A qualitative investigation of resilience and well-being among medical physics residents.

PURPOSE: Medical physics residents (MPRs) will define and shape the future of physics in medicine. We sought to better understand the residency experience, as related to resilience and well-being, through the lens of current MPRs and medical physicists (MPs) working with residents. METHODS AND MATERIALS: From February-May 2019, we conducted 32, 1-h, confidential, semi-structured interviews with MPs either currently enrolled in an accredited residency (n = 16) or currently employed by a department with an accredited residency (n = 16). Interviews centered on the topics of mentorship, work/life integration, and discrimination. Qualitative analysis methods were used to derive key themes from the interview transcripts. RESULTS: With regard to the medical physics residency experience, four key themes emerged during qualitative analysis: the demanding nature of medical physics residencies, the negative impacts of residency on MPRs during training and beyond, strategies MPRs use to cope with residency stress, and the role of professional societies in addressing residency-related change. CONCLUSIONS: Residency training is a stress-inducing time in the path to becoming a board-certified MP. By uncovering several sources of this stress, we have identified opportunities to support the resiliency and well-being of MPs in training through recommendations by professional societies, programmatic changes, and interventions at the department and residency program director level for residency programs, as well as strategies that MPRs themselves can use to support well-being on their career journey.

Feasibility of function-guided lung treatment planning with parametric response mapping.

PURPOSE: Recent advancements in functional lung imaging have been developed to improve clinicians' knowledge of patient pulmonary condition prior to treatment. Ultimately, it may be possible to employ these functional imaging modalities to tailor radiation treatment plans to optimize patient outcome and mitigate pulmonary complications. Parametric response mapping (PRM) is a computed tomography (CT)-based functional lung imaging method that utilizes a voxel-wise image analysis technique to classify lung abnormality phenotypes, and has previously been shown to be effective at assessing lung complication risk in diagnostic applications. The purpose of this work was to demonstrate the implementation of PRM guidance in radiotherapy treatment planning. METHODS AND MATERIALS: A retrospective study was performed with 18 lung cancer patients to test the incorporation of PRM into a radiotherapy planning workflow. Paired inspiration/expiration pretreatment CT scans were acquired and PRM analysis was utilized to classify each voxel as normal, parenchymal disease, small airway disease, and emphysema. Density maps were generated for each PRM classification to contour high density regions of pulmonary abnormalities. Conventional volumetric-modulated arc therapy and PRM-guided treatment plans were designed for each patient. RESULTS: PRM guidance was successfully implemented into the treatment planning process. The inclusion of PRM priorities resulted in statistically significant (p < 0.05) improvements to the V20Gy within the PRM avoidance contours. On average, reductions of 5.4% in the V20Gy(%) were found. The PRM-guided treatment plans did not significantly increase the dose to the organs at risk or result in insufficient planning target volume coverage, but did increase plan complexity. CONCLUSIONS: PRM guidance was successfully implemented into a treatment planning workflow and shown to be effective for dose redistribution within the lung. This work has provided a framework for the potential clinical implementation of PRM-guided treatment planning.

A prediction model for early death in non-small cell lung cancer patients following curative-intent chemoradiotherapy.

BACKGROUND: Early death after a treatment can be seen as a therapeutic failure. Accurate prediction of patients at risk for early mortality is crucial to avoid unnecessary harm and reducing costs. The goal of our work is two-fold: first, to evaluate the performance of a previously published model for early death in our cohorts. Second, to develop a prognostic model for early death prediction following radiotherapy. MATERIAL AND METHODS: Patients with NSCLC treated with chemoradiotherapy or radiotherapy alone were included in this study. Four different cohorts from different countries were available for this work (N = 1540). The previous model used age, gender, performance status, tumor stage, income deprivation, no previous treatment given (yes/no) and body mass index to make predictions. A random forest model was developed by learning on the Maastro cohort (N = 698). The new model used performance status, age, gender, T and N stage, total tumor volume (cc), total tumor dose (Gy) and chemotherapy timing (none, sequential, concurrent) to make predictions. Death within 4 months of receiving the first radiotherapy fraction was used as the outcome. RESULTS: Early death rates ranged from 6 to 11% within the four cohorts. The previous model performed with AUC values ranging from 0.54 to 0.64 on the validation cohorts. Our newly developed model had improved AUC values ranging from 0.62 to 0.71 on the validation cohorts. CONCLUSIONS: Using advanced machine learning methods and informative variables, prognostic models for early mortality can be developed. Development of accurate prognostic tools for early mortality is important to inform patients about treatment options and optimize care.

The impact of a high-definition multileaf collimator for spine SBRT.

PURPOSE: Advanced radiotherapy delivery systems designed for high-dose, high-precision treatments often come equipped with high-definition multi-leaf collimators (HD-MLC) aimed at more finely shaping radiation dose to the target. In this work, we study the effect of a high definition MLC on spine stereotactic body radiation therapy (SBRT) treatment plan quality and plan deliverability. METHODS AND MATERIALS: Seventeen spine SBRT cases were planned with VMAT using a standard definition MLC (M120), HD-MLC, and HD-MLC with an added objective to reduce monitor units (MU). M120 plans were converted into plans deliverable on an HD-MLC using in-house software. Plan quality and plan deliverability as measured by portal dosimetry were compared among the three types of plans. RESULTS: Only minor differences were noted in plan quality between the M120 and HD-MLC plans. Plans generated with the HD-MLC tended to have better spinal cord sparing (3% reduction in maximum cord dose). HD-MLC plans on average had 12% more MU and 55% greater modulation complexity as defined by an in-house metric. HD-MLC plans also had significantly degraded deliverability. Of the VMAT arcs measured, 94% had lower gamma passing metrics when using the HD-MLC. CONCLUSION: Modest improvements in plan quality were noted when switching from M120 to HD-MLC at the expense of significantly less accurate deliverability in some cases.

Predicting deliverability of volumetric-modulated arc therapy (VMAT) plans using aperture complexity analysis.

The purpose of this study was to evaluate the ability of an aperture complexity metric for volumetric-modulated arc therapy (VMAT) plans to predict plan delivery accuracy. We developed a complexity analysis tool as a plug-in script to Varian's Eclipse treatment planning system. This script reports the modulation of plans, arcs, and individual control points for VMAT plans using a previously developed complexity metric. The calculated complexities are compared to that of 649 VMAT plans previously treated at our institution from 2013 to mid-2015. We used the VMAT quality assurance (QA) results from the 649 treated plans, plus 62 plans that failed pretreatment QA, to validate the ability of the complexity metric to predict plan deliverability. We used a receiver operating characteristic (ROC) analysis to determine an appropriate complexity threshold value above which a plan should be considered for reoptimization before it moves further through our planning workflow. The average complexity metric for the 649 treated plans analyzed with the script was 0.132 mm-1 with a standard deviation of 0.036 mm-1. We found that when using a threshold complexity value of 0.180 mm-1, the true positive rate for correctly identifying plans that failed QA was 44%, and the false-positive rate was 7%. Used clinically with this threshold, the script can identify overly modulated plans and thus prevent a significant portion of QA failures. Reducing VMAT plan complexity has a number of important clinical benefits, including improving plan deliverability and reducing treatment time. Use of the complexity metric during both the planning and QA processes can reduce the number of QA failures and improve the quality of VMAT plans used for treatment.

Improving treatment plan evaluation with automation.

The goal of this work is to evaluate the effectiveness of Plan-Checker Tool (PCT) which was created to improve first-time plan quality, reduce patient delays, increase the efficiency of our electronic workflow, and standardize and automate the phys-ics plan review in the treatment planning system (TPS). PCT uses an application programming interface to check and compare data from the TPS and treatment management system (TMS). PCT includes a comprehensive checklist of automated and manual checks that are documented when performed by the user as part of a plan readiness check for treatment. Prior to and during PCT development, errors identified during the physics review and causes of patient treatment start delays were tracked to prioritize which checks should be automated. Nineteen of 33checklist items were automated, with data extracted with PCT. There was a 60% reduction in the number of patient delays in the six months after PCT release. PCT was suc-cessfully implemented for use on all external beam treatment plans in our clinic. While the number of errors found during the physics check did not decrease, automation of checks increased visibility of errors during the physics check, which led to decreased patient delays. The methods used here can be applied to any TMS and TPS that allows queries of the database.

SafetyNet: Streamlining and Automating QA in radiotherapy.

Proper quality assurance (QA) of the radiotherapy process can be time-consuming and expensive. Many QA efforts, such as data export and import, are inefficient when done by humans. Additionally, humans can be unreliable, lose attention, and fail to complete critical steps that are required for smooth operations. In our group we have sought to break down the QA tasks into separate steps and to automate those steps that are better done by software running autonomously or at the instigation of a human. A team of medical physicists and software engineers worked together to identify opportunities to streamline and automate QA. Development efforts follow a formal cycle of writing software requirements, developing software, testing and commissioning. The clinical release process is separated into clinical evaluation testing, training, and finally clinical release. We have improved six processes related to QA and safety. Steps that were previously performed by humans have been automated or streamlined to increase first-time quality, reduce time spent by humans doing low-level tasks, and expedite QA tests. Much of the gains were had by automating data transfer, implementing computer-based checking and automation of systems with an event-driven framework. These coordinated efforts by software engineers and clinical physicists have resulted in speed improvements in expediting patient-sensitive QA tests.

Integrating local and distant radiation-induced lung injury: Development and validation of a predictive model for ventilation loss.

BACKGROUND: Investigations on radiation-induced lung injury (RILI) have predominantly focused on local effects, primarily those associated with radiation damage to lung parenchyma. However, recent studies from our group and others have revealed that radiation-induced damage to branching serial structures such as airways and vessels may also have a substantial impact on post-radiotherapy (RT) lung function. Furthermore, recent results from multiple functional lung avoidance RT trials, although promising, have demonstrated only modest toxicity reduction, likely because they were primarily focused on dose avoidance to lung parenchyma. These observations emphasize the critical need for predictive dose-response models that effectively incorporate both local and distant RILI effects. PURPOSE: We develop and validate a predictive model for ventilation loss after lung RT. This model, referred to as P+A, integrates local (parenchyma [P]) and distant (central and peripheral airways [A]) radiation-induced damage, modeling partial (narrowing) and complete (collapse) obstruction of airways. METHODS: In an IRB-approved prospective study, pre-RT breath-hold CTs (BHCTs) and pre- and one-year post-RT 4DCTs were acquired from lung cancer patients treated with definitive RT. Up to 13 generations of airways were automatically segmented on the BHCTs using a research virtual bronchoscopy software. Ventilation maps derived from the 4DCT scans were utilized to quantify pre- and post-RT ventilation, serving, respectively, as input data and reference standard (RS) in model validation. To predict ventilation loss solely due to parenchymal damage (referred to as P model), we used a normal tissue complication probability (NTCP) model. Our model used this NTCP-based estimate and predicted additional loss due radiation-induced partial or complete occlusion of individual airways, applying fluid dynamics principles and a refined version of our previously developed airway radiosensitivity model. Predictions of post-RT ventilation were estimated in the sublobar volumes (SLVs) connected to the terminal airways. To validate the model, we conducted a k-fold cross-validation. Model parameters were optimized as the values that provided the lowest root mean square error (RMSE) between predicted post-RT ventilation and the RS for all SLVs in the training data. The performance of the P+A and the P models was evaluated by comparing their respective post-RT ventilation values with the RS predictions. Additional evaluation using various receiver operating characteristic (ROC) metrics was also performed. RESULTS: We extracted a dataset of 560 SLVs from four enrolled patients. Our results demonstrated that the P+A model consistently outperformed the P model, exhibiting RMSEs that were nearly half as low across all patients (13 ± 3 percentile for the P+A model vs. 24 ± 3 percentile for the P model on average). Notably, the P+A model aligned closely with the RS in ventilation loss distributions per lobe, particularly in regions exposed to doses ≥13.5 Gy. The ROC analysis further supported the superior performance of the P+A model compared to the P model in sensitivity (0.98 vs. 0.07), accuracy (0.87 vs. 0.25), and balanced predictions. CONCLUSIONS: These early findings indicate that airway damage is a crucial factor in RILI that should be included in dose-response modeling to enhance predictions of post-RT lung function.

Factors associated with acute esophagitis during radiation therapy for lung cancer.

INTRODUCTION: Limiting acute esophagitis remains a clinical challenge during the treatment of locally advanced non-small cell lung cancer (NSCLC). METHODS: Demographic, dosimetric, and acute toxicity data were prospectively collected for patients undergoing definitive radiation therapy +/- chemotherapy for stage II-III NSCLC from 2012 to 2022 across a statewide consortium. Logistic regression models were used to characterize the risk of grade 2 + and 3 + esophagitis as a function of dosimetric and clinical covariates. Multivariate regression models were fitted to predict the 50 % risk of grade 2 esophagitis and 3 % risk of grade 3 esophagitis. RESULTS: Of 1760 patients, 84.2 % had stage III disease and 85.3 % received concurrent chemotherapy. 79.2 % of patients had an ECOG performance status ≤ 1. Overall rates of acute grade 2 + and 3 + esophagitis were 48.4 % and 2.2 %, respectively. On multivariate analyses, performance status, mean esophageal dose (MED) and minimum dose to the 2 cc of esophagus receiving the highest dose (D2cc) were significantly associated with grade 2 + and 3 + esophagitis. Concurrent chemotherapy was associated with grade 2 + but not grade 3 + esophagitis. For all patients, MED of 29 Gy and D2cc of 61 Gy corresponded to a 3 % risk of acute grade 3 + esophagitis. For patients receiving chemotherapy, MED of 22 Gy and D2cc of 50 Gy corresponded to a 50 % risk of acute grade 2 + esophagitis. CONCLUSIONS: Performance status, concurrent chemotherapy, MED and D2cc are associated with acute esophagitis during definitive treatment of NSCLC. Models that quantitatively account for these factors can be useful in individualizing radiation plans.

Predictors of Early Hospice or Death in Patients With Inoperable Lung Cancer Treated With Curative Intent.

INTRODUCTION: Treatment for inoperable stage II to III non-small cell lung cancer (NSCLC) involves chemo-radiotherapy (CRT). However, some patients transition to hospice or die early during their treatment course. We present a model to prognosticate early poor outcomes in NSCLC patients treated with curative-intent CRT. METHODS AND MATERIALS: Across a statewide consortium, data was prospectively collected on stage II to III NSCLC patients who received CRT between 2012 and 2019. Early poor outcomes included hospice enrollment or death within 3 months of completing CRT. Logistic regression models were used to assess predictors in prognostic models. LASSO regression with multiple imputation were used to build a final multivariate model, accounting for missing covariates. RESULTS: Of the 2267 included patients, 128 experienced early poor outcomes. Mean age was 71 years and 59% received concurrent chemotherapy. The best predictive model, created parsimoniously from statistically significant univariate predictors, included age, ECOG, planning target volume (PTV), mean heart dose, pretreatment lack of energy, and cough. The estimated area under the ROC curve for this multivariable model was 0.71, with a negative predictive value of 95%, specificity of 97%, positive predictive value of 23%, and sensitivity of 16% at a predicted risk threshold of 20%. CONCLUSIONS: This multivariate model identified a combination of clinical variables and patient reported factors that may identify individuals with inoperable NSCLC undergoing curative intent chemo-radiotherapy who are at higher risk for early poor outcomes.

Intricacies of Human-AI Interaction in Dynamic Decision-Making for Precision Oncology: A Case Study in Response-Adaptive Radiotherapy.

Background: Adaptive treatment strategies that can dynamically react to individual cancer progression can provide effective personalized care. Longitudinal multi-omics information, paired with an artificially intelligent clinical decision support system (AI-CDSS) can assist clinicians in determining optimal therapeutic options and treatment adaptations. However, AI-CDSS is not perfectly accurate, as such, clinicians' over/under reliance on AI may lead to unintended consequences, ultimately failing to develop optimal strategies. To investigate such collaborative decision-making process, we conducted a Human-AI interaction case study on response-adaptive radiotherapy (RT). Methods: We designed and conducted a two-phase study for two disease sites and two treatment modalities-adaptive RT for non-small cell lung cancer (NSCLC) and adaptive stereotactic body RT for hepatocellular carcinoma (HCC)-in which clinicians were asked to consider mid-treatment modification of the dose per fraction for a number of retrospective cancer patients without AI-support (Unassisted Phase) and with AI-assistance (AI-assisted Phase). The AI-CDSS graphically presented trade-offs in tumor control and the likelihood of toxicity to organs at risk, provided an optimal recommendation, and associated model uncertainties. In addition, we asked for clinicians' decision confidence level and trust level in individual AI recommendations and encouraged them to provide written remarks. We enrolled 13 evaluators (radiation oncology physicians and residents) from two medical institutions located in two different states, out of which, 4 evaluators volunteered in both NSCLC and HCC studies, resulting in a total of 17 completed evaluations (9 NSCLC, and 8 HCC). To limit the evaluation time to under an hour, we selected 8 treated patients for NSCLC and 9 for HCC, resulting in a total of 144 sets of evaluations (72 from NSCLC and 72 from HCC). Evaluation for each patient consisted of 8 required inputs and 2 optional remarks, resulting in up to a total of 1440 data points. Results: AI-assistance did not homogeneously influence all experts and clinical decisions. From NSCLC cohort, 41 (57%) decisions and from HCC cohort, 34 (47%) decisions were adjusted after AI assistance. Two evaluations (12%) from the NSCLC cohort had zero decision adjustments, while the remaining 15 (88%) evaluations resulted in at least two decision adjustments. Decision adjustment level positively correlated with dissimilarity in decision-making with AI [NSCLC: ρ = 0.53 ( p < 0.001); HCC: ρ = 0.60 ( p < 0.001)] indicating that evaluators adjusted their decision closer towards AI recommendation. Agreement with AI-recommendation positively correlated with AI Trust Level [NSCLC: ρ = 0.59 ( p < 0.001); HCC: ρ = 0.7 ( p < 0.001)] indicating that evaluators followed AI's recommendation if they agreed with that recommendation. The correlation between decision confidence changes and decision adjustment level showed an opposite trend [NSCLC: ρ = -0.24 ( p = 0.045), HCC: ρ = 0.28 ( p = 0.017)] reflecting the difference in behavior due to underlying differences in disease type and treatment modality. Decision confidence positively correlated with the closeness of decisions to the standard of care (NSCLC: 2 Gy/fx; HCC: 10 Gy/fx) indicating that evaluators were generally more confident in prescribing dose fractionations more similar to those used in standard clinical practice. Inter-evaluator agreement increased with AI-assistance indicating that AI-assistance can decrease inter-physician variability. The majority of decisions were adjusted to achieve higher tumor control in NSCLC and lower normal tissue complications in HCC. Analysis of evaluators' remarks indicated concerns for organs at risk and RT outcome estimates as important decision-making factors. Conclusions: Human-AI interaction depends on the complex interrelationship between expert's prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. The collaborative decision-making process can be summarized as follows: (i) some clinicians may not believe in an AI system, completely disregarding its recommendation, (ii) some clinicians may believe in the AI system but will critically analyze its recommendations on a case-by-case basis; (iii) when a clinician finds that the AI recommendation indicates the possibility for better outcomes they will adjust their decisions accordingly; and (iv) When a clinician finds that the AI recommendation indicate a worse possible outcome they will disregard it and seek their own alternative approach.

Phase II Trial Assessing Toxicity of Personalized Response-Based Radiation Treatment in Patients with Locally Advanced Non-Small Cell Lung Cancer.

INTRODUCTION: Local failure rates after treatment for locally advanced non-small-cell lung cancer (NSCLC) remain high. Efforts to improve local control with uniform dose-escalation or dose-escalation to mid-treatment PET-avid residual disease have been limited by heightened toxicity. This trial aimed to refine response-based adaptive radiation (RT) and minimize toxicity by incorporating FDG-PET and V/Q SPECT imaging mid-treatment. METHODS: 47 patients with Stage IIA-III unresectable NSCLC were prospectively enrolled in this single-institution trial (NCT02492867). Patients received concurrent chemoradiation with personalized response-based adaptive RT over 30 fractions incorporating V/Q SPECT and FDG-PET. The first 21 fractions (46.2Gy at 2.2 Gy/fraction) were delivered to the tumor while minimizing dose to SPECT-defined functional lung. The plan was then adapted for the final 9 fractions (2.2-3.8Gy/fraction) up to a total of 80.4Gy, based on mid-treatment FDG-PET tumor response to escalate dose to residual tumor while minimizing dose to SPECT-defined functional lung. Non-progressing patients received consolidative carboplatin/paclitaxel or durvalumab. The primary endpoint of the study was ≥ grade 2 lung and esophageal toxicities. Secondary endpoints included time to local progression, tumor response, and overall survival. RESULTS: At one year post-treatment, the rates of grade 2 and grade 3 pneumonitis were 21.3% and 2.1%, respectively, with no difference in pneumonitis rates among patients who received and did not receive adjuvant durvalumab (p=0.74). While there were no grade 3 esophageal-related toxicities, 66.0% of patients experienced grade 2 esophagitis. 1- and 2-year local control rates were 94.5% (95% CI, 87.4% - 100%) and 87.5% (95% CI, 76.7% - 100%), respectively. Overall survival was 82.8% (95% CI, 72.6% -94.4%) at 1 year and 62.3% (95% CI, 49.6%-78.3%) at 2 years. CONCLUSIONS: Response-based adaptive dose-escalation accounting for tumor change and normal tissue function during treatment provided excellent local control, comparable toxicity to standard chemoradiation, and did not increase toxicity with adjuvant immunotherapy.

The Effect of Stereotactic Body Radiation Therapy for Hepatocellular Cancer on Regional Hepatic Liver Function.

PURPOSE: To investigate direct radiation dose-related and inflammation-mediated regional hepatic function losses after stereotactic body radiation therapy (SBRT) in patients with hepatocellular carcinoma (HCC) and poor liver function. METHODS AND MATERIALS: Twenty-four patients with HCC enrolled on an IRB-approved adaptive SBRT trial had liver dynamic gadoxetic acid-enhanced magnetic resonance imaging and blood sample collections before and 1 month after SBRT. Gadoxetic acid uptake rate (k1) maps were quantified for regional hepatic function and coregistered to both 2-Gy equivalent dose and physical dose distributions. Regional k1 loss patterns from before to after SBRT were analyzed for effects of dose and patient using a mixed-effects model and logistic function and were associated with pretherapy liver-function albumin-bilirubin scores. Plasma levels of tumor necrosis factor α receptor 1 (TNFR1), an inflammation marker, were correlated with mean k1 losses in the lowest dose regions by Spearman rank correlation. RESULTS: The whole group had a k1 loss rate of 0.4%/Gy (2-Gy equivalent dose); however, there was a significant random effect of patient in the mixed-effect model (P < .05). Patients with poor and good liver functions lost 50% of k1 values at 12.5 and 57.2 Gy and 33% and 16% of k1 values at the lowest dose regions (<5 Gy), respectively. The k1 losses at the lowest dose regions of individual patients were significantly correlated with their TNFR1 levels after SBRT (P < .02). CONCLUSIONS: The findings suggest that regional hepatic function losses after SBRT in patients with HCC include both direct radiation dose-dependent and inflammation-mediated effects, which could influence how to manage these patients to preserve their liver function after SBRT.

Deep learning prediction of post-SBRT liver function changes and NTCP modeling in hepatocellular carcinoma based on DGAE-MRI.

BACKGROUND: Stereotactic body radiation therapy (SBRT) produces excellent local control for patients with hepatocellular carcinoma (HCC). However, the risk of toxicity for normal liver tissue is still a limiting factor. Normal tissue complication probability (NTCP) models have been proposed to estimate the toxicity with the assumption of uniform liver function distribution, which is not optimal. With more accurate regional liver functional imaging available for individual patient, we can improve the estimation and be more patient-specific. PURPOSE: To develop normal tissue complication probability (NTCP) models using pre-/during-treatment (RT) dynamic Gadoxetic Acid-enhanced (DGAE) MRI for adaptation of RT in a patient-specific manner in hepatocellular cancer (HCC) patients who receive SBRT. METHODS: 24 of 146 HCC patients who received SBRT underwent DGAE MRI. Physical doses were converted into EQD2 for analysis. Voxel-by-voxel quantification of the contrast uptake rate (k1) from DGAE-MRI was used to quantify liver function. A logistic dose-response model was used to estimate the fraction of liver functional loss, and NTCP was estimated using the cumulative functional reserve model for changes in Child-Pugh (C-P) scores. Model parameters were calculated using maximum-likelihood estimations. During-RT liver functional maps were predicted from dose distributions and pre-RT k1 maps with a conditional Wasserstein generative adversarial network (cWGAN). Imaging prediction quality was assessed using root-mean-square error (RMSE) and structural similarity (SSIM) metrics. The dose-response and NTCP were fit on both original and cWGAN predicted images and compared using a Wilcoxon signed-rank test. RESULTS: Logistic dose response models for changes in k1 yielded D50 of 35.2 (95% CI: 26.7-47.5) Gy and k of 0.62 (0.49-0.75) for the whole population. The high baseline ALBI (poor liver function) subgroup showed a significantly smaller D50 of 11.7 (CI: 9.06-15.4) Gy and larger k of 0.96 (CI: 0.74-1.22) compared to a low baseline ALBI (good liver function) subgroup of 54.8 (CI: 38.3-79.1) Gy and 0.59 (CI: 0.48-0.74), with p-values of < 0.001 and = 0.008, respectively, which indicates higher radiosensitivity for the worse baseline liver function cohort. Subset analyses were also performed for high/low baseline CP subgroups. The corresponding NTCP models showed good agreement for the fit parameters between cWGAN predicted and the ground-truth during-RT images with no statistical differences for low ALBI subgroup. CONCLUSIONS: NTCP models which incorporate voxel-wise functional information from DGAE-MRI k1 maps were successfully developed and feasibility was demonstrated in a small patient cohort. cWGAN predicted functional maps show promise for estimating localized patient-specific response to RT and warrant further validation in a larger patient cohort.

Cardiac and Pulmonary Dosimetric Parameters in Patients With Lung Cancer Undergoing Postoperative Radiation Therapy Across a Statewide Consortium.

PURPOSE: The recently published Lung Adjuvant Radiotherapy Trial (Lung ART) reported increased rates of cardiac and pulmonary toxic effects in the postoperative radiation therapy (PORT) arm. It remains unknown whether the dosimetric parameters reported in Lung ART are representative of contemporary real-world practice, which remains relevant for patients undergoing PORT for positive surgical margins. The purpose of this study was to examine heart and lung dose exposure in patients receiving PORT for non-small cell lung cancer across a statewide consortium. METHODS AND MATERIALS: From 2012 to 2022, demographic and dosimetric data were prospectively collected for 377 patients at 27 academic and community centers within the Michigan Radiation Oncology Quality Consortium undergoing PORT for nonmetastatic non-small cell lung cancer. Dosimetric parameters for target coverage and organ-at-risk exposure were calculated using data from dose-volume histograms, and rates of 3-dimensional conformal radiation therapy (3D-CRT) and intensity modulated radiation therapy (IMRT) utilization were assessed. RESULTS: Fifty-one percent of patients in this cohort had N2 disease at the time of surgery, and 25% had a positive margin. Sixty-six percent of patients were treated with IMRT compared with 32% with 3D-CRT. The planning target volume was significantly smaller in patients treated with 3D-CRT (149.2 vs 265.4 cm3; P < .0001). The median mean heart dose for all patients was 8.7 Gy (interquartile range [IQR], 3.5-15.3 Gy), the median heart volume receiving at least 5 Gy (V5) was 35.2% (IQR, 18.5%-60.2%), and the median heart volume receiving at least 35 Gy (V35) was 9% (IQR, 3.2%-17.7%). The median mean lung dose was 11.4 Gy (IQR, 8.1-14.3 Gy), and the median lung volume receiving at least 20 Gy (V20) was 19.6% (IQR, 12.7%-25.4%). These dosimetric parameters did not significantly differ by treatment modality (IMRT vs 3D-CRT) or in patients with positive versus negative surgical margins. CONCLUSIONS: With increased rates of IMRT use, cardiac and lung dosimetric parameters in this statewide consortium were slightly lower than those reported in Lung ART. These data provide useful benchmarks for treatment planning in patients undergoing PORT for positive surgical margins.

Real-time, volumetric imaging of radiation dose delivery deep into the liver during cancer treatment.

Ionizing radiation acoustic imaging (iRAI) allows online monitoring of radiation's interactions with tissues during radiation therapy, providing real-time, adaptive feedback for cancer treatments. We describe an iRAI volumetric imaging system that enables mapping of the three-dimensional (3D) radiation dose distribution in a complex clinical radiotherapy treatment. The method relies on a two-dimensional matrix array transducer and a matching multi-channel preamplifier board. The feasibility of imaging temporal 3D dose accumulation was first validated in a tissue-mimicking phantom. Next, semiquantitative iRAI relative dose measurements were verified in vivo in a rabbit model. Finally, real-time visualization of the 3D radiation dose delivered to a patient with liver metastases was accomplished with a clinical linear accelerator. These studies demonstrate the potential of iRAI to monitor and quantify the 3D radiation dose deposition during treatment, potentially improving radiotherapy treatment efficacy using real-time adaptive treatment.

Knowledge-Based Quality Assurance and Model Maintenance in Lung Cancer Radiation Therapy in a Statewide Quality Consortium of Academic and Community Practice Centers.

PURPOSE: Locally advanced lung cancer (LALC) treatment planning is often complex due to challenging tradeoffs related to large targets near organs at risk, making the judgment of plan quality difficult. The purpose of this work was to update and maintain a multi-institutional knowledge-based planning (KBP) model developed by a statewide consortium of academic and community practices for use as a plan quality assurance (QA) tool. METHODS AND MATERIALS: Sixty LALC volumetric-modulated arc therapy plans from 2021 were collected from 24 institutions. Plan quality was scored, with high-quality clinical (HQC) plans selected to update a KBP model originally developed in 2017. The model was validated via automated KBP planning, with 20 cases excluded from the model. Differences in dose-volume histogram metrics in the clinical plans, 2017 KBP model plans, and 2022 KBP model plans were compared. Twenty recent clinical cases not meeting consortium quality metrics were replanned with the 2022 model to investigate potential plan quality improvements. RESULTS: Forty-seven plans were included in the final KBP model. Compared with the clinical plans, the 2022 model validation plans improved 60%, 65%, and 65% of the lung V20Gy, mean heart dose, and spinal canal D0.03cc metrics, respectively. The 2022 model showed improvements from the 2017 model in hot spot management at the cost of greater lung doses. Of the 20 recent cases not meeting quality metrics, 40% of the KBP model-replanned cases resulted in acceptable plans, suggesting potential clinical plan improvements. CONCLUSIONS: A multi-institutional KBP model was updated using plans from a statewide consortium. Multidisciplinary plan review resulted in HQC model training plans and model validation resulted in acceptable quality plans. The model proved to be effective at identifying potential plan quality improvements. Work is ongoing to develop web-based training plan review tools and vendor-agnostic platforms to provide the model as a QA tool statewide.

Gender-Based Discrimination and Sexual Harassment in Medical Physics.

PURPOSE: Gender-based discrimination and sexual harassment have been well-studied in the fields of science, technology, engineering, math, and medicine. However, less is known about these topics and their effect within the profession of medical physics. We aimed to better understand and clarify the views and experiences of practicing medical physicists and medical physics residents regarding gender-based discrimination and sexual harassment. METHODS AND MATERIALS: We conducted in-depth, semistructured, and confidential interviews with 32 practicing medical physicists and medical physics residents across the United States. The interviews were broad and covered the topics of discrimination, mentorship, and work/life integration. All participants were associated with a department with a residency program accredited by the Commission on Accreditation of Medical Physics Education Programs and had appointments with a clinical component. RESULTS: Participants shared views about gender-based discrimination and sexual harassment that were polarized. Some perceived that discrimination and harassment were a current concern within medical physics, while some either perceived that they were not a concern or that discrimination positively affected women and minoritized populations. Many participants shared personal experiences of discrimination and harassment, including those related to unequal compensation, discrimination against mothers, discrimination during the hiring process, gender-biased assumptions about behaviors or goals, communication biases, and overt and persistent sexual harassment. CONCLUSIONS: There is an urgent need to acknowledge, better understand, and address gender-based discrimination and sexual harassment in the field of medical physics.

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS).

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient's pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN's RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.