Knowledge-based planning for Gamma Knife.

BACKGROUND: Current methods for Gamma Knife (GK) treatment planning utilizes either manual forward planning, where planners manually place shots in a tumor to achieve a desired dose distribution, or inverse planning, whereby the dose delivered to a tumor is optimized for multiple objectives based on established metrics. For other treatment modalities like IMRT and VMAT, there has been a recent push to develop knowledge-based planning (KBP) pipelines to address the limitations presented by forward and inverse planning. However, no complete KBP pipeline has been created for GK. PURPOSE: To develop a novel (KBP) pipeline, using inverse optimization (IO) with 3D dose predictions for GK. METHODS: Data were obtained for 349 patients from Sunnybrook Health Sciences Centre. A 3D dose prediction model was trained using 322 patients, based on a previously published deep learning methodology, and dose predictions were generated for the remaining 27 out-of-sample patients. A generalized IO model was developed to learn objective function weights from dose predictions. These weights were then used in an inverse planning model to generate deliverable treatment plans. A dose mimicking (DM) model was also implemented for comparison. The quality of the resulting plans was compared to their clinical counterparts using standard GK quality metrics. The performance of the models was also characterized with respect to the dose predictions. RESULTS: Across all quality metrics, plans generated using the IO pipeline performed at least as well as or better than the respective clinical plans. The average conformity and gradient indices of IO plans was 0.737 ± $\pm$ 0.158 and 3.356 ± $\pm$ 1.030 respectively, compared to 0.713 ± $\pm$ 0.124 and 3.452 ± $\pm$ 1.123 for the clinical plans. IO plans also performed better than DM plans for five of the six quality metrics. Plans generated using IO also have average treatment times comparable to that of clinical plans. With regards to the dose predictions, predictions with higher conformity tend to result in higher quality KBP plans. CONCLUSIONS: Plans resulting from an IO KBP pipeline are, on average, of equal or superior quality compared to those obtained through manual planning. The results demonstrate the potential for the use of KBP to generate GK treatment with minimal human intervention.

3D dose prediction for Gamma Knife radiosurgery using deep learning and data modification.

PURPOSE: To develop a machine learning-based, 3D dose prediction methodology for Gamma Knife (GK) radiosurgery. The methodology accounts for cases involving targets of any number, size, and shape. METHODS: Data from 322 GK treatment plans was modified by isolating and cropping the contoured MRI and clinical dose distributions based on tumor location, then scaling the resulting tumor spaces to a standard size. An accompanying 3D tensor was created for each instance to account for tumor size. The modified dataset for 272 patients was used to train both a generative adversarial network (GAN-GK) and a 3D U-Net model (U-Net-GK). Unmodified data was used to train equivalent baseline models. All models were used to predict the dose distribution of 50 out-of-sample patients. Prediction accuracy was evaluated using gamma, with criteria of 4 %/2mm, 3 %/3mm, 3 %/1mm and 1 %/1mm. Prediction quality was assessed using coverage, selectivity, and conformity indices. RESULTS: The predictions resulting from GAN-GK and U-Net-GK were similar to their clinical counterparts, with average gamma (4 %/2mm) passing rates of 84.9 ± 15.3 % and 83.1 ± 17.2 %, respectively. In contrast, the gamma passing rate of baseline models were significantly worse than their respective GK-specific models (p < 0.001) at all criterion levels. The quality of GK-specific predictions was also similar to that of clinical plans. CONCLUSION: Deep learning models can use GK-specific data modification to predict 3D dose distributions for GKRS plans with a large range in size, shape, or number of targets. Standard deep learning models applied to unmodified GK data generated poorer predictions.

Inverse optimization on hierarchical networks: an application to breast cancer clinical pathways.

Clinical pathways are standardized processes that outline the steps required for managing a specific disease. However, patient pathways often deviate from clinical pathways. Measuring the concordance of patient pathways to clinical pathways is important for health system monitoring and informing quality improvement initiatives. In this paper, we develop an inverse optimization-based approach to measuring pathway concordance in breast cancer, a complex disease. We capture this complexity in a hierarchical network that models the patient's journey through the health system. A novel inverse shortest path model is formulated and solved on this hierarchical network to estimate arc costs, which are used to form a concordance metric to measure the distance between patient pathways and shortest paths (i.e., clinical pathways). Using real breast cancer patient data from Ontario, Canada, we demonstrate that our concordance metric has a statistically significant association with survival for all breast cancer patient subgroups. We also use it to quantify the extent of patient pathway discordances across all subgroups, finding that patients undertaking additional clinical activities constitute the primary driver of discordance in the population.

OpenKBP: The open-access knowledge-based planning grand challenge and dataset.

PURPOSE: To advance fair and consistent comparisons of dose prediction methods for knowledge-based planning (KBP) in radiation therapy research. METHODS: We hosted OpenKBP, a 2020 AAPM Grand Challenge, and challenged participants to develop the best method for predicting the dose of contoured computed tomography (CT) images. The models were evaluated according to two separate scores: (a) dose score, which evaluates the full three-dimensional (3D) dose distributions, and (b) dose-volume histogram (DVH) score, which evaluates a set DVH metrics. We used these scores to quantify the quality of the models based on their out-of-sample predictions. To develop and test their models, participants were given the data of 340 patients who were treated for head-and-neck cancer with radiation therapy. The data were partitioned into training ( n = 200 ), validation ( n = 40 ), and testing ( n = 100 ) datasets. All participants performed training and validation with the corresponding datasets during the first (validation) phase of the Challenge. In the second (testing) phase, the participants used their model on the testing data to quantify the out-of-sample performance, which was hidden from participants and used to determine the final competition ranking. Participants also responded to a survey to summarize their models. RESULTS: The Challenge attracted 195 participants from 28 countries, and 73 of those participants formed 44 teams in the validation phase, which received a total of 1750 submissions. The testing phase garnered submissions from 28 of those teams, which represents 28 unique prediction methods. On average, over the course of the validation phase, participants improved the dose and DVH scores of their models by a factor of 2.7 and 5.7, respectively. In the testing phase one model achieved the best dose score (2.429) and DVH score (1.478), which were both significantly better than the dose score (2.564) and the DVH score (1.529) that was achieved by the runner-up models. Lastly, many of the top performing teams reported that they used generalizable techniques (e.g., ensembles) to achieve higher performance than their competition. CONCLUSION: OpenKBP is the first competition for knowledge-based planning research. The Challenge helped launch the first platform that enables researchers to compare KBP prediction methods fairly and consistently using a large open-source dataset and standardized metrics. OpenKBP has also democratized KBP research by making it accessible to everyone, which should help accelerate the progress of KBP research. The OpenKBP datasets are available publicly to help benchmark future KBP research.

Peripheral inflammatory biomarkers define biotypes of bipolar depression.

We identified biologically relevant moderators of response to tumor necrosis factor (TNF)-α inhibitor, infliximab, among 60 individuals with bipolar depression. Data were derived from a 12-week, randomized, placebo-controlled clinical trial secondarily evaluating the efficacy of infliximab on a measure of anhedonia (i.e., Snaith-Hamilton Pleasure Scale). Three inflammatory biotypes were derived from peripheral cytokine measurements using an iterative, machine learning-based approach. Infliximab-randomized participants classified as biotype 3 exhibited lower baseline concentrations of pro- and anti-inflammatory cytokines and soluble TNF receptor-1 and reported greater pro-hedonic improvements, relative to those classified as biotype 1 or 2. Pretreatment biotypes also moderated changes in neuroinflammatory substrates relevant to infliximab's hypothesized mechanism of action. Neuronal origin-enriched extracellular vesicle (NEV) protein concentrations were reduced to two factors using principal axis factoring: phosphorylated nuclear factorκB (p-NFκB), Fas-associated death domain (p-FADD), and IκB kinase (p-IKKα/ß) and TNF receptor-1 (TNFR1) comprised factor "NEV1," whereas phosphorylated insulin receptor substrate-1 (p-IRS1), p38 mitogen-activated protein kinase (p-p38), and c-Jun N-terminal kinase (p-JNK) constituted "NEV2". Among infliximab-randomized subjects classified as biotype 3, NEV1 scores were decreased at weeks 2 and 6 and increased at week 12, relative to baseline, and NEV2 scores increased over time. Decreases in NEV1 scores and increases in NEV2 scores were associated with greater reductions in anhedonic symptoms in our classification and regression tree model (r2 = 0.22, RMSE = 0.08). Our findings provide preliminary evidence supporting the hypothesis that the pro-hedonic effects of infliximab require modulation of multiple TNF-α signaling pathways, including NF-κB, IRS1, and MAPK.

Predicting Postoperative Cochlear Implant Performance Using Supervised Machine Learning.

OBJECTIVES: To predict postoperative cochlear implant performance with heterogeneous text and numerical variables using supervised machine learning techniques. STUDY DESIGN: A supervised machine learning approach comprising neural networks and decision tree-based ensemble algorithms were used to predict 1-year postoperative cochlear implant performance based on retrospective data. SETTING: Tertiary referral center. PATIENTS: One thousand six hundred four adults who received one cochlear implant from 1989 to 2019. Two hundred eighty two text and numerical objective demographic, audiometric, and patient-reported outcome survey instrument variables were included. OUTCOME MEASURES: Outcomes for postoperative cochlear implant performance were discrete Hearing in Noise Test (HINT; %) performance and binned HINT performance classification ("High," "Mid," and "Low" performers). Algorithm performance was assessed using hold-out validation datasets and were compared using root mean square error (RMSE) in the units of the target variable and classification accuracy. RESULTS: The neural network 1-year HINT prediction RMSE and classification accuracy were 0.57 and 95.4%, respectively, with only numerical variable inputs. Using both text and numerical variables, neural networks predicted postoperative HINT with a RMSE of 25.0%, and classification accuracy of 73.3%. When applied to numerical variables only, the XGBoost algorithm produced a 1-year HINT score prediction performance RMSE of 25.3%. We identified over 20 influential variables including preoperative sentence-test performance, age at surgery, as well as specific tinnitus handicap inventory (THI), Short Form 36 (SF-36), and health utilities index (HUI) question responses as the highest influencers of postoperative HINT. CONCLUSION: Our results suggest that supervised machine learning can predict postoperative cochlear implant performance and identify preoperative factors that significantly influence that performance. These algorithms can help improve the understanding of the diverse factors that impact functional performance from heterogeneous data sources.

The importance of evaluating the complete automated knowledge-based planning pipeline.

We determine how prediction methods combine with optimization methods in two-stage knowledge-based planning (KBP) pipelines to produce radiation therapy treatment plans. We trained two dose prediction methods, a generative adversarial network (GAN) and a random forest (RF) with the same 130 treatment plans. The models were applied to 87 out-of-sample patients to create two sets of predicted dose distributions that were used as input to two optimization models. The first optimization model, inverse planning (IP), estimates weights for dose-objectives from a predicted dose distribution and generates new plans using conventional inverse planning. The second optimization model, dose mimicking (DM), minimizes the sum of one-sided quadratic penalties between the predictions and the generated plans using several dose-objectives. Altogether, four KBP pipelines (GAN-IP, GAN-DM, RF-IP, and RF-DM) were constructed and benchmarked against the corresponding clinical plans using clinical criteria; the error of both prediction methods was also evaluated. The best performing plans were GAN-IP plans, which satisfied the same criteria as their corresponding clinical plans (78%) more often than any other KBP pipeline. However, GAN did not necessarily provide the best prediction for the second-stage optimization models. Specifically, both the RF-IP and RF-DM plans satisfied the same criteria as the clinical plans 25% and 15% more often than GAN-DM plans (the worst performing plans), respectively. GAN predictions also had a higher mean absolute error (3.9 Gy) than those from RF (3.6 Gy). We find that state-of-the-art prediction methods when paired with different optimization algorithms, produce treatment plans with considerable variation in quality.

A contemporary review of machine learning in otolaryngology-head and neck surgery.

One of the key challenges with big data is leveraging the complex network of information to yield useful clinical insights. The confluence of massive amounts of health data and a desire to make inferences and insights on these data has produced a substantial amount of interest in machine-learning analytic methods. There has been a drastic increase in the otolaryngology literature volume describing novel applications of machine learning within the past 5 years. In this timely contemporary review, we provide an overview of popular machine-learning techniques, and review recent machine-learning applications in otolaryngology-head and neck surgery including neurotology, head and neck oncology, laryngology, and rhinology. Investigators have realized significant success in validated models with model sensitivities and specificities approaching 100%. Challenges remain in the implementation of machine-learning algorithms. This may be in part the unfamiliarity of these techniques to clinician leaders on the front lines of patient care. Spreading awareness and confidence in machine learning will follow with further validation and proof-of-value analyses that demonstrate model performance superiority over established methods. We are poised to see a greater influx of machine-learning applications to clinical problems in otolaryngology-head and neck surgery, and it is prudent for providers to understand the potential benefits and limitations of these technologies. Laryngoscope, 130:45-51, 2020.

Knowledge-based automated planning with three-dimensional generative adversarial networks.

PURPOSE: To develop a knowledge-based automated planning pipeline that generates treatment plans without feature engineering, using deep neural network architectures for predicting three-dimensional (3D) dose. METHODS: Our knowledge-based automated planning (KBAP) pipeline consisted of a knowledge-based planning (KBP) method that predicts dose for a contoured computed tomography (CT) image followed by two optimization models that learn objective function weights and generate fluence-based plans, respectively. We developed a novel generative adversarial network (GAN)-based KBP approach, a 3D GAN model, which predicts dose for the full 3D CT image at once and accounts for correlations between adjacent CT slices. Baseline comparisons were made against two state-of-the-art deep learning-based KBP methods from the literature. We also developed an additional benchmark, a two-dimensional (2D) GAN model which predicts dose to each axial slice independently. For all models, we investigated the impact of multiplicatively scaling the predictions before optimization, such that the predicted dose distributions achieved all target clinical criteria. Each KBP model was trained on 130 previously delivered oropharyngeal treatment plans. Performance was tested on 87 out-of-sample previously delivered treatment plans. All KBAP plans were evaluated using clinical planning criteria and compared to their corresponding clinical plans. KBP prediction quality was assessed using dose-volume histogram (DVH) differences from the corresponding clinical plans. RESULTS: The best performing KBAP plans were generated using predictions from the 3D GAN model that were multiplicatively scaled. These plans satisfied 77% of all clinical criteria, compared to the clinical plans, which satisfied 67% of all criteria. In general, multiplicatively scaling predictions prior to optimization increased the fraction of clinical criteria satisfaction by 11% relative to the plans generated with nonscaled predictions. Additionally, these KBAP plans satisfied the same criteria as the clinical plans 84% and 8% more frequently as compared to the two benchmark methods, respectively. CONCLUSIONS: We developed the first knowledge-based automated planning framework using a 3D generative adversarial network for prediction. Our results, based on 217 oropharyngeal cancer treatment plans, demonstrated superior performance in satisfying clinical criteria and generated more realistic plans as compared to the previous state-of-the-art approaches.

Machine Learning and Cochlear Implantation-A Structured Review of Opportunities and Challenges.

OBJECTIVE: The use of machine learning technology to automate intellectual processes and boost clinical process efficiency in medicine has exploded in the past 5 years. Machine learning excels in automating pattern recognition and in adapting learned representations to new settings. Moreover, machine learning techniques have the advantage of incorporating complexity and are free from many of the limitations of traditional deterministic approaches. Cochlear implants (CI) are a unique fit for machine learning techniques given the need for optimization of signal processing to fit complex environmental scenarios and individual patients' CI MAPping. However, there are many other opportunities where machine learning may assist in CI beyond signal processing. The objective of this review was to synthesize past applications of machine learning technologies for pediatric and adult CI and describe novel opportunities for research and development. DATA SOURCES: The PubMed/MEDLINE, EMBASE, Scopus, and ISI Web of Knowledge databases were mined using a directed search strategy to identify the nexus between CI and artificial intelligence/machine learning literature. STUDY SELECTION: Non-English language articles, articles without an available abstract or full-text, and nonrelevant articles were manually appraised and excluded. Included articles were evaluated for specific machine learning methodologies, content, and application success. DATA SYNTHESIS: The database search identified 298 articles. Two hundred fifty-nine articles (86.9%) were excluded based on the available abstract/full-text, language, and relevance. The remaining 39 articles were included in the review analysis. There was a marked increase in year-over-year publications from 2013 to 2018. Applications of machine learning technologies involved speech/signal processing optimization (17; 43.6% of articles), automated evoked potential measurement (6; 15.4%), postoperative performance/efficacy prediction (5; 12.8%), and surgical anatomy location prediction (3; 7.7%), and 2 (5.1%) in each of robotics, electrode placement performance, and biomaterials performance. CONCLUSION: The relationship between CI and artificial intelligence is strengthening with a recent increase in publications reporting successful applications. Considerable effort has been directed toward augmenting signal processing and automating postoperative MAPping using machine learning algorithms. Other promising applications include augmenting CI surgery mechanics and personalized medicine approaches for boosting CI patient performance. Future opportunities include addressing scalability and the research and clinical communities' acceptance of machine learning algorithms as effective techniques.

Robust radiotherapy planning.

Motion and uncertainty in radiotherapy is traditionally handled via margins. The clinical target volume (CTV) is expanded to a larger planning target volume (PTV), which is irradiated to the prescribed dose. However, the PTV concept has several limitations, especially in proton therapy. Therefore, robust and probabilistic optimization methods have been developed that directly incorporate motion and uncertainty into treatment plan optimization for intensity modulated radiotherapy (IMRT) and intensity modulated proton therapy (IMPT). Thereby, the explicit definition of a PTV becomes obsolete and treatment plan optimization is directly based on the CTV. Initial work focused on random and systematic setup errors in IMRT. Later, inter-fraction prostate motion and intra-fraction lung motion became a research focus. Over the past ten years, IMPT has emerged as a new application for robust planning methods. In proton therapy, range or setup errors may lead to dose degradation and misalignment of dose contributions from different beams - a problem that cannot generally be addressed by margins. Therefore, IMPT has led to the first implementations of robust planning methods in commercial planning systems, making these methods available for clinical use. This paper first summarizes the limitations of the PTV concept. Subsequently, robust optimization methods are introduced and their applications in IMRT and IMPT planning are reviewed.

A small number of objective function weight vectors is sufficient for automated treatment planning in prostate cancer.

Current practice for treatment planning optimization can be both inefficient and time consuming. In this paper, we propose an automated planning methodology that aims to combine both explorative and prescriptive approaches for improving the efficiency and the quality of the treatment planning process. Given a treatment plan, our explorative approach explores trade-offs between different objectives and finds an acceptable region for objective function weights via inverse optimization. Intuitively, the shape and size of these regions describe how 'sensitive' a patient is to perturbations in objective function weights. We then develop an integer programming-based prescriptive approach that exploits the information encoded by these regions to find a set of five representative objective function weight vectors such that for each patient there exists at least one representative weight vector that can produce a high quality treatment plan. Using 315 patients from Princess Margaret Cancer Centre, we show that the produced treatment plans are comparable and, for [Formula: see text] of cases, improve upon the inversely optimized plans that are generated from the historical clinical treatment plans.

Knowledge-based automated planning for oropharyngeal cancer.

PURPOSE: The purpose of this study was to automatically generate radiation therapy plans for oropharynx patients by combining knowledge-based planning (KBP) predictions with an inverse optimization (IO) pipeline. METHODS: We developed two KBP approaches, the bagging query (BQ) method and the generalized principal component analysis-based (gPCA) method, to predict achievable dose-volume histograms (DVHs). These approaches generalize existing methods by predicting physically feasible organ-at-risk (OAR) and target DVHs in sites with multiple targets. Using leave-one-out cross validation, we applied both models to a large dataset of 217 oropharynx patients. The predicted DVHs were input into an IO pipeline that generated treatment plans (BQ and gPCA plans) via an intermediate step that estimated objective function weights for an inverse planning model. The KBP predictions were compared to the clinical DVHs for benchmarking. To assess the complete pipeline, we compared the BQ and gPCA plans to both the predictions and clinical plans. To isolate the effect of the KBP predictions, we put clinical DVHs through the IO pipeline to produce clinical inverse optimized (CIO) plans. This approach also allowed us to estimate the complexity of the clinical plans. The BQ and gPCA plans were benchmarked against the CIO plans using DVH differences and clinical planning criteria. Iso-complexity plans (relative to CIO) were also generated and evaluated. RESULTS: The BQ method tended to predict that less dose is delivered than what was observed in the clinical plans while the gPCA predictions were more similar to clinical DVHs. Both populations of KBP predictions were reproduced with inverse plans to within a median DVH difference of 3 Gy. Clinical planning criteria for OARs were satisfied most frequently by the BQ plans (74.4%), by 6.3% points more than the clinical plans. Meanwhile, target criteria were satisfied most frequently by the gPCA plans (90.2%), and by 21.2% points more than clinical plans. However, once the complexity of the plans was constrained to that of the CIO plans, the performance of the BQ plans degraded significantly. In contrast, the gPCA plans still satisfied more clinical criteria than both the clinical and CIO plans, with the most notable improvement being in target criteria. CONCLUSION: Our automated pipeline can successfully use DVH predictions to generate high-quality plans without human intervention. Between the two KBP methods, gPCA plans tend to achieve comparable performance as clinical plans, even when controlling for plan complexity, whereas BQ plans tended to underperform.

Inverse optimization of objective function weights for treatment planning using clinical dose-volume histograms.

We developed and evaluated a novel inverse optimization (IO) model to estimate objective function weights from clinical dose-volume histograms (DVHs). These weights were used to solve a treatment planning problem to generate 'inverse plans' that had similar DVHs to the original clinical DVHs. Our methodology was applied to 217 clinical head and neck cancer treatment plans that were previously delivered at Princess Margaret Cancer Centre in Canada. Inverse plan DVHs were compared to the clinical DVHs using objective function values, dose-volume differences, and frequency of clinical planning criteria satisfaction. Median differences between the clinical and inverse DVHs were within 1.1 Gy. For most structures, the difference in clinical planning criteria satisfaction between the clinical and inverse plans was at most 1.4%. For structures where the two plans differed by more than 1.4% in planning criteria satisfaction, the difference in average criterion violation was less than 0.5 Gy. Overall, the inverse plans were very similar to the clinical plans. Compared with a previous inverse optimization method from the literature, our new inverse plans typically satisfied the same or more clinical criteria, and had consistently lower fluence heterogeneity. Overall, this paper demonstrates that DVHs, which are essentially summary statistics, provide sufficient information to estimate objective function weights that result in high quality treatment plans. However, as with any summary statistic that compresses three-dimensional dose information, care must be taken to avoid generating plans with undesirable features such as hotspots; our computational results suggest that such undesirable spatial features were uncommon. Our IO-based approach can be integrated into the current clinical planning paradigm to better initialize the planning process and improve planning efficiency. It could also be embedded in a knowledge-based planning or adaptive radiation therapy framework to automatically generate a new plan given a predicted or updated target DVH, respectively.

Sample size requirements for knowledge-based treatment planning.

PURPOSE: To determine how training set size affects the accuracy of knowledge-based treatment planning (KBP) models. METHODS: The authors selected four models from three classes of KBP approaches, corresponding to three distinct quantities that KBP models may predict: dose-volume histogram (DVH) points, DVH curves, and objective function weights. DVH point prediction is done using the best plan from a database of similar clinical plans; DVH curve prediction employs principal component analysis and multiple linear regression; and objective function weights uses either logistic regression or K-nearest neighbors. The authors trained each KBP model using training sets of sizes n = 10, 20, 30, 50, 75, 100, 150, and 200. The authors set aside 100 randomly selected patients from their cohort of 315 prostate cancer patients from Princess Margaret Cancer Center to serve as a validation set for all experiments. For each value of n, the authors randomly selected 100 different training sets with replacement from the remaining 215 patients. Each of the 100 training sets was used to train a model for each value of n and for each KBT approach. To evaluate the models, the authors predicted the KBP endpoints for each of the 100 patients in the validation set. To estimate the minimum required sample size, the authors used statistical testing to determine if the median error for each sample size from 10 to 150 is equal to the median error for the maximum sample size of 200. RESULTS: The minimum required sample size was different for each model. The DVH point prediction method predicts two dose metrics for the bladder and two for the rectum. The authors found that more than 200 samples were required to achieve consistent model predictions for all four metrics. For DVH curve prediction, the authors found that at least 75 samples were needed to accurately predict the bladder DVH, while only 20 samples were needed to predict the rectum DVH. Finally, for objective function weight prediction, at least 10 samples were needed to train the logistic regression model, while at least 150 samples were required to train the K-nearest neighbor methodology. CONCLUSIONS: In conclusion, the minimum required sample size needed to accurately train KBP models for prostate cancer depends on the specific model and endpoint to be predicted. The authors' results may provide a lower bound for more complicated tumor sites.

The value of nodal information in predicting lung cancer relapse using 4DPET/4DCT.

PURPOSE: There is evidence that computed tomography (CT) and positron emission tomography (PET) imaging metrics are prognostic and predictive in nonsmall cell lung cancer (NSCLC) treatment outcomes. However, few studies have explored the use of standardized uptake value (SUV)-based image features of nodal regions as predictive features. The authors investigated and compared the use of tumor and node image features extracted from the radiotherapy target volumes to predict relapse in a cohort of NSCLC patients undergoing chemoradiation treatment. METHODS: A prospective cohort of 25 patients with locally advanced NSCLC underwent 4DPET/4DCT imaging for radiation planning. Thirty-seven image features were derived from the CT-defined volumes and SUVs of the PET image from both the tumor and nodal target regions. The machine learning methods of logistic regression and repeated stratified five-fold cross-validation (CV) were used to predict local and overall relapses in 2 yr. The authors used well-known feature selection methods (Spearman's rank correlation, recursive feature elimination) within each fold of CV. Classifiers were ranked on their Matthew's correlation coefficient (MCC) after CV. Area under the curve, sensitivity, and specificity values are also presented. RESULTS: For predicting local relapse, the best classifier found had a mean MCC of 0.07 and was composed of eight tumor features. For predicting overall relapse, the best classifier found had a mean MCC of 0.29 and was composed of a single feature: the volume greater than 0.5 times the maximum SUV (N). CONCLUSIONS: The best classifier for predicting local relapse had only tumor features. In contrast, the best classifier for predicting overall relapse included a node feature. Overall, the methods showed that nodes add value in predicting overall relapse but not local relapse.

The perils of adapting to dose errors in radiation therapy.

We consider adaptive robust methods for lung cancer that are also dose-reactive, wherein the treatment is modified after each treatment session to account for the dose delivered in prior treatment sessions. Such methods are of interest because they potentially allow for errors in the delivered dose to be corrected as the treatment progresses, thereby ensuring that the tumor receives a sufficient dose at the end of the treatment. We show through a computational study with real lung cancer patient data that while dose reaction is beneficial with respect to the final dose distribution, it may lead to exaggerated daily underdose and overdose relative to non-reactive methods that grows as the treatment progresses. However, by combining dose reaction with a mechanism for updating an estimate of the uncertainty, the magnitude of this growth can be mitigated substantially. The key finding of this paper is that reacting to dose errors - an adaptation strategy that is both simple and intuitively appealing - may backfire and lead to treatments that are clinically unacceptable.

Robust optimization methods for cardiac sparing in tangential breast IMRT.

PURPOSE: In left-sided tangential breast intensity modulated radiation therapy (IMRT), the heart may enter the radiation field and receive excessive radiation while the patient is breathing. The patient's breathing pattern is often irregular and unpredictable. We verify the clinical applicability of a heart-sparing robust optimization approach for breast IMRT. We compare robust optimized plans with clinical plans at free-breathing and clinical plans at deep inspiration breath-hold (DIBH) using active breathing control (ABC). METHODS: Eight patients were included in the study with each patient simulated using 4D-CT. The 4D-CT image acquisition generated ten breathing phase datasets. An average scan was constructed using all the phase datasets. Two of the eight patients were also imaged at breath-hold using ABC. The 4D-CT datasets were used to calculate the accumulated dose for robust optimized and clinical plans based on deformable registration. We generated a set of simulated breathing probability mass functions, which represent the fraction of time patients spend in different breathing phases. The robust optimization method was applied to each patient using a set of dose-influence matrices extracted from the 4D-CT data and a model of the breathing motion uncertainty. The goal of the optimization models was to minimize the dose to the heart while ensuring dose constraints on the target were achieved under breathing motion uncertainty. RESULTS: Robust optimized plans were improved or equivalent to the clinical plans in terms of heart sparing for all patients studied. The robust method reduced the accumulated heart dose (D10cc) by up to 801 cGy compared to the clinical method while also improving the coverage of the accumulated whole breast target volume. On average, the robust method reduced the heart dose (D10cc) by 364 cGy and improved the optBreast dose (D99%) by 477 cGy. In addition, the robust method had smaller deviations from the planned dose to the accumulated dose. The deviation of the accumulated dose from the planned dose for the optBreast (D99%) was 12 cGy for robust versus 445 cGy for clinical. The deviation for the heart (D10cc) was 41 cGy for robust and 320 cGy for clinical. CONCLUSIONS: The robust optimization approach can reduce heart dose compared to the clinical method at free-breathing and can potentially reduce the need for breath-hold techniques.

Adaptive and robust radiation therapy in the presence of drift.

Combining adaptive and robust optimization in radiation therapy has the potential to mitigate the negative effects of both intrafraction and interfraction uncertainty over a fractionated treatment course. A previously developed adaptive and robust radiation therapy (ARRT) method for lung cancer was demonstrated to be effective when the sequence of breathing patterns was well-behaved. In this paper, we examine the applicability of the ARRT method to less well-behaved breathing patterns. We develop a novel method to generate sequences of probability mass functions that represent different types of drift in the underlying breathing pattern. Computational results derived from applying the ARRT method to these sequences demonstrate that the ARRT method is effective for a much broader class of breathing patterns than previously demonstrated.