple instance geometry approximation (MIGA) could derive an IMRT plan that is less sensitive to known respiratory motions.

Methods And Materials: CT scans were acquired with an active breathing control device at multiple breath-hold states.

Adaptive diffusion smoothing: a diffusion-based method to reduce IMRT field complexity.

Inverse-planned intensity modulated radiation therapy (IMRT) is often able to achieve complex treatment planning goals that are unattainable with forward three-dimensional (3D) conformal planning. However, the common use of IMRT has introduced several new challenges. The potentially high degree of modulation in IMRT beams risks the loss of some advantages of 3D planning, such as excellent target coverage and high delivery efficiency.

Lexicographic ordering: intuitive multicriteria optimization for IMRT.

Optimization problems in IMRT inverse planning are inherently multicriterial since they involve multiple planning goals for targets and their neighbouring critical tissue structures. Clinical decisions are generally required, based on tradeoffs among these goals. Since the tradeoffs cannot be quantitatively determined prior to optimization, the decision-making process is usually indirect and iterative, requiring many repetitive optimizations.

How extensive of a 4D dataset is needed to estimate cumulative dose distribution plan evaluation metrics in conformal lung therapy?

The purpose of this study was to investigate the number of intermediate states required to adequately approximate the clinically relevant cumulative dose to deforming/moving thoracic anatomy in four-dimensional (4D) conformal radiotherapy that uses 6 MV photons to target tumors. Four patients were involved in this study. For the first three patients, computed tomography images acquired at exhale and inhale were available; they were registered using B-spline deformation model and the computed transformation was further used to simulate intermediate states between exhale and inhale.

Reporting and analyzing statistical uncertainties in Monte Carlo-based treatment planning.

Purpose: To investigate methods of reporting and analyzing statistical uncertainties in doses to targets and normal tissues in Monte Carlo (MC)-based treatment planning.

Methods And Materials: Methods for quantifying statistical uncertainties in dose, such as uncertainty specification to specific dose points, or to volume-based regions, were analyzed in MC-based treatment planning for 5 lung cancer patients. The effect of statistical uncertainties on target and normal tissue dose indices was evaluated.

Monte Carlo-based lung cancer treatment planning incorporating PET-defined target volumes.

Despite the well-known benefits of positron emission tomography (PET) imaging in lung cancer diagnosis and staging, the poor spatial resolution of PET has limited its use in radiotherapy planning. Methods used for segmenting tumor from normal tissue, such as threshold boundaries using a fraction of the standardized uptake value (SUV), are subject to uncertainties. The issue of respiratory motion in the thorax confounds the problem of accurate target definition.

Dose reconstruction in deforming lung anatomy: dose grid size effects and clinical implications.

In this study we investigated the accumulation of dose to a deforming anatomy (such as lung) based on voxel tracking and by using time weighting factors derived from a breathing probability distribution function (p.d.f.

Evaluating the influence of setup uncertainties on treatment planning for focal liver tumors.

Purpose: A mechanism has been developed to evaluate the influence of random setup variations on dose during treatment planning. The information available for studying these factors shifts from population-based models toward patient-specific data as treatment progresses and setup measurements for an individual patient become available. This study evaluates the influence of population as well as patient-specific setup distributions on treatment plans for focal liver tumors.

The influence of beam model differences in the comparison of dose calculation algorithms for lung cancer treatment planning.

In this study, we show that beam model differences play an important role in the comparison of does calculated with various algorithms for lung cancer treatment planning. These differences may impact the accurate correlation of dose with clinical outcome. To accomplish this, we modified the beam model penumbral parameters in an equivalent path length (EPL) algorithm and subsequently compared the EPL doses with those generated with Monte Carlo (MC).

Mutual information based CT registration of the lung at exhale and inhale breathing states using thin-plate splines.

The advent of dynamic radiotherapy modeling and treatment techniques requires an infrastructure to weigh the merits of various interventions (breath holding, gating, tracking). The creation of treatment planning models that account for motion and deformation can allow the relative worth of such techniques to be evaluated. In order to develop a treatment planning model of a moving and deforming organ such as the lung, registration tools that account for deformation are required.

Accounting for center-of-mass target motion using convolution methods in Monte Carlo-based dose calculations of the lung.

We have applied convolution methods to account for some of the effects of respiratory induced motion in clinical treatment planning of the lung. The 3-D displacement of the GTV center-of-mass (COM) as determined from breath-hold exhale and inhale CT scans was used to approximate the breathing induced motion. The time-course of the GTV-COM was estimated using a probability distribution function (PDF) previously derived from diaphragmatic motion [Med.

Alterations in normal liver doses due to organ motion.

Purpose: To assess the clinical significance of differences between treatment planning calculations based on static computed tomography (CT) and more realistic predictions of the actual delivered dose to intrahepatic lesions by a geometric convolution approach that accounts for random setup variations and breathing-induced organ motion.

Materials And Methods: We recalculated target and normal liver doses for 40 patients previously treated on a conformal therapy dose escalation protocol to include the effect of setup uncertainties and liver motion due to patient breathing. Initial three-dimensional (3D) dose calculations based on pretreatment CT scans taken with voluntary breath-hold at normal exhalation were convolved with 3D anisotropic probability distribution functions reflecting population measurements of position setup variation.

A fluence convolution method to account for respiratory motion in three-dimensional dose calculations of the liver: a Monte Carlo study.

We describe the implementation of a fluence convolution method to account for the influence of superior-inferior (SI) respiratory induced motion on a Monte Carlo-based dose calculation of a tumor located in the liver. This method involves convolving the static fluence map with a function describing the SI motion of the liver-the motion function has been previously derived from measurements of diaphragm movement observed under fluoroscopy. Significant differences are noted between fluence-convolved and static dose distributions in an example clinical treatment plan; hot and cold spots (on the order of 25%) are observed in the fluence-convolved plan at the superior and inferior borders of the liver, respectively.