Framework for Radiation Oncology Department-wide Evaluation and Implementation of Commercial Artificial Intelligence Autocontouring.

PURPOSE: Artificial intelligence (AI)-based autocontouring in radiation oncology has potential benefits such as standardization and time savings. However, commercial AI solutions require careful evaluation before clinical integration. We developed a multidimensional evaluation method to test pretrained AI-based automated contouring solutions across a network of clinics. METHODS AND MATERIALS: Curated data included 121 patient planning computed tomography (CT) scans with a total of 859 clinically approved contours used for treatment from 4 clinics. Regions of interest (ROIs) were generated with 3 commercial AI-based automated contouring software solutions (AI1, AI2, AI3) spanning the following disease sites: brain, head and neck (H&N), thorax, abdomen, and pelvis. Quantitative agreement between AI-generated and clinical contours was measured by Dice similarity coefficient (DSC) and Hausdorff distance (HD). Qualitative assessment was performed by multiple experts scoring blinded AI-contours using a Likert scale. Workflow and usability surveying was also conducted. RESULTS: AI1, AI2, and AI3 contours had high quantitative agreement in 27.8%, 32.8%, and 34.1% of cases (DSC >0.9), performing well in pelvis (median DSC = 0.86/0.88/0.91) and thorax (median DSC = 0.91/0.89/0.91). All 3 solutions had low quantitative agreement in 7.4%, 8.8%, and 6.1% of cases (DSC <0.5), performing worse in brain (median DSC = 0.65/0.78/0.75) and H&N (median DSC = 0.76/0.80/0.81). Qualitatively, AI1 and AI2 contours were acceptable (rated 1-2) with at most minor edits in 70.7% and 74.6% of ROIs (2906 ratings), higher for abdomen (AI1: 79.2%) and thorax (AI2: 90.2%), and lower for H&N (29.0/35.6%). An end-user survey showed strong user preference for full automation and mixed preferences for accuracy versus total number of structures generated. CONCLUSIONS: Our evaluation method provided a comprehensive analysis of both quantitative and qualitative measures of commercially available pretrained AI autocontouring algorithms. The evaluation framework served as a roadmap for clinical integration that aligned with user workflow preference.

Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration.

Multiomics data including imaging radiomics and various types of molecular biomarkers have been increasingly investigated for better diagnosis and therapy in the era of precision oncology. Artificial intelligence (AI) including machine learning (ML) and deep learning (DL) techniques combined with the exponential growth of multiomics data may have great potential to revolutionize cancer subtyping, risk stratification, prognostication, prediction and clinical decision-making. In this article, we first present different categories of multiomics data and their roles in diagnosis and therapy. Second, AI-based data fusion methods and modeling methods as well as different validation schemes are illustrated. Third, the applications and examples of multiomics research in oncology are demonstrated. Finally, the challenges regarding the heterogeneity data set, availability of omics data, and validation of the research are discussed. The transition of multiomics research to real clinics still requires consistent efforts in standardizing omics data collection and analysis, building computational infrastructure for data sharing and storing, developing advanced methods to improve data fusion and interpretability, and ultimately, conducting large-scale prospective clinical trials to fill the gap between study findings and clinical benefits.

Automated treatment planning for proton pencil beam scanning using deep learning dose prediction and dose-mimicking optimization.

PURPOSE: The purpose of this study is to investigate the use of a deep learning architecture for automated treatment planning for proton pencil beam scanning (PBS). METHODS: A 3-dimensional (3D) U-Net model has been implemented in a commercial treatment planning system (TPS) that uses contoured regions of interest (ROI) binary masks as model inputs with a predicted dose distribution as the model output. Predicted dose distributions were converted to deliverable PBS treatment plans using a voxel-wise robust dose mimicking optimization algorithm. This model was leveraged to generate machine learning (ML) optimized plans for patients receiving proton PBS irradiation of the chest wall. Model training was carried out on a retrospective set of 48 previously-treated chest wall patient treatment plans. Model evaluation was carried out by generating ML-optimized plans on a hold-out set of 12 contoured chest wall patient CT datasets from previously treated patients. Clinical goal criteria and gamma analysis were used to compare dose distributions of the ML-optimized plans against the clinically approved plans across the test patients. RESULTS: Statistical analysis of mean clinical goal criteria indicates that compared to the clinical plans, the ML optimization workflow generated robust plans with similar dose to the heart, lungs, and esophagus while achieving superior dosimetric coverage to the PTV chest wall (clinical mean V95 = 97.6% vs. ML mean V95 = 99.1%, p < 0.001) across the 12 test patients. CONCLUSIONS: ML-based automated treatment plan optimization using the 3D U-Net model can generate treatment plans of similar clinical quality compared to human-driven optimization.

Independent association of metabolic tumor response on FDG-PET with pulmonary toxicity following risk-adaptive chemoradiation for unresectable non-small cell lung cancer: Inherent radiosensitivity or immune response?

BACKGROUND: In the context of a phase II trial of risk-adaptive chemoradiation, we evaluated whether tumor metabolic response could serve as a correlate of treatment sensitivity and toxicity. METHODS: Forty-five patients with AJCCv7 stage IIB-IIIB NSCLC enrolled on the FLARE-RT phase II trial (NCT02773238). [18F]fluorodeoxyglucose (FDG) PET-CT images were acquired prior to treatment and after 24 Gy during week 3. Patients with unfavorable on-treatment tumor response received concomitant boosts to 74 Gy total over 30 fractions rather than standard 60 Gy. Metabolic tumor volume and mean standardized uptake value (SUVmean) were calculated semi-automatically. Risk factors of pulmonary toxicity included concurrent chemotherapy regimen, adjuvant anti-PDL1 immunotherapy, and lung dosimetry. Incidence of CTCAE v4 grade 2+ pneumonitis was analyzed using the Fine-Gray method with competing risks of metastasis or death. Peripheral germline DNA microarray sequencing measured predefined candidate genes from distinct pathways: 96 DNA repair, 53 immunology, 38 oncology, 27 lung biology. RESULTS: Twenty-four patients received proton therapy, 23 received ICI, 26 received carboplatin-paclitaxel, and 17 pneumonitis events were observed. Pneumonitis risk was significantly higher for patients with COPD (HR 3.78 [1.48, 9.60], p = 0.005), those treated with immunotherapy (HR 2.82 [1.03, 7.71], p = 0.043) but not with carboplatin-paclitaxel (HR 1.98 [0.71, 5.54], p = 0.19). Pneumonitis rates were similar among selected patients receiving 74 Gy radiation vs 60 Gy (p = 0.33), proton therapy vs photon (p = 0.60), or with higher lung dosimetric V20 (p = 0.30). Patients in the upper quartile decrease in SUVmean (>39.7%) were at greater risk for pneumonitis (HR 4.00 [1.54, 10.44], p = 0.005) and remained significant in multivariable analysis (HR 3.34 [1.23, 9.10], p = 0.018). Germline DNA gene alterations in immunology pathways were most frequently associated with pneumonitis. CONCLUSION: Tumor metabolic response as measured by mean SUV is associated with increased pneumonitis risk in a clinical trial cohort of NSCLC patients independent of treatment factors. This may be partially attributed to patient-specific differences in immunogenicity.

Radiation and immune checkpoint inhibitor-mediated pneumonitis risk stratification in patients with locally advanced non-small cell lung cancer: role of functional lung radiomics?

BACKGROUND: Patients undergoing chemoradiation and immune checkpoint inhibitor (ICI) therapy for locally advanced non-small cell lung cancer (NSCLC) experience pulmonary toxicity at higher rates than historical reports. Identifying biomarkers beyond conventional clinical factors and radiation dosimetry is especially relevant in the modern cancer immunotherapy era. We investigated the role of novel functional lung radiomics, relative to functional lung dosimetry and clinical characteristics, for pneumonitis risk stratification in locally advanced NSCLC. METHODS: Patients with locally advanced NSCLC were prospectively enrolled on the FLARE-RT trial (NCT02773238). All received concurrent chemoradiation using functional lung avoidance planning, while approximately half received consolidation durvalumab ICI. Within tumour-subtracted lung regions, 110 radiomics features (size, shape, intensity, texture) were extracted on pre-treatment [99mTc]MAA SPECT/CT perfusion images using fixed-bin-width discretization. The performance of functional lung radiomics for pneumonitis (CTCAE v4 grade 2 or higher) risk stratification was benchmarked against previously reported lung dosimetric parameters and clinical risk factors. Multivariate least absolute shrinkage and selection operator Cox models of time-varying pneumonitis risk were constructed, and prediction performance was evaluated using optimism-adjusted concordance index (c-index) with 95% confidence interval reporting throughout. RESULTS: Thirty-nine patients were included in the study and pneumonitis occurred in 16/39 (41%) patients. Among clinical characteristics and anatomic/functional lung dosimetry variables, only the presence of baseline chronic obstructive pulmonary disease (COPD) was significantly associated with the development of pneumonitis (HR 4.59 [1.69-12.49]) and served as the primary prediction benchmark model (c-index 0.69 [0.59-0.80]). Discrimination of time-varying pneumonitis risk was numerically higher when combining COPD with perfused lung radiomics size (c-index 0.77 [0.65-0.88]) or shape feature classes (c-index 0.79 [0.66-0.91]) but did not reach statistical significance compared to benchmark models (p > 0.26). COPD was associated with perfused lung radiomics size features, including patients with larger lung volumes (AUC 0.75 [0.59-0.91]). Perfused lung radiomic texture features were correlated with lung volume (adj R2 = 0.84-1.00), representing surrogates rather than independent predictors of pneumonitis risk. CONCLUSIONS: In patients undergoing chemoradiation with functional lung avoidance therapy and optional consolidative immune checkpoint inhibitor therapy for locally advanced NSCLC, the strongest predictor of pneumonitis was the presence of baseline chronic obstructive pulmonary disease. Results from this novel functional lung radiomics exploratory study can inform future validation studies to refine pneumonitis risk models following combinations of radiation and immunotherapy. Our results support functional lung radiomics as surrogates of COPD for non-invasive monitoring during and after treatment. Further study of clinical, dosimetric, and radiomic feature combinations for radiation and immune-mediated pneumonitis risk stratification in a larger patient population is warranted.

Assessment of Cardiac, Vascular, and Pulmonary Pathobiology In Vivo During Acute COVID-19.

Background Acute COVID-19-related myocardial, pulmonary, and vascular pathology and how these relate to each other remain unclear. To our knowledge, no studies have used complementary imaging techniques, including molecular imaging, to elucidate this. We used multimodality imaging and biochemical sampling in vivo to identify the pathobiology of acute COVID-19. Specifically, we investigated the presence of myocardial inflammation and its association with coronary artery disease, systemic vasculitis, and pneumonitis. Methods and Results Consecutive patients presenting with acute COVID-19 were prospectively recruited during hospital admission in this cross-sectional study. Imaging involved computed tomography coronary angiography (identified coronary disease), cardiac 2-deoxy-2-[fluorine-18]fluoro-D-glucose positron emission tomography/computed tomography (identified vascular, cardiac, and pulmonary inflammatory cell infiltration), and cardiac magnetic resonance (identified myocardial disease) alongside biomarker sampling. Of 33 patients (median age 51 years, 94% men), 24 (73%) had respiratory symptoms, with the remainder having nonspecific viral symptoms. A total of 9 patients (35%, n=9/25) had cardiac magnetic resonance-defined myocarditis. Of these patients, 53% (n=5/8) had myocardial inflammatory cell infiltration. A total of 2 patients (5%) had elevated troponin levels. Cardiac troponin concentrations were not significantly higher in patients with and without myocarditis (8.4 ng/L [interquartile range, IQR: 4.0-55.3] versus 3.5 ng/L [IQR: 2.5-5.5]; P=0.07) or myocardial cell infiltration (4.4 ng/L [IQR: 3.4-8.3] versus 3.5 ng/L [IQR: 2.8-7.2]; P=0.89). No patients had obstructive coronary artery disease or vasculitis. Pulmonary inflammation and consolidation (percentage of total lung volume) was 17% (IQR: 5%-31%) and 11% (IQR: 7%-18%), respectively. Neither were associated with the presence of myocarditis. Conclusions Myocarditis was present in a third patients with acute COVID-19, and the majority had inflammatory cell infiltration. Pneumonitis was ubiquitous, but this inflammation was not associated with myocarditis. The mechanism of cardiac pathology is nonischemic and not attributable to a vasculitic process. Registration URL: https://www.isrctn.com; Unique identifier: ISRCTN12154994.

Prognostic Value of Early Fluorodeoxyglucose-Positron Emission Tomography Response Imaging and Peripheral Immunologic Biomarkers: Substudy of a Phase II Trial of Risk-Adaptive Chemoradiation for Unresectable Non-Small Cell Lung Cancer.

Purpose: We sought to examine the prognostic value of fluorodeoxyglucose-positron emission tomography (PET) imaging during chemoradiation for unresectable non-small cell lung cancer for survival and hypothesized that tumor PET response is correlated with peripheral T-cell function. Methods and Materials: Forty-five patients with American Joint Committee on Cancer version 7 stage IIB-IIIB non-small cell lung cancer enrolled in a phase II trial and received platinum-doublet chemotherapy concurrent with 6 weeks of radiation (NCT02773238). Fluorodeoxyglucose-PET was performed before treatment start and after 24 Gy of radiation (week 3). PET response status was prospectively defined by multifactorial radiologic interpretation. PET responders received 60 Gy in 30 fractions, while nonresponders received concomitant boosts to 74 Gy in 30 fractions. Peripheral blood was drawn synchronously with PET imaging, from which germline DNA sequencing, T-cell receptor sequencing, and plasma cytokine analysis were performed. Results: Median follow-up was 18.8 months, 1-year overall survival (OS) 82%, 1-year progression-free survival 53%, and 1-year locoregional control 88%. Higher midtreatment PET total lesion glycolysis was detrimental to OS (1 year 87% vs 63%, P < .001), progression-free survival (1 year 60% vs 26%, P = .044), and locoregional control (1 year 94% vs 65%, P = .012), even after adjustment for clinical/treatment factors. Twenty-nine of 45 patients (64%) were classified as PET responders based on a priori definition. Higher tumor programmed death-ligand 1 expression was correlated with response on PET (P = .017). Higher T-cell receptor richness and clone distribution slope were associated with improved OS (P = .018-0.035); clone distribution slope was correlated with PET response (P = .031). Conclusions: Midchemoradiation PET imaging is prognostic for survival; PET response may be linked to tumor and peripheral T-cell biomarkers.

A Prospective Study of a Resorbable Intravesical Fiducial Marker for Bladder Cancer Radiation Therapy.

Purpose: We conducted a prospective pilot study to evaluate safety and feasibility of TraceIT, a resorbable radiopaque hydrogel, to improve image guidance for bladder cancer radiation therapy (RT). Methods and Materials: Patients with muscle invasive bladder cancer receiving definitive RT were eligible. TraceIT was injected intravesically around the tumor bed during maximal transurethral resection of bladder tumor. The primary endpoint was the difference between radiation treatment planning margin on daily cone beam computed tomography based on alignment to TraceIT versus standard-of-care pelvic bone anatomy. The Van Herk margin formula was used to determine the optimal planning target volume margin. TraceIT visibility, recurrence rates, and survival were estimated by Kaplan-Meier method. Toxicity was measured by Common Terminology Criteria for Adverse Events version 4.03. Results: The trial was fully accrued and 15 patients were analyzed. TraceIT was injected in 4 sites/patient (range, 4-6). Overall, 94% (95% confidence interval [CI], 90%-98%) of injection sites were radiographically visible at RT initiation versus 71% (95% CI, 62%-81%) at RT completion. The median duration of radiographic visibility for injection sites was 106 days (95% CI, 104-113). Most patients were treated with a standard split-course approach with initial pelvic radiation fields, then midcourse repeat transurethral resection of bladder tumor followed by bladder tumor bed boost fields, and 14/15 received concurrent chemotherapy. Alignment to fiducials could allow for reduced planning target volume margins (0.67 vs 1.56 cm) for the initial phase of RT, but not for the boost (1.01 vs 0.96 cm). This allowed for improved target coverage (D95% 80%-83% to 91%-94%) for 2 patients retrospectively planned with both volumetric-modulated arc therapy and 3-dimensional conformal RT. At median follow-up of 22 months, no acute or late complications attributable to TraceIT placement occurred. No patients required salvage cystectomy. Conclusions: TraceIT intravesical fiducial placement is safe and feasible and may facilitate tumor bed delineation and targeting in patients undergoing RT for localized muscle invasive bladder cancer. Improved image guided treatment may facilitate strategies to improve local control and minimize toxicity.

Multitask Learning Radiomics on Longitudinal Imaging to Predict Survival Outcomes following Risk-Adaptive Chemoradiation for Non-Small Cell Lung Cancer.

Medical imaging provides quantitative and spatial information to evaluate treatment response in the management of patients with non-small cell lung cancer (NSCLC). High throughput extraction of radiomic features on these images can potentially phenotype tumors non-invasively and support risk stratification based on survival outcome prediction. The prognostic value of radiomics from different imaging modalities and time points prior to and during chemoradiation therapy of NSCLC, relative to conventional imaging biomarker or delta radiomics models, remains uncharacterized. We investigated the utility of multitask learning of multi-time point radiomic features, as opposed to single-task learning, for improving survival outcome prediction relative to conventional clinical imaging feature model benchmarks. Survival outcomes were prospectively collected for 45 patients with unresectable NSCLC enrolled on the FLARE-RT phase II trial of risk-adaptive chemoradiation and optional consolidation PD-L1 checkpoint blockade (NCT02773238). FDG-PET, CT, and perfusion SPECT imaging pretreatment and week 3 mid-treatment was performed and 110 IBSI-compliant pyradiomics shape-/intensity-/texture-based features from the metabolic tumor volume were extracted. Outcome modeling consisted of a fused Laplacian sparse group LASSO with component-wise gradient boosting survival regression in a multitask learning framework. Testing performance under stratified 10-fold cross-validation was evaluated for multitask learning radiomics of different imaging modalities and time points. Multitask learning models were benchmarked against conventional clinical imaging and delta radiomics models and evaluated with the concordance index (c-index) and index of prediction accuracy (IPA). FDG-PET radiomics had higher prognostic value for overall survival in test folds (c-index 0.71 [0.67, 0.75]) than CT radiomics (c-index 0.64 [0.60, 0.71]) or perfusion SPECT radiomics (c-index 0.60 [0.57, 0.63]). Multitask learning of pre-/mid-treatment FDG-PET radiomics (c-index 0.71 [0.67, 0.75]) outperformed benchmark clinical imaging (c-index 0.65 [0.59, 0.71]) and FDG-PET delta radiomics (c-index 0.52 [0.48, 0.58]) models. Similarly, the IPA for multitask learning FDG-PET radiomics (30%) was higher than clinical imaging (26%) and delta radiomics (15%) models. Radiomics models performed consistently under different voxel resampling conditions. Multitask learning radiomics for outcome modeling provides a clinical decision support platform that leverages longitudinal imaging information. This framework can reveal the relative importance of different imaging modalities and time points when designing risk-adaptive cancer treatment strategies.

A system for equitable workload distribution in clinical medical physics.

BACKGROUND: Clinical medical physics duties include routine tasks, special procedures, and development projects. It can be challenging to distribute the effort equitably across all team members, especially in large clinics or systems where physicists cover multiple sites. The purpose of this work is to study an equitable workload distribution system in radiotherapy physics that addresses the complex and dynamic nature of effort assignment. METHODS: We formed a working group that defined all relevant clinical tasks and estimated the total time spent per task. Estimates used data from the oncology information system, a survey of physicists, and group consensus. We introduced a quantitative workload unit, "equivalent workday" (eWD), as a common unit for effort. The sum of all eWD values adjusted for each physicist's clinical full-time equivalent yields a "normalized total effort" (nTE) metric for each physicist, that is, the fraction of the total effort assigned to that physicist. We implemented this system in clinical operation. During a trial period of 9 months, we made adjustments to include tasks previously unaccounted for and refined the system. The workload distribution of eight physicists over 12 months was compared before and after implementation of the nTE system. RESULTS: Prior to implementation, differences in workload of up to 50% existed between individual physicists (nTE range of 10.0%-15.0%). During the trial period, additional categories were added to account for leave and clinical projects that had previously been assigned informally. In the 1-year period after implementation, the individual workload differences were within 5% (nTE range of 12.3%-12.8%). CONCLUSION: We developed a system to equitably distribute workload and demonstrated improvements in the equity of workload. A quantitative approach to workload distribution improves both transparency and accountability. While the system was motivated by the complexities within an academic medical center, it may be generally applicable for other clinics.

Framework for Machine Learning of CT and PET Radiomics to Predict Local Failure after Radiotherapy in Locally Advanced Head and Neck Cancers.

CONTEXT: Cancer Radiomics is an emerging field in medical imaging and refers to the process of converting routine radiological images that are typically qualitatively interpreted to quantifiable descriptions of the tumor phenotypes and when combined with statistical analytics can improve the accuracy of clinical outcome prediction models. However, to understand the radiomic features and their correlation to molecular changes in the tumor, first, there is a need for the development of robust image analysis methods, software tools and statistical prediction models which is often limited in low- and middle-income countries (LMIC). AIMS: The aim is to build a framework for machine learning of radiomic features of planning computed tomography (CT) and positron emission tomography (PET) using open source radiomics and data analytics platforms to make it widely accessible to clinical groups. The framework is tested in a small cohort to predict local disease failure following radiation treatment for head-and-neck cancer (HNC). The predictors were also compared with the existing Aerts HNC radiomics signature. SETTINGS AND DESIGN: Retrospective analysis of patients with locally advanced HNC between 2017 and 2018 and 31 patients with both pre- and post-radiation CT and evaluation PET were selected. SUBJECTS AND METHODS: Tumor volumes were delineated on baseline PET using the semi-automatic adaptive-threshold algorithm and propagated to CT; PyRadiomics features (total of 110 under shape/intensity/texture classes) were extracted. Two feature-selection methods were tested for model stability. Models were built based on least absolute shrinkage and selection operator-logistic and Ridge regression of the top pretreatment radiomic features and compared to Aerts' HNC-signature. Average model performance across all internal validation test folds was summarized by the area under the receiver operator curve (ROC). RESULTS: Both feature selection methods selected CT features MCC (GLCM), SumEntropy (GLCM) and Sphericity (Shape) that could predict the binary failure status in the cross-validated group and achieved an AUC >0.7. However, models using Aerts' signature features (Energy, Compactness, GLRLM-GrayLevelNonUniformity and GrayLevelNonUniformity-HLH wavelet) could not achieve a clear separation between outcomes (AUC = 0.51-0.54). CONCLUSIONS: Radiomics pipeline included open-source workflows which makes it adoptable in LMIC countries. Additional independent validation of data is crucial for the implementation of radiomic models for clinical risk stratification.

Reliability of Quantitative 18F-FDG PET/CT Imaging Biomarkers for Classifying Early Response to Chemoradiotherapy in Patients With Locally Advanced Non-Small Cell Lung Cancer.

PURPOSE OF THE REPORT: We evaluated the reliability of 18F-FDG PET imaging biomarkers to classify early response status across observers, scanners, and reconstruction algorithms in support of biologically adaptive radiation therapy for locally advanced non-small cell lung cancer. PATIENTS AND METHODS: Thirty-one patients with unresectable locally advanced non-small cell lung cancer were prospectively enrolled on a phase 2 trial (NCT02773238) and underwent 18F-FDG PET on GE Discovery STE (DSTE) or GE Discovery MI (DMI) PET/CT systems at baseline and during the third week external beam radiation therapy regimens. All PET scans were reconstructed using OSEM; GE-DMI scans were also reconstructed with BSREM-TOF (block sequential regularized expectation maximization reconstruction algorithm incorporating time of flight). Primary tumors were contoured by 3 observers using semiautomatic gradient-based segmentation. SUVmax, SUVmean, SUVpeak, MTV (metabolic tumor volume), and total lesion glycolysis were correlated with midtherapy multidisciplinary clinical response assessment. Dice similarity of contours and response classification areas under the curve were evaluated across observers, scanners, and reconstruction algorithms. LASSO logistic regression models were trained on DSTE PET patient data and independently tested on DMI PET patient data. RESULTS: Interobserver variability of PET contours was low for both OSEM and BSREM-TOF reconstructions; intraobserver variability between reconstructions was slightly higher. ΔSUVpeak was the most robust response predictor across observers and image reconstructions. LASSO models consistently selected ΔSUVpeak and ΔMTV as response predictors. Response classification models achieved high cross-validated performance on the DSTE cohort and more variable testing performance on the DMI cohort. CONCLUSIONS: The variability FDG PET lesion contours and imaging biomarkers was relatively low across observers, scanners, and reconstructions. Objective midtreatment PET response assessment may lead to improved precision of biologically adaptive radiation therapy.

Treatment Intensification in Locally Advanced/Unresectable NSCLC Through Combined Modality Treatment and Precision Dose Escalation.

The best survival for patients with unresectable, locally advanced NSCLC is currently achieved through concurrent chemoradiation followed by durvalumab for a year. Despite the best standard of care treatment, the majority of patients still develop disease recurrence, which could be distant and/or local. Trials continue to try and improve outcomes for patients with unresectable NSCLC, typically through treatment intensification, with the addition of more systemic agents, or more radiation dose to the tumor. Although RTOG 0617 showed that uniform dose escalation across an unselected population of patients undergoing chemoradiation is not beneficial, efforts continue to select patients and tumor subsets that are likely to benefit from dose escalation. This review describes some of the ongoing therapeutic trials in unresectable NSCLC, with an emphasis on quantitative imaging and precision radiation dose escalation.

Whole-Lesion DCE-MRI Intensity Histogram Analysis for Diagnosis in Patients with Suspected Lung Cancer.

RATIONALE AND OBJECTIVES: To explore the diagnostic value of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) intensity histogram metrics, relative to time intensity curve (TIC)-derived metrics, in patients with suspected lung cancer. MATERIALS AND METHODS: This retrospective study enrolled 49 patients with suspected lung cancer on routine CT imaging who underwent DCE-MRI scans and had final histopathologic diagnosis. Three TIC-derived metrics (maximum enhancement ratio, peak time [Tmax] and slope) and eight intensity histogram metrics (volume, integral, maximum, minimum, median, coefficient of variation [CoV], skewness, and kurtosis) were extracted from DCE-MRI images. TIC-derived and intensity histogram metrics were compared between benignity versus malignancy using the Wilcoxon rank-sum test. Associations between imaging metrics and malignancy risk were assessed by univariate and multivariate logistic regression odds ratios (ORs). RESULTS: There were 33 malignant lesions and 16 benign lesions based on histopathology. Lower CoV (OR = 0.2 per 1-SD increase, p = 0.0006), lower Tmax (OR = 0.4 per 1-SD increase, p = 0.005), and steeper slope (OR = 2.4 per 1-SD increase, p = 0.010) were significantly associated with increased risk of malignancy. Under multivariate analysis, CoV was significantly independently associated with malignancy likelihood after accounting for either Tmax (OR = 0.3 per 1-SD increase, p = 0.007) or slope (OR = 0.3 per 1-SD increase, p = 0.011). CONCLUSION: This initial study found that DCE-MRI CoV was independently associated with malignancy in patients with suspected lung cancer. CoV has the potential to help diagnose indeterminate pulmonary lesions and may complement TIC-derived DCE-MRI metrics. Further studies are warranted to validate the diagnostic value of DCE-MRI intensity histogram analysis.

Sensitivity analysis of FDG PET tumor voxel cluster radiomics and dosimetry for predicting mid-chemoradiation regional response of locally advanced lung cancer.

We investigated the sensitivity of regional tumor response prediction to variability in voxel clustering techniques, imaging features, and machine learning algorithms in 25 patients with locally advanced non-small cell lung cancer (LA-NSCLC) enrolled on the FLARE-RT clinical trial. Metabolic tumor volumes (MTV) from pre-chemoradiation (PETpre) and mid-chemoradiation fluorodeoxyglucose-positron emission tomography (FDG PET) images (PETmid) were subdivided into K-means or hierarchical voxel clusters by standardized uptake values (SUV) and 3D-positions. MTV cluster separability was evaluated by CH index, and morphologic changes were captured by Dice similarity and centroid Euclidean distance. PETpre conventional features included SUVmean, MTV/MTV cluster size, and mean radiation dose. PETpre radiomics consisted of 41 intensity histogram and 3D texture features (PET Oncology Radiomics Test Suite) extracted from MTV or MTV clusters. Machine learning models (multiple linear regression, support vector regression, logistic regression, support vector machines) of conventional features or radiomic features were constructed to predict PETmid response. Leave-one-out-cross-validated root-mean-squared-error (RMSE) for continuous response regression (ΔSUVmean) and area-under-receiver-operating-characteristic-curve (AUC) for binary response classification were calculated. K-means MTV 2-clusters (MTVhi, MTVlo) achieved maximum CH index separability (Friedman p < 0.001). Between PETpre and PETmid, MTV cluster pairs overlapped (Dice 0.70-0.87) and migrated 0.6-1.1 cm. PETmid ΔSUVmean response prediction was superior in MTV and MTVlo (RMSE = 0.17-0.21) compared to MTVhi (RMSE = 0.42-0.52, Friedman p < 0.001). PETmid ΔSUVmean response class prediction performance trended higher in MTVlo (AUC = 0.83-0.88) compared to MTVhi (AUC = 0.44-0.58, Friedman p = 0.052). Models were more sensitive to MTV/MTV cluster regions (Friedman p = 0.026) than feature sets/algorithms (Wilcoxon signed-rank p = 0.36). Top-ranked radiomic features included GLZSM-LZHGE (large-zone-high-SUV), GTSDM-CP (cluster-prominence), GTSDM-CS (cluster-shade) and NGTDM-CNT (contrast). Top-ranked features were consistent between MTVhi and MTVlo cluster pairs but varied between MTVhi-MTVlo clusters, reflecting distinct regional radiomic phenotypes. Variability in tumor voxel cluster response prediction can inform robust radiomic target definition for risk-adaptive chemoradiation in patients with LA-NSCLC. FLARE-RT trial: NCT02773238.

A machine learning-based framework for delivery error prediction in proton pencil beam scanning using irradiation log-files.

PURPOSE: This study aims to investigate the use of machine learning models for delivery error prediction in proton pencil beam scanning (PBS) delivery. METHODS: A dataset of planned and delivered PBS spot parameters was generated from a set of 20 prostate patient treatments. Planned spot parameters (spot position, MU and energy) were extracted from the treatment planning system (TPS) for each beam. Delivered spot parameters were extracted from irradiation log-files for each beam delivery following treatment. The dataset was used as a training dataset for three machine learning models which were trained to predict delivered spot parameters based on planned parameters. K-fold cross validation was employed for hyper-parameter tuning and model selection where the mean absolute error (MAE) was used as the model evaluation metric. The model with lowest MAE was then selected to generate a predicted dose distribution for a test prostate patient within a commercial TPS. RESULTS: Analysis of the spot position delivery error between planned and delivered values resulted in standard deviations of 0.39 mm and 0.44 mm for x and y spot positions respectively. Prediction error standard deviation values of spot positions using the selected model were 0.22 mm and 0.11 mm for x and y spot positions respectively. Finally, a three-way comparison of dose distributions and DVH values for select OARs indicates that the random-forest-predicted dose distribution within the test prostate patient was in closer agreement to the delivered dose distribution than the planned distribution. CONCLUSIONS: PBS delivery error can be accurately predicted using machine learning techniques.

Scanning Beam Proton Therapy versus Photon IMRT for Stage III Lung Cancer: Comparison of Dosimetry, Toxicity, and Outcomes.

PURPOSE: There are limited clinical data on scanning-beam proton therapy (SPT) in treating locally advanced lung cancer, as most published studies have used passive-scatter technology. There is increasing interest in whether the dosimetric advantages of SPT compared with photon therapy can translate into superior clinical outcomes. We present our experience of SPT and photon intensity modulated radiation therapy (IMRT) with clinical dosimetry and outcomes in patients with stage III lung cancer. METHODS AND MATERIALS: Patients with stage III lung cancer treated at our center between 2013 and May 2018 were identified in compliance with our institutional review board (64 patients = 34 SPT + 30 IMRT). Most proton patients were treated with pencil beam scanning (28 of 34), and 6 of 34 were treated with uniform scanning. Fisher exact test, χ2 test, and Mann-Whitney test were used to compare groups. All tests were 2-sided. RESULTS: Patient characteristics were similar between the IMRT and SPT patients, except for worse lung function in the IMRT group. Mean dose to lung, heart, and esophagus was lower in the SPT group, with most benefit in the low-dose region (lungs, 9.7 Gy vs 15.7 Gy for SPT vs IMRT, respectively [P = .004]; heart, 7 Gy vs 14 Gy [P = .001]; esophagus, 28.2 Gy vs 30.9 Gy [P = .023]). Esophagitis and dermatitis grades were not different between the 2 groups. Grade 2+ pneumonitis was 21% in the SPT group and 40% in the IMRT group (P = .107). Changes in blood counts were not different between the 2 groups. Overall survival and progression-free survival were not different between SPT and IMRT (median overall survival, 41.6 vs 30.7 months, respectively [P = .52]; median progression-free survival, 19.5 vs 14.6 months [P = .50]). CONCLUSIONS: We report our experience with SPT and IMRT in stage III lung cancer. Our cohort of patients treated with SPT had lower doses to normal organs (lungs, heart, esophagus) than our IMRT cohort. There was no statistically significant difference in toxicity rates or survival, although there may have been a trend toward lower rates of pneumonitis.

The Dancing Cord: Inherent Spinal Cord Motion and Its Effect on Cord Dose in Spine Stereotactic Body Radiation Therapy.

BACKGROUND: Spinal cord dose limits are critically important for the safe practice of spine stereotactic body radiotherapy (SBRT). However, the effect of inherent spinal cord motion on cord dose in SBRT is unknown. OBJECTIVE: To assess the effects of cord motion on spinal cord dose in SBRT. METHODS: Dynamic balanced fast field echo (BFFE) magnetic resonance imaging (MRI) was obtained in 21 spine metastasis patients treated with SBRT. Planning computed tomography (CT), conventional static T2-weighted MRI, BFFE MRI, and dose planning data were coregistered. Spinal cord from the dynamic BFFE images (corddyn) was compared with the T2-weighted MRI (cordstat) to analyze motion of corddyn beyond the cordstat (Dice coefficient, Jaccard index), and beyond cordstat with added planning organ at risk volume (PRV) margins. Cord dose was compared between cordstat, and corddyn (Wilcoxon signed-rank test). RESULTS: Dice coefficient (0.70-0.95, median 0.87) and Jaccard index (0.54-0.90, median 0.77) demonstrated motion of corddyn beyond cordstat. In 62% of the patients (13/21), the dose to corddyn exceeded that of cordstat by 0.6% to 13.8% (median 4.3%). The corddyn spatially excursed outside the 1-mm PRV margin of cordstat in 9 patients (43%); among these dose to corddyn exceeded dose to cordstat >+ 1-mm PRV margin in 78% of the patients (7/9). Corddyn did not excurse outside the 1.5-mm or 2-mm PRV cord cordstat margin. CONCLUSION: Spinal cord motion may contribute to increases in radiation dose to the cord from SBRT for spine metastasis. A PRV margin of at least 1.5 to 2 mm surrounding the cord should be strongly considered to account for inherent spinal cord motion.

Clinical Monte Carlo versus Pencil Beam Treatment Planning in Nasopharyngeal Patients Receiving IMPT.

PURPOSE: Pencil beam (PB) analytical algorithms have been the standard of care for proton therapy dose calculations. The introduction of Monte Carlo (MC) algorithms may provide more robust and accurate planning and can improve therapeutic benefit. We conducted a dosimetric analysis to quantify the differences between MC and PB algorithms in the clinical setting of dose-painted nasopharyngeal cancer intensity-modulated proton radiotherapy. PATIENTS AND METHODS: Plans of 14 patients treated with PB analytical algorithm optimized and calculated (PBPB) were retrospectively analyzed. The PBPB plans were recalculated using MC to generate PBMC plans and, finally, reoptimized and recalculated with MC to generate MCMC plans. The plans were compared across several dosimetric endpoints and correlated with documented toxicity. Robustness of the planning scenarios (PBPB, PBMC, MCMC) in the presence of setup and range uncertainties was compared. RESULTS: A median decrease of up to 5 Gy (P < .05) was observed in coverage of planning target volume high-risk, intermediate-risk, and low-risk volumes when PB plans were recalculated using the MC algorithm. This loss in coverage was regained by reoptimizing with MC, albeit with a slightly higher dose to normal tissues but within the standard tolerance limits. The robustness of both PB and MC plans remained similar in the presence of setup and range uncertainties. The MC-calculated mean dose to the oral avoidance structure, along with changes in global maximum dose between PB and MC dosimetry, may be associated with acute toxicity-related events. CONCLUSION: Retrospective analyses of plan dosimetry quantified a loss of coverage with PB that could be recovered under MC optimization. MC optimization should be performed for the complex dosimetry in patients with nasopharyngeal carcinoma before plan acceptance and should also be used in correlative studies of proton dosimetry with clinical endpoints.

Comparison of regional lung perfusion response on longitudinal MAA SPECT/CT in lung cancer patients treated with and without functional tissue-avoidance radiation therapy.

OBJECTIVE: The effect of functional lung avoidance planning on radiation dose-dependent changes in regional lung perfusion is unknown. We characterized dose-perfusion response on longitudinal perfusion single photon emission computed tomography (SPECT)/CT in two cohorts of lung cancer patients treated with and without functional lung avoidance techniques. METHODS: The study included 28 primary lung cancer patients: 20 from interventional (NCT02773238) (FLARE-RT) and eight from observational (NCT01982123) (LUNG-RT) clinical trials. FLARE-RT treatment plans included perfused lung dose constraints while LUNG-RT plans adhered to clinical standards. Pre- and 3 month post-treatment macro-aggregated albumin (MAA) SPECT/CT scans were rigidly co-registered to planning four-dimensional CT scans. Tumour-subtracted lung dose was converted to EQD2 and sorted into 5 Gy bins. Mean dose and percent change between pre/post-RT MAA-SPECT uptake (%ΔPERF), normalized to total tumour-subtracted lung uptake, were calculated in each binned dose region. Perfusion frequency histograms of pre/post-RT MAA-SPECT were analyzed. Dose-response data were parameterized by sigmoid logistic functions to estimate maximum perfusion increase (%ΔPERFmaxincrease), maximum perfusion decrease (%ΔPERFmaxdecrease), dose midpoint (Dmid), and dose-response slope (k). RESULTS: Differences in MAA perfusion frequency distribution shape between time points were observed in 11/20 (55%) FLARE-RT and 2/8 (25%) LUNG-RT patients (p < 0.05). FLARE-RT dose response was characterized by >10% perfusion increase in the 0-5 Gy dose bin for 8/20 patients (%ΔPERFmaxincrease = 10-40%), which was not observed in any LUNG-RT patients (p = 0.03). The dose midpoint Dmid at which relative perfusion declined by 50% trended higher in FLARE-RT compared to LUNG-RT cohorts (35 GyEQD2 vs 21 GyEQD2, p = 0.09), while the dose-response slope k was similar between FLARE-RT and LUNG-RT cohorts (3.1-3.2, p = 0.86). CONCLUSION: Functional lung avoidance planning may promote increased post-treatment perfusion in low dose regions for select patients, though inter-patient variability remains high in unbalanced cohorts. These preliminary findings form testable hypotheses that warrant subsequent validation in larger cohorts within randomized or case-matched control investigations. ADVANCES IN KNOWLEDGE: This novel preliminary study reports differences in dose-response relationships between patients receiving functional lung avoidance radiation therapy (FLARE-RT) and those receiving conventionally planned radiation therapy (LUNG-RT). Following further validation and testing of these effects in larger patient populations, individualized estimation of regional lung perfusion dose-response may help refine future risk-adaptive strategies to minimize lung function deficits and toxicity incidence.