Embedding machine learning based toxicity models within radiotherapy treatment plan optimization.

Objective.This study addresses radiation-induced toxicity (RIT) challenges in radiotherapy (RT) by developing a personalized treatment planning framework. It leverages patient-specific data and dosimetric information to create an optimization model that limits adverse side effects using constraints learned from historical data.Approach.The study uses the optimization with constraint learning (OCL) framework, incorporating patient-specific factors into the optimization process. It consists of three steps: optimizing the baseline treatment plan using population-wide dosimetric constraints; training a machine learning (ML) model to estimate the patient's RIT for the baseline plan; and adapting the treatment plan to minimize RIT using ML-learned patient-specific constraints. Various predictive models, including classification trees, ensembles of trees, and neural networks, are applied to predict the probability of grade 2+ radiation pneumonitis (RP2+) for non-small cell lung (NSCLC) cancer patients three months post-RT. The methodology is assessed with four high RP2+ risk NSCLC patients, with the goal of optimizing the dose distribution to constrain the RP2+ outcome below a pre-specified threshold. Conventional and OCL-enhanced plans are compared based on dosimetric parameters and predicted RP2+ risk. Sensitivity analysis on risk thresholds and data uncertainty is performed using a toy NSCLC case.Main results.Experiments show the methodology's capacity to directly incorporate all predictive models into RT treatment planning. In the four patients studied, mean lung dose and V20 were reduced by an average of 1.78 Gy and 3.66%, resulting in an average RP2+ risk reduction from 95% to 42%. Notably, this reduction maintains tumor coverage, although in two cases, sparing the lung slightly increased spinal cord max-dose (0.23 and 0.79 Gy).Significance.By integrating patient-specific information into learned constraints, the study significantly reduces adverse side effects like RP2+ without compromising target coverage. This unified framework bridges the gap between predicting toxicities and optimizing treatment plans in personalized RT decision-making.

Computer Simulation to Assess Emergency Department Length of Stay in Pediatric Traumatic Brain Injury.

OBJECTIVES: Our study aimed to identify how emergency department (ED) arrival rate, process of care, and physical layout can impact ED length of stay (LOS) in pediatric traumatic brain injury care. METHODS: Process flows and value stream maps were developed for 3 level I pediatric trauma centers. Computer simulation models were also used to examine "what if" scenarios based on ED arrival rates. RESULTS: Differences were observed in prearrival preparation time, ED physical layouts, and time spent on processes. Shorter prearrival preparation time, trauma bed location far from diagnostic or treatment areas, and ED arrival rates that exceed 20 patients/day prolonged ED LOS. This was particularly apparent in 1 center where computer simulation showed that relocation of trauma beds can reduce ED LOS regardless of the number of patients that arrive per day. CONCLUSIONS: Exceeding certain threshold ED arrival rates of children with traumatic brain injury can substantially increase pediatric trauma center ED LOS but modifications to ED processes and bed location may mitigate this increase.

The influence of anisotropy on the clinical target volume of brain tumor patients.

Objective.Current radiotherapy guidelines for glioma target volume definition recommend a uniform margin expansion from the gross tumor volume (GTV) to the clinical target volume (CTV), assuming uniform infiltration in the invaded brain tissue. However, glioma cells migrate preferentially along white matter tracts, suggesting that white matter directionality should be considered in an anisotropic CTV expansion. We investigate two models of anisotropic CTV expansion and evaluate their clinical feasibility.Approach.To incorporate white matter directionality into the CTV, a diffusion tensor imaging (DTI) atlas is used. The DTI atlas consists of water diffusion tensors that are first spatially transformed into local tumor resistance tensors, also known as metric tensors, and secondly fed to a CTV expansion algorithm to generate anisotropic CTVs. Two models of spatial transformation are considered in the first step. The first model assumes that tumor cells experience reduced resistance parallel to the white matter fibers. The second model assumes that the anisotropy of tumor cell resistance is proportional to the anisotropy observed in DTI, with an 'anisotropy weighting parameter' controlling the proportionality. The models are evaluated in a cohort of ten brain tumor patients.Main results.To evaluate the sensitivity of the model, a library of model-generated CTVs was computed by varying the resistance and anisotropy parameters. Our results indicate that the resistance coefficient had the most significant effect on the global shape of the CTV expansion by redistributing the target volume from potentially less involved gray matter to white matter tissue. In addition, the anisotropy weighting parameter proved useful in locally increasing CTV expansion in regions characterized by strong tissue directionality, such as near the corpus callosum.Significance.By incorporating anisotropy into the CTV expansion, this study is a step toward an interactive CTV definition that can assist physicians in incorporating neuroanatomy into a clinically optimized CTV.

Online adaptive planning methods for intensity-modulated radiotherapy.

Online adaptive radiation therapy aims at adapting a patient's treatment plan to their current anatomy to account for inter-fraction variations before daily treatment delivery. As this process needs to be accomplished while the patient is immobilized on the treatment couch, it requires time-efficient adaptive planning methods to generate a quality daily treatment plan rapidly. The conventional planning methods do not meet the time requirement of online adaptive radiation therapy because they often involve excessive human intervention, significantly prolonging the planning phase. This article reviews the planning strategies employed by current commercial online adaptive radiation therapy systems, research on online adaptive planning, and artificial intelligence's potential application to online adaptive planning.

Exploring trade-offs in treatment planning for brain tumor cases with a probabilistic definition of the clinical target volume.

PURPOSE: This study demonstrates how a novel probabilistic clinical target volume (CTV) concept-the clinical target distribution (CTD)-can be used to navigate the trade-off between target coverage and organ sparing with a semi-interactive treatment planning approach. METHODS: Two probabilistic treatment planning methods are presented that use tumor probabilities to balance tumor control with organ-at-risk (OAR) sparing. The first method explores OAR dose reduction by systematically discarding x % $x\%$ of CTD voxels with an unfavorable dose-to-probability ratio from the minimum dose coverage objective. The second method sequentially expands the target volume from the GTV edge, calculating the CTD coverage versus OAR sparing trade-off after dosing each expansion. Each planning method leads to estimated levels of tumor control under specific statistical models of tumor infiltration: an independent tumor islets model and contiguous circumferential tumor growth model. The methods are illustrated by creating proton therapy treatment plans for two glioblastoma patients with the clinical goal of sparing the hippocampus and brainstem. For probabilistic plan evaluation, the concept of a dose-expected-volume histogram is introduced, which plots the dose to the expected tumor volume ⟨ v ⟩ $\langle v \rangle$ considering tumor probabilities. RESULTS: Both probabilistic planning approaches generate a library of treatment plans to interactively navigate the planning trade-offs. In the first probabilistic approach, a significant reduction of hippocampus dose could be achieved by excluding merely 1% of CTD voxels without compromising expected tumor control probability (TCP) or CTD coverage: the hippocampus D 2 % $D_{2\%}$ dose reduces with 9.5 and 5.3 Gy for Patient 1 and 2, while the TCP loss remains below 1%. Moreover, discarding up to 10% of the CTD voxels does not significantly diminish the expected CTD dose, even though evaluation with a binary volume suggests poor CTD coverage. In the second probabilistic approach, the expected CTD D ⟨ 98 % ⟩ $D_{\langle 98\%\rangle }$ and TCP depend more strongly on the extent of the high-dose region: the target volume margin cannot be reduced by more than 2 mm if one aims at keeping the expected CTD D ⟨ 98 % ⟩ $D_{\langle 98\%\rangle }$ loss and TCP loss under 1 Gy and 2%, respectively. Therefore, there is less potential for improved OAR sparing without compromising TCP or expected CTD coverage. CONCLUSIONS: This study proposes and implements treatment planning strategies to explore trade-offs using tumor probabilities.

Personalized mid-course FDG-PET based adaptive treatment planning for non-small cell lung cancer using machine learning and optimization.

Objective. Traditional radiotherapy (RT) treatment planning of non-small cell lung cancer (NSCLC) relies on population-wide estimates of organ tolerance to minimize excess toxicity. The goal of this study is to develop a personalized treatment planning based on patient-specific lung radiosensitivity, by combining machine learning and optimization.Approach. Sixty-nine non-small cell lung cancer patients with baseline and mid-treatment [18]F-fluorodeoxyglucose (FDG)-PET images were retrospectively analyzed. A probabilistic Bayesian networks (BN) model was developed to predict the risk of radiation pneumonitis (RP) at three months post-RT using pre- and mid-treatment FDG information. A patient-specific dose modifying factor (DMF), as a surrogate for lung radiosensitivity, was estimated to personalize the normal tissue toxicity probability (NTCP) model. This personalized NTCP was then integrated into a NTCP-based optimization model for RT adaptation, ensuring tumor coverage and respecting patient-specific lung radiosensitivity. The methodology was employed to adapt the treatment planning of fifteen NSCLC patients.Main results. The magnitude of the BN predicted risks corresponded with the RP severity. Average predicted risk for grade 1-4 RP were 0.18, 0.42, 0.63, and 0.76, respectively (p< 0.001). The proposed model yielded an average area under the receiver-operating characteristic curve (AUROC) of 0.84, outperforming the AUROCs of LKB-NTCP (0.77), and pre-treatment BN (0.79). Average DMF for the radio-tolerant (RP grade = 1) and radiosensitive (RP grade ≥ 2) groups were 0.8 and 1.63,p< 0.01. RT personalization resulted in five dose escalation strategies (average mean tumor dose increase = 6.47 Gy, range = [2.67-17.5]), and ten dose de-escalation (average mean lung dose reduction = 2.98 Gy [0.8-5.4]), corresponding to average NTCP reduction of 15% [4-27].Significance. Personalized FDG-PET-based mid-treatment adaptation of NSCLC RT could significantly lower the RP risk without compromising tumor control. The proposed methodology could help the design of personalized clinical trials for NSCLC patients.

Toward Personalized Radiation Therapy of Liver Metastasis: Importance of Serial Blood Biomarkers.

PURPOSE: To assess the added value of serial blood biomarkers in liver metastasis stereotactic body radiation therapy (SBRT). MATERIALS AND METHODS: Eighty-nine patients were retrospectively included. Pre- and midtreatment blood samples were analyzed for potential biomarkers of the treatment response. Three biomarker classes were studied: gene mutation status, complete blood count, and inflammatory cytokine concentration in plasma. One-year local failure (LF) and 2-year overall survival (OS) were chosen as study end points. Multivariate logistic regression was used for response prediction. Added predictive benefit was assessed by quantifying the difference between the predictive performance of a baseline model (clinicopathologic and dosimetric predictors) and that of the biomarker-enhanced model, using three metrics: (1) likelihood ratio, (2) predictive variance, and (3) area under the receiver operating characteristic curve (AUC). RESULTS: The most important predictors of LF were mutation in KRAS gene (hazard ratio [HR] = 2.92, 95% CI, [1.17 to 7.28], P = .02) and baseline and midtreatment concentration of plasma interleukin-6 (HR = 1.15 [1.04 to 1.26] and 1.06 [1.01 to 1.13], P = .01). Absolute lymphocyte count and platelet-to-lymphocyte ratio at baseline as well as neutrophil-to-lymphocyte ratio at baseline and before fraction 3 (HR = 1.33 [1.16 to 1.51] and 1.19 [1.09 to 1.30]) had the most significant association with OS (P = .0003). Addition of baseline GEN and inflammatory plasma cytokine biomarkers in predicting LF, respectively, increased AUC by 0.06 (from 0.73 to 0.79) and 0.07 (from 0.77 to 0.84). In predicting OS, inclusion of midtreatment complete blood count biomarkers increased AUC from 0.72 to 0.80, along with significant boosts in likelihood ratio and predictive variance. CONCLUSION: Inclusion of serial blood biomarkers leads to significant gain in predicting response to liver metastasis stereotactic body radiation therapy and can guide treatment personalization.

Perspectives on the model-based approach to proton therapy trials: A retrospective study of a lung cancer randomized trial.

PURPOSE: The goal of this study was to assess whether a model-based approach applied retrospectively to a completed randomized controlled trial (RCT) would have significantly altered the selection of patients of the original trial, using the same selection criteria and endpoint for testing the potential clinical benefit of protons compared to photons. METHODS AND MATERIALS: A model-based approach, based on three widely used normal tissue complication probability (NTCP) models for radiation pneumonitis (RP), was applied retrospectively to a completed non-small cell lung cancer RCT (NCT00915005). It was assumed that patients were selected by the model-based approach if their expected ΔNTCP value was above a threshold of 5%. The endpoint chosen matched that of the original trial, the first occurrence of severe (grade ≥3) RP. RESULTS: Our analysis demonstrates that NTCP differences between proton and photon therapy treatments may be too small to support a model-based trial approach for lung cancer using RP as the normal tissue endpoint. The analyzed lung trial showed that less than 19% (32/165) of patients enrolled in the completed trial would have been enrolled in a model-based trial, prescribing photon therapy to all other patients. The number of patients enrolled was also found to be dependent on the type of NTCP model used for evaluating RP, with the three models enrolling 3%, 13% or 19% of patients. This result does show limitations in NTCP models which would affect the success of a model-based trial approach. No conclusion regarding the development of RP in patients randomized by the model-based approach could statistically be made. CONCLUSIONS: Uncertainties in the outcome models to predict NTCP are the inherent drawback of a model-based approach to clinical trials. The impact of these uncertainties on enrollment in model-based trials depends on the predicted difference between the two treatment arms and on the set threshold for patient stratification. Our analysis demonstrates that NTCP differences between proton and photon therapy treatments may be too small to support a model-based trial approach for specific treatment sites, such as lung cancer, depending on the chosen normal tissue endpoint.

Towards optimal stopping in radiation therapy.

A typical fractionated radiotherapy (RT) course is a long and arduous process, demanding significant financial, physical, and mental commitments from patients. Each additional session of RT significantly increases the physical and psychological burden on patients and leads to higher radiation exposure in organs-at-risk (OAR), while, in some cases, the therapeutic benefits might not be high enough to justify the risks. Today, through technological advancements in molecular biology, imaging, and genetics more information is gathered about individual patient response before, during, and after the treatment. we highlight some of the ways that mathematical tools can help assess treatment efficacy on the fly, adapt the treatment plan based on individual biological response, and optimally stop the treatment, if necessary. We term this "Optimal Stopping in RT (OSRT)", after a similar concept in the fields of dynamic programming and Markov decision processes. In short, OSRT can dynamically determine "whether, when and how" to stop the treatment to improve therapeutic ratios.

Adaptive treatment-length optimization in spatiobiologically integrated radiotherapy.

Recent theoretical research on spatiobiologically integrated radiotherapy has focused on optimization models that adapt fluence-maps to the evolution of tumor state, for example, cell densities, as observed in quantitative functional images acquired over the treatment course. We propose an optimization model that adapts the length of the treatment course as well as the fluence-maps to such imaged tumor state. Specifically, after observing the tumor cell densities at the beginning of a session, the treatment planner solves a group of convex optimization problems to determine an optimal number of remaining treatment sessions, and a corresponding optimal fluence-map for each of these sessions. The objective is to minimize the total number of tumor cells remaining (TNTCR) at the end of this proposed treatment course, subject to upper limits on the biologically effective dose delivered to the organs-at-risk. This fluence-map is administered in future sessions until the next image is available, and then the number of sessions and the fluence-map are re-optimized based on the latest cell density information. We demonstrate via computer simulations on five head-and-neck test cases that such adaptive treatment-length and fluence-map planning reduces the TNTCR and increases the biological effect on the tumor while employing shorter treatment courses, as compared to only adapting fluence-maps and using a pre-determined treatment course length based on one-size-fits-all guidelines.

Simulation of the Emergency Department Care Process for Pediatric Traumatic Brain Injury.

The treatment of patients in the emergency department (ED) with severe pediatric traumatic brain injury (TBI) is challenging, and treatment process strategies that facilitate good outcomes are not well documented. The overall objective of this study was to identify factors that can affect the care process associated with pediatric TBI. This objective was achieved using a discrete-event simulation model of patients with TBI as they progress through the ED treatment process of a Level I trauma center. This model was used to identify areas where the ED length of stay can be reduced. The number of patients arriving at any given time was also varied in the simulation model to observe the impact to bed allocation policies and changes in staff and equipment. The findings showed that implementing changes in the ED (i.e., availability of two computerized tomography scanners, formation of resuscitation teams that included eight staff personnel, and modifying the bed allocation policy) could result in a 17% reduction in the mean ED length of stay. The study outcomes would be of interest to those (e.g., health administrators, health managers, and physicians) who can make decisions related to the treatment process in an ED.

Examining Emergency Department Treatment Processes in Severe Pediatric Traumatic Brain Injury.

BACKGROUND: In the treatment of pediatric traumatic brain injury (TBI), timely treatment of patients can affect the outcome. Our objectives were to examine the treatment process of acute pediatric TBI and the impact of non-value-added time (NVAT) on patient outcomes. METHODS: Data for 136 pediatric trauma patients (age < 18 years) with severe TBI from 2 trauma centers in the United States were collected. A process flow and value stream map identified NVATs and their sources in the treatment process. Cluster and regression analysis were used to examine the relationship between NVAT, as a percentage of the patient's length of stay (LOS), and the patient outcome, measured by their corresponding Glasgow outcome scale. RESULTS: There were 14 distinct sources of NVAT identified. A regression analysis showed that increased NVAT was associated with less favorable outcomes (relative ratio = 1.015, confidence interval = [1.002-1.029]). Specifically, 1% increase in the NVAT-to-LOS ratio was associated with a 1.5% increase in the chance of a less favorable outcome (i.e., death or vegetative state). CONCLUSION: The NVAT has a significant impact on the outcome of pediatric TBI, and every minute spent on performing non-value-added processes can lead to an increase in the likelihood of less favorable outcomes.