Search

PURPOSE: Small cell lung cancer (SCLC) is characterized by rapid progression after platinum resistance. Circulating tumor (ctDNA) dynamics early in treatment may help determine platinum sensitivity. MATERIALS AND METHODS: Serial plasma samples were collected from patients receiving platinum-based chemotherapy for SCLC on the first 3 days of cycle one and on the first days of subsequent cycles with paired samples collected both before and again after infusions. Tumor-informed plasma analysis was carried out using CAncer Personalized Profiling by deep Sequencing (CAPP-Seq). The mean variant allele frequency (VAF) of all pretreatment mutations was tracked in subsequent blood draws and correlated with radiologic response. RESULTS: ctDNA kinetics were assessed in 122 samples from 21 patients. Pretreatment VAF did not differ significantly between patients who did and did not respond to chemotherapy (mean 22.5% v 4.6%, P =.17). A slight increase in ctDNA on cycle 1, day 1 immediately post-treatment was seen in six of the seven patients with available draws (fold change from baseline: 1.01-1.44), half of whom achieved a response. All patients who responded had a >2-fold decrease in mean VAF on cycle 2 day 1 (C2D1). Progression-free survival (PFS) and overall survival (OS) were significantly longer in patients with a >2-fold decrease in mean VAF after one treatment cycle (6.8 v 2.6 months, log-rank P =.0004 and 21.7 v 6.4 months, log rank P =.04, respectively). CONCLUSION: A >2-fold decrease in ctDNA concentration was observed by C2D1 in all patients who were sensitive to platinum-based therapy and was associated with longer PFS and OS. [ABSTRACT FROM AUTHOR]

Background: In radiotherapy, real‐time tumor tracking can verify tumor position during beam delivery, guide the radiation beam to target the tumor, and reduce the chance of a geometric miss. Markerless kV x‐ray image‐based tumor tracking is challenging due to the low tumor visibility caused by tumor‐obscuring structures. Developing a new method to enhance tumor visibility for real‐time tumor tracking is essential. Purpose: To introduce a novel method for markerless kV image‐based tracking of lung tumors via deep learning‐based target decomposition. Methods: We utilized a conditional Generative Adversarial Network (cGAN), known as Pix2Pix, to build a patient‐specific model and generate the synthetic decomposed target image (sDTI) to enhance tumor visibility on the real‐time kV projection images acquired by the onboard kV imager equipped on modern linear accelerators. We used 4DCT simulation images to generate the digitally reconstructed radiograph (DRR) and DTI image pairs for model training. We augmented the training dataset by randomly shifting the 4DCT in the superior‐inferior, anterior‐posterior, and left‐right directions during the DRR and DTI generation process. We performed real‐time 2D tumor tracking via template matching between the DTI generated from the CT simulation and the sDTI generated from the real‐time kV projection images. We validated the proposed method using nine patients' datasets with implanted beacons near the tumor. Results: The sDTI can effectively improve the image contrast around the lung tumors on the kV projection images for the nine patients. With the beacon motion as ground truth, the tracking errors were on average 0.8 ± 0.7 mm in the superior‐inferior (SI) direction and 0.9 ± 0.8 mm in the in‐plane left‐right (IPLR) direction. The percentage of successful tracking, defined as a tracking error less than 2 mm in the SI direction, is 92.2% on the 4312 tested images. The patient‐specific model took approximately 12 h to train. During testing, it took approximately 35 ms to generate one sDTI, and 13 ms to perform the tumor tracking using template matching. Conclusions: Our method offers the potential solution for nearly real‐time markerless lung tumor tracking. It achieved a high level of accuracy and an impressive tracking rate. Further development of 3D lung tumor tracking is warranted. [ABSTRACT FROM AUTHOR]

Simple Summary: We studied the feasibility and safety of using bronchoscopically implanted electromagnetic transponders to monitor deep inspiration breath hold (DIBH) for thoracic radiation therapy (RT) of primary lung cancers or lung metastases. Three transponders were implanted near the tumor, followed by CT simulation. The initial gating window was ±5 mm; in a second cohort, the window was incrementally reduced to determine the smallest feasible gating window: this was identified to be ±3 mm. Among the 48 patients enrolled, transponder-guided DIBH was feasible in all but two patients (96% feasible), where it failed because the distance between the transponders and the antenna was >19 cm. Toxicities at least possibly related to transponders or the implantation procedure were grade 2 in six patients, grade 3 in three patients, and grade 4 in one patient. Toxicities at least possibly related to RT were grade 2 in 18 patients and grade 3 in four patients. Transponder-guided DIBH is a feasible and safe approach for delivering thoracic RT. Background: Electromagnetic transponders bronchoscopically implanted near the tumor can be used to monitor deep inspiration breath hold (DIBH) for thoracic radiation therapy (RT). The feasibility and safety of this approach require further study. Methods: We enrolled patients with primary lung cancer or lung metastases. Three transponders were implanted near the tumor, followed by simulation with DIBH, free breathing, and 4D-CT as backup. The initial gating window for treatment was ±5 mm; in a second cohort, the window was incrementally reduced to determine the smallest feasible gating window. The primary endpoint was feasibility, defined as completion of RT using transponder-guided DIBH. Patients were followed for assessment of transponder- and RT-related toxicity. Results: We enrolled 48 patients (35 with primary lung cancer and 13 with lung metastases). The median distance of transponders to tumor was 1.6 cm (IQR 0.6–2.8 cm). RT delivery ranged from 3 to 35 fractions. Transponder-guided DIBH was feasible in all but two patients (96% feasible), where it failed because the distance between the transponders and the antenna was >19 cm. Among the remaining 46 patients, 6 were treated prone to keep the transponders within 19 cm of the antenna, and 40 were treated supine. The smallest feasible gating window was identified as ±3 mm. Thirty-nine (85%) patients completed one year of follow-up. Toxicities at least possibly related to transponders or the implantation procedure were grade 2 in six patients (six incidences, cough and hemoptysis), grade 3 in three patients (five incidences, cough, dyspnea, pneumonia, and supraventricular tachycardia), and grade 4 pneumonia in one patient (occurring a few days after implantation but recovered fully and completed RT). Toxicities at least possibly related to RT were grade 2 in 18 patients (41 incidences, most commonly cough, fatigue, and pneumonitis) and grade 3 in four patients (seven incidences, most commonly pneumonia), and no patients had grade 4 or higher toxicity. Conclusions: Bronchoscopically implanted electromagnetic transponder–guided DIBH lung RT is feasible and safe, allowing for precise tumor targeting and reduced normal tissue exposure. Transponder–antenna distance was the most common challenge due to a limited antenna range, which could sometimes be circumvented by prone positioning. [ABSTRACT FROM AUTHOR]

PURPOSE: Small cell lung cancer (SCLC) often metastasizes to the brain and has poor prognosis. SCLC subtypes distinguished by expressing transcriptional factors ASCL1 or NEUROD1 have been identified. This study investigates the impact of transcription factor–defined SCLC subtype on incidence and outcomes of brain metastases (BMs). METHODS: Patients with SCLC with ASCL1 (A) and NEUROD1 (N) immunohistochemical expression status were identified and classified: (1) A+/N–, (2) A+/N+, (3) A–/N+, and (4) A–/N–. Cumulative incidence competing risk analyses were used to assess incidence of CNS progression. Cox proportional hazards models were used for multivariable analyses of overall survival (OS) and CNS progression-free survival (CNS-PFS). RESULTS: Of 164 patients, most were either A+/N– or A+/N+ (n = 62, n = 63, respectively). BMs were present at diagnosis in 24 patients (15%). Among them, the 12-month cumulative incidence of subsequent CNS progression was numerically highest for A+/N– (50% [95% CI, 10.5 to 74.7]; P =.47). Among those BM-free at diagnosis, the 12-month cumulative incidence of CNS progression was numerically the highest for A+/N– (16% [95% CI, 7.5 to 27.9]) and A–/N+ (9.1% [95% CI, 0.0 to 34.8]; P =.20). Both subtypes, A+/N– and A–/N+, had worse OS compared with A+/N+ (A+/N–: hazard ratio [HR], 1.62 [95% CI, 1.01 to 2.51]; P <.05; A–/N+: HR, 3.02 [95% CI, 1.35 to 6.76]; P =.007). Excellent response rates (28, 65% CR/PR) across subtypes were seen in patients who had CNS-directed radiotherapy versus systemic therapy alone (9, 36% CR/PR). CONCLUSION: To our knowledge, this report is the first to investigate CNS-specific outcomes based on transcription factor subtypes in patients with SCLC. BM-free patients at diagnosis with A+/N– or A–/N+ subtypes had worse outcomes compared with those with transcriptional factor coexpression. Further investigation into the mechanisms and implications of SCLC subtyping on CNS-specific outcomes is warranted to ultimately guide personalized care. This study investigates the impact of transcription factor-defined subtypes in small cell lung cancer (SCLC) on brain metastasis (BM) incidence and outcomes. [ABSTRACT FROM AUTHOR]

Purpose: For patients receiving lung stereotactic ablative radiotherapy (SABR), evidence suggests that high peritumor density predicts an increased risk of microscopic disease (MDE) and local-regional failure, but only if there is low or heterogenous incidental dose surrounding the tumor (GTV). A data-mining method (Cox-per-radius) has been developed to investigate this dose-density interaction. We apply the method to predict local relapse (LR) and regional failure (RF) in patients with non-small cell lung cancer. Methods: 199 patients treated in a routine setting were collated from a single institution for training, and 76 patients from an external institution for validation. Three density metrics (mean, 90th percentile, standard deviation (SD)) were studied in 1mm annuli between 0.5cm inside and 2cm outside the GTV boundary. Dose SD and fraction of volume receiving less than 30Gy were studied in annuli 0.5-2cm outside the GTV to describe incidental MDE dosage. Heat-maps were created that correlate with changes in LR and RF rates due to the interaction between dose heterogeneity and density at each distance combination. Regions of significant improvement were studied in Cox proportional hazards models, and explored with and without re-fitting in external data. Correlations between the dose component of the interaction and common dose metrics were reported. Results: Local relapse occurred at a rate of 6.5% in the training cohort, and 18% in the validation cohort, which included larger and more centrally located tumors. High peritumor density in combination with high dose variability (0.5 - 1.6cm) predicts LR. No interactions predicted RF. The LR interaction improved the predictive ability compared to using clinical variables alone (optimism-adjusted C-index; 0.82 vs 0.76). Re-fitting model coefficients in external data confirmed the importance of this interaction (C-index; 0.86 vs 0.76). Dose variability in the 0.5-1.6 cm annular region strongly correlates with heterogeneity inside the target volume (SD; r = 0.53 training, r = 0.65 validation). Conclusion: In these real-world cohorts, the combination of relatively high peritumor density and high dose variability predicts increase in LR, but not RF, following lung SABR. This external validation justifies potential use of the model to increase low-dose CTV margins for high-risk patients. [ABSTRACT FROM AUTHOR]

Although concurrent chemoradiation (CRT) and durvalumab consolidation has become a standard treatment for stage III non-small cell lung cancer (NSCLC), clinicopathologic and genomic factors associated with its efficacy remain poorly characterized. Here, in a multi-institutional retrospective cohort study of 328 patients treated with CRT and durvalumab, we identify that very high PD-L1 tumor proportion score (TPS) expression (≥ 90%) and increased tumor mutational burden (TMB) are independently associated with prolonged disease control. Additionally, we identify the impact of pneumonitis and its timing on disease outcomes among patients who discontinue durvalumab: compared to patients who experienced early-onset pneumonitis (< 3 months) leading to durvalumab discontinuation, patients with late-onset pneumonitis had a significantly longer PFS (12.7 months vs not reached; HR 0.24 [95% CI, 0.10 to 0.58]; P = 0.001) and overall survival (37.2 months vs not reached; HR 0.26 [95% CI, 0.09 to 0.79]; P = 0.017). These findings suggest that opportunities exist to improve outcomes in patients with lower PD-L1 and TMB levels, and those at highest risk for pneumonitis. Concurrent chemoradiation and durvalumab is standard of care for stage III non-small cell lung cancer, however, efficacy is variable. Here, the authors show PD-L1 tumor proportion score expression and increased tumor mutational burden are predictive of response and that early-onset pneumonitis leading to durvalumab discontinuation is associated with poor survival. [ABSTRACT FROM AUTHOR]

Purpose: Stereotactic body proton therapy (SBPT) is an emerging treatment strategy for lung tumors that aims to combine the excellent local control benefits of ultra-hypofractionation with the physical advantages of protons, which reduce the integral dose to organs at risk (OARs) compared to photons. To date, however, very little data delivering SBPT in 5 or fewer fractions to lung tumors have been reported. Given that photon stereotactic body radiation therapy can struggle to deliver ablative doses to high-risk tumors (i.e., central/ultra-central location, prior in-field radiation, tumor size >5 cm, or the presence of severe pulmonary comorbidities) while adhering to OAR dose constraints, we hypothesized that SBPT would be an effective alternative for patients with high-risk tumors. Methods and Materials: Twenty-seven high-risk patients with 29 lung tumors treated with SBPT at the New York Proton Center between December 2019 and November 2022 were retrospectively identified. Patients were divided into three major subgroups: early-stage non-small cell lung cancer (NSCLC), locally recurrent NSCLC, and metastatic cancer from lung cancer or other histologies. Patient characteristics were reported using descriptive statistics, actuarial methods were used to quantify disease control rates, and toxicities were scored using CTCAE v 5.0. Results: The most common high-risk indications for SBPT were central/ultra-central tumor location (69.0%), severe COPD (48.1%), reirradiation (44.4%), significant pulmonary fibrosis (22.2%), and large tumor size > 5 cm (18.5%). In total, 96.6% of tumors were fully covered by the prescription dose without compromising target coverage. Three-year actuarial rates of local control for early-stage NSCLC, locally recurrent NSCLC, and metastatic patients were 89%, 100%, and 43%, respectively. Three-year actuarial rates of regional control were 89%, 67%, and 86%. Three-year actuarial rates of distant metastasis-free survival were 79%, 100%, and 0%. Two patients (7.4%), both of whom had clinically significant baseline interstitial lung disease and pre-treatment continuous oxygen demand, experienced grade =2 pulmonary toxicity (1 grade 3, 1 grade 5). There were no acute or late grade =2 toxicities related to esophagitis, cardiac injury, airway injury, pulmonary fibrosis, bronchopulmonary hemorrhage or brachial plexopathy. Conclusions: In the largest study of proton SBRT reported to date, SBPT has a favorable toxicity profile while being an effective approach for treating most high-risk tumors without requiring dose de-escalation or compromising tumor coverage and warrants further investigation. [ABSTRACT FROM AUTHOR]

As patient breathing irregularities can introduce a large uncertainty in targeting the internal tumor volume (ITV) of lung cancer patients, and thereby affect treatment quality, this study evaluates dose tolerance of tumor motion amplitude variations in ITV-based volumetric modulated arc therapy (VMAT). A motion-incorporated planning technique was employed to simulate treatment delivery of 10 lung cancer patients' clinical VMAT plans using original and three scaling-up (by 0.5, 1.0, and 2.0 cm) motion waveforms from single-breath four-dimensional computed tomography (4DCT) and multi-breath time-resolved 4D magnetic resonance imaging (TR-4DMRI). The planning tumor volume (PTV = ITV + 5 mm margin) dose coverage (PTV D95%) was evaluated. The repeated waveforms were used to move the isocenter in sync with the clinical leaf motion and gantry rotation. The continuous VMAT arcs were broken down into many static beam fields at the control points (2°-interval) and the composite plan represented the motion-incorporated VMAT plan. Eight motion-incorporated plans per patient were simulated and the plan with the native 4DCT waveform was used as a control. The first (D95% ≤ 95%) and second (D95% ≤ 90%) plan breaching points due to motion amplitude increase were identified and analyzed. The PTV D95% in the motion-incorporated plans was 99.4 ± 1.0% using 4DCT, closely agreeing with the corresponding ITV-based VMAT plan (PTV D95% = 100%). Tumor motion irregularities were observed in TR-4DMRI and triggered D95% ≤ 95% in one case. For small tumors, 4 mm extra motion triggered D95% ≤ 95%, and 6–8 mm triggered D95% ≤ 90%. For large tumors, 14 mm and 21 mm extra motions triggered the first and second breaching points, respectively. This study has demonstrated that PTV D95% breaching points may occur for small tumors during treatment delivery. Clinically, it is important to monitor and avoid systematic motion increase, including baseline drift, and large random motion spikes through threshold-based beam gating. [ABSTRACT FROM AUTHOR]

Background: Diffuse pleural mesothelioma (DPM) is an aggressive malignancy that, despite recent treatment advances, has unacceptably poor outcomes. Therapeutic research in DPM is inhibited by a paucity of preclinical models that faithfully recapitulate the human disease. Methods: We established 22 patient-derived xenografts (PDX) from 22 patients with DPM and performed multi-omic analyses to deconvolute the mutational landscapes, global expression profiles, and molecular subtypes of these PDX models and compared features to those of the matched primary patient tumors. Targeted next-generation sequencing (NGS; MSK-IMPACT), immunohistochemistry, and histologic subtyping were performed on all available samples. RNA sequencing was performed on all available PDX samples. Clinical outcomes and treatment history were annotated for all patients. Platinum-doublet progression-free survival (PFS) was determined from the start of chemotherapy until radiographic/clinical progression and grouped into < or ≥ 6 months. Results: PDX models were established from both treatment naïve and previously treated samples and were noted to closely resemble the histology, genomic landscape, and proteomic profiles of the parent tumor. After establishing the validity of the models, transcriptomic analyses demonstrated overexpression in WNT/β-catenin, hedgehog, and TGF-β signaling and a consistent suppression of immune-related signaling in PDXs derived from patients with worse clinical outcomes. Conclusions: These data demonstrate that DPM PDX models closely resemble the genotype and phenotype of parental tumors, and identify pathways altered in DPM for future exploration in preclinical studies. [ABSTRACT FROM AUTHOR]

PURPOSE: Local therapy prolongs progression-free survival in patients with oligometastatic non–small-cell lung cancers treated with chemotherapy. We previously reported that local therapy also prolongs survival and time to next therapy in patients on tyrosine kinase inhibitors (TKIs) for EGFR -mutant lung adenocarcinomas. Here, we investigate the role of local therapy in patients progressing on TKIs for ALK / ROS1 / RET -rearranged lung adenocarcinomas. MATERIALS AND METHODS: Patients with advanced ALK / ROS / RET -rearranged lung adenocarcinomas who underwent radiation, surgery, or percutaneous thermal ablation from 2012 to 2020 for progression on an ALK/ROS1/RET TKI were included. Progression patterns were identified. Times from local therapy to progression, next therapy, and death were measured. RESULTS: Sixty-one patients with ALK (n = 37), ROS1 (n = 12), and RET (n = 12) fusions were identified. Patients received radiotherapy (92%), surgery (13%), and percutaneous thermal ablation (8%). Local therapy was administered for solitary/oligoprogressive (94%) or polyprogressive (6%) disease. For most patients (85%), local therapy addressed all progressing sites. The median times from any local therapy to subsequent progression and next systemic therapy were 6.8 months (95% CI, 5.1 to 8.1) and 10 months (95% CI, 8.4 to 15.3), respectively. Third or greater local therapy was associated with shorter time to progression and next therapy than first/second local therapies (hazard ratio, 4.97; P <.001 and hazard ratio, 2.48; P <.001). The median overall survival from first local therapy was 34 months (95% CI, 26 to not reached). CONCLUSION: Local therapy for progression on ALK, ROS1, or RET TKIs is associated with clinically meaningful time on continued TKI therapy beyond progression, especially earlier in the course of disease. Local therapy for PD on ALK/ROS1/RET TKIs in NSCLC led to a median of 7 months until next PD and 10 months until next systemic therapy. [ABSTRACT FROM AUTHOR]

The article discusses clinical trials on treatments for patients with malignant pleural mesotheliomas. One study compared the efficacy of cytotoxic chemotherapy with cisplatin and pemetrexed versus cisplatin alone. Another clinical trial evaluated the use of cediranib, a tyrosine kinase inhibitor (TKI) which inhibit vascular endothelial growth factor (VEGF), with cisplatin and pemetrexed. An overview of randomized trials on immune checkpoint inhibitors incorporated in chemotherapy is presented.

Accurate and robust segmentation of lung cancers from CT, even those located close to mediastinum, is needed to more accurately plan and deliver radiotherapy and to measure treatment response. Therefore, we developed a new cross-modality educed distillation (CMEDL) approach, using unpaired CT and MRI scans, whereby an informative teacher MRI network guides a student CT network to extract features that signal the difference between foreground and background. Our contribution eliminates two requirements of distillation methods: (i) paired image sets by using an image to image (I2I) translation and (ii) pre-training of the teacher network with a large training set by using concurrent training of all networks. Our framework uses an end-to-end trained unpaired I2I translation, teacher, and student segmentation networks. Architectural flexibility of our framework is demonstrated using 3 segmentation and 2 I2I networks. Networks were trained with 377 CT and 82 T2w MRI from different sets of patients, with independent validation (N = 209 tumors) and testing (N = 609 tumors) datasets. Network design, methods to combine MRI with CT information, distillation learning under informative (MRI to CT), weak (CT to MRI) and equal teacher (MRI to MRI), and ablation tests were performed. Accuracy was measured using Dice similarity (DSC), surface Dice (sDSC), and Hausdorff distance at the $95^{\textit {th}}$ percentile (HD95). The CMEDL approach was significantly (p < 0.001) more accurate (DSC of 0.77 vs. 0.73) than non-CMEDL methods with an informative teacher for CT lung tumor, with a weak teacher (DSC of 0.84 vs. 0.81) for MRI lung tumor, and with equal teacher (DSC of 0.90 vs. 0.88) for MRI multi-organ segmentation. CMEDL also reduced inter-rater lung tumor segmentation variabilities. [ABSTRACT FROM AUTHOR]

PURPOSE Community-academic partnerships have the potential to improve access to clinical trials for underrepresented minority patients who more often receive cancer treatment in community settings. In 2017, the Memorial Sloan Kettering (MSK) Cancer Center began opening investigator-initiated clinical trials in radiation oncology in targeted community-based partner sites with a high potential to improve diverse population accrual. This study evaluates the effectiveness of a set of implementation strategies for increasing overall communitybased enrollment and the resulting proportional enrollment of Hispanic patients on trials on the basis of availability in community-based partner sites. METHODS An interrupted time series analysis evaluating implementation strategies was conducted from April 2018 to September 2021. Descriptive analysis ofHispanic enrollment on investigator-initiated randomized therapeutic radiation trials open at community-based sites was compared with those open only at themain academic center. RESULTS Overall, 84 patients were enrolled in clinical trials in the MSK Alliance, of which 48 (56%) identified as Hispanic. The quarterly patient enrollment pre-vs postimplementation increased from 1.39 (95% CI, -3.67 to 6.46) to 9.42 (95% CI, 2.05 to 16.78; P5 .017). In the investigator-initiated randomized therapeutic radiation trials open in the MSK Alliance, Hispanic representation was 11.5% and 35.9% in twometastatic trials and 14.2% in a proton versus photon trial. Inmatched trials open only at the main academic center, Hispanic representation was 5.6%, 6.0%, and 4.0%, respectively. CONCLUSION A combination of practice-level and physician-level strategies implemented at community-based partner sites was associated with increased clinical trial enrollment, which translated to improved Hispanic representation. This supports the role Q:2 of strategic community-academic partnerships in addressing disparities in clinical trial enrollment. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the efficacy of using bronchoscopically implanted anchored electromagnetic transponders (EMTs) as surrogates for 1) tumor position and 2) repeatability of lung inflation during deep‐inspiration breath‐hold (DIBH) lung radiotherapy. Methods: Forty‐one patients treated with either hypofractionated (HF) or conventional (CF) lung radiotherapy on an IRB‐approved prospective protocol using coached DIBH were evaluated for this study. Three anchored EMTs were bronchoscopically implanted into small airways near or within the tumor. DIBH treatment was gated by tracking the EMT positions. Breath‐hold cone‐beam‐CTs (CBCTs) were acquired prior to every HF treatment or weekly for CF patients. Retrospectively, rigid registrations between each CBCT and the breath‐hold planning CT were performed to match to 1) spine, 2) EMTs and 3) tumor. Absolute differences in registration between EMTs and spine were analyzed to determine surrogacy of EMTs for lung inflation. Differences in registration between EMTs and the tumor were analyzed to determine surrogacy of EMTs for tumor position. The stability of the EMTs was evaluated by analyzing the difference between inter‐EMT displacements recorded at treatment from that of the plan for the CF patients, as well as the geometric residual (GR) recorded at the time of treatment. Results: A total of 219 CBCTs were analyzed. The average differences between EMT centroid and spine registration among all CBCTs were 0.45±0.42 cm, 0.29±0.28 cm, and 0.18±0.15 cm in superior‐inferior (SI), anterior‐posterior (AP) and lateral directions, respectively. Only 59% of CBCTs had differences in registration < 0.5 cm for EMT centroid compared to spine, indicating that lung inflation is not reproducible from simulation to treatment. The average differences between EMT centroid and tumor registration among all CBCTs were 0.13±0.13 cm, 0.14±0.13 cm and 0.12±0.12 cm in SI, AP and lateral directions, respectively. Ninety‐five percent of CBCTs resulted in a < 0.5 cm change between EMT centroid and tumor registration, indicating that EMT positions correspond well with tumor position during treatments. Six out of the seven recorded CF patients had average differences in inter‐EMT displacements ≤0.26 cm and average GR ≤0.22 cm, indicating that the EMTs are stable throughout treatment. Conclusions: Bronchoscopically implanted anchored EMTs are good surrogates for tumor position and are reliable for maintaining tumor position when tracked during DIBH treatment, as long as the tumor size and shape are stable. Large differences in registration between EMTs and spine for many treatments suggest that lung inflation achieved at simulation is often not reproduced. [ABSTRACT FROM AUTHOR]

Purpose: Despite the widespread availability of in‐treatment room cone beam computed tomography (CBCT) imaging, due to the lack of reliable segmentation methods, CBCT is only used for gross set up corrections in lung radiotherapies. Accurate and reliable auto‐segmentation tools could potentiate volumetric response assessment and geometry‐guided adaptive radiation therapies. Therefore, we developed a new deep learning CBCT lung tumor segmentation method. Methods: The key idea of our approach called cross‐modality educed distillation (CMEDL) is to use magnetic resonance imaging (MRI) to guide a CBCT segmentation network training to extract more informative features during training. We accomplish this by training an end‐to‐end network comprised of unpaired domain adaptation (UDA) and cross‐domain segmentation distillation networks (SDNs) using unpaired CBCT and MRI datasets. UDA approach uses CBCT and MRI that are not aligned and may arise from different sets of patients. The UDA network synthesizes pseudo MRI from CBCT images. The SDN consists of teacher MRI and student CBCT segmentation networks. Feature distillation regularizes the student network to extract CBCT features that match the statistical distribution of MRI features extracted by the teacher network and obtain better differentiation of tumor from background. The UDA network was implemented with a cycleGAN improved with contextual losses separately on Unet and dense fully convolutional segmentation networks (DenseFCN). Performance comparisons were done against CBCT only using 2D and 3D networks. We also compared against an alternative framework that used UDA with MR segmentation network, whereby segmentation was done on the synthesized pseudo MRI representation. All networks were trained with 216 weekly CBCTs and 82 T2‐weighted turbo spin echo MRI acquired from different patient cohorts. Validation was done on 20 weekly CBCTs from patients not used in training. Independent testing was done on 38 weekly CBCTs from patients not used in training or validation. Segmentation accuracy was measured using surface Dice similarity coefficient (SDSC) and Hausdroff distance at 95th percentile (HD95) metrics. Results: The CMEDL approach significantly improved (p < 0.001) the accuracy of both Unet (SDSC of 0.83 ± 0.08; HD95 of 7.69 ± 7.86 mm) and DenseFCN (SDSC of 0.75 ± 0.13; HD95 of 11.42 ± 9.87 mm) over CBCT only 2DUnet (SDSC of 0.69 ± 0.11; HD95 of 21.70 ± 16.34 mm), 3D Unet (SDSC of 0.72 ± 0.20; HD95 15.01 ± 12.98 mm), and DenseFCN (SDSC of 0.66 ± 0.15; HD95 of 22.15 ± 17.19 mm) networks. The alternate framework using UDA with the MRI network was also more accurate than the CBCT only methods but less accurate the CMEDL approach. Conclusions: Our results demonstrate feasibility of the introduced CMEDL approach to produce reasonably accurate lung cancer segmentation from CBCT images. Further validation on larger datasets is necessary for clinical translation. [ABSTRACT FROM AUTHOR]

Background: Radiation therapy is one of the most commonly used cancer therapeutics but genetic determinants of clinical benefit are poorly characterized. Pathogenic germline variants in ATM are known to cause ataxia-telangiectasia, a rare hereditary syndrome notable for marked radiosensitivity. In contrast, somatic inactivation of ATM is a common event in a wide variety of cancers, but its clinical actionability remains obscure.Methods: We analyzed 20 107 consecutively treated advanced cancer patients who underwent targeted genomic sequencing as part of an institutional genomic profiling initiative and identified 1085 harboring a somatic or germline ATM mutation, including 357 who received radiotherapy (RT). Outcomes of irradiated tumors harboring ATM loss-of-function (LoF) mutations were compared with those harboring variants of unknown significance. All statistical tests were 2-sided.Results: Among 357 pan-cancer patients who received 727 courses of RT, genetic inactivation of ATM was associated with improved radiotherapeutic efficacy. The 2-year cumulative incidence of irradiated tumor progression was 13.2% vs 27.5% for tumors harboring an ATM LoF vs variant of unknown significance allele, respectively (hazard ratio [HR] = 0.51, 95% confidence interval [CI] = 0.34 to 0.77, P = .001). The greatest clinical benefit was seen in tumors harboring biallelic ATM inactivation (HR = 0.19, 95% CI = 0.06 to 0.60, P = .005), with statistically significant benefit also observed in tumors with monoallelic ATM inactivation (HR = 0.57, 95% CI = 0.35 to 0.92, P = .02). Notably, ATM LoF was highly predictive of outcome in TP53 wild-type tumors but not among TP53-mutant tumors.Conclusions: We demonstrate that somatic ATM inactivation is associated with markedly improved tumor control following RT. The identification of a radio-sensitive tumor phenotype across multiple cancer types offers potential clinical opportunities for genomically guided RT. [ABSTRACT FROM AUTHOR]

Purpose. Current magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) applies sagittal/coronal 2D-cine to monitor major tumor motions, however, the beam eye's view (BEV) with volumetric tumor projection would be the best measure for radiation beam conformality, independent of tumor through-plane motion. The goal is to assess the feasibility, accuracy, and performance of the BEV approach. Methods. Beam-specific BEV 2D-cine with volume-projected tumor contours were simulated to establish a 2D/3D tumor match against a tumor-motion library based on multi-breath time-resolved (TR) 4DMRI images. Two BEV-library-matching methods were developed: (1) fast screening with tumor center-of-mass (∆COM), in-plane area ratio, and DICE similarity, and finalizing with the highest DICE score and (2) DICE screening for top-3 candidates and finalizing with rigid registration. A 4D-XCAT digital phantom and 8 lung-cancer patients were used for assessment. For each patient, 3 sets of 40 s TR-4DMRI were acquired at 2 Hz and 6 representative BEV were created with the isocenter set at tumor COM in mid-respiration. One TR-4DMRI set (40 × 2 = 80-images) was used to simulate BEV 2D-cine and the other two (160-images) were used to create a library. The matching result was validated against the ground truth within the test set. Using a leave-one-out strategy, the success rate, accuracy, and speed of tumor matching were assessed for volume-projected tumors over 11520 time-points (=8patients•3sets•80images•6BEVs). Results. Volume-projected tumor contour area on the 6 BEVs varies by 60% ± 8% and (in-plane/volume-projected) varies by 82% ± 9%. The changes with tumor shape, orientation, and through-plane motion. Method-1 produces 96% matching success (ΔCOM = 0.7 ± 0.2 mm, =1.01 ± 0.02, Dice=0.92 ± 0.02) with the computational time of 15 ± 1 ms/match, while method-2 produces 94% ± 1% success (ΔCOM = 0.2 ± 0.1 mm, =1.00 ± 0.01, Dice = 0.94 ± 0.02) with 223 ± 13 ms/match. Conclusion. This study has demonstrated the feasibility, accuracy, and benefits of BEV 2D-cine imaging with tumor-volume projection, allowing real-time tumor motion monitoring and beam conformality checking. Further clinical evaluation is necessary before MRgRT applications. [ABSTRACT FROM AUTHOR]

Based on an analysis of published literature, our department recently lowered the preferred mean esophagus dose (MED) constraint for conventionally fractionated (2 Gy/fraction in approximately 30 fractions) treatment of locally advanced non‐small cell lung cancer (LA‐NSCLC) with the goal of reducing the incidence of symptomatic acute esophagitis (AE). The goal of the change was to encourage treatment planners to achieve a MED close to 21 Gy while still permitting MED to go up to the previous guideline of 34 Gy in difficult cases. We compared all our suitable LA‐NSCLC patients treated with plans from one year before through one year after the constraint change. The primary endpoint for this study was achievability of the new constraint by the planners; the secondary endpoint was reduction in symptomatic AE. Planners were able to achieve the new constraint in statistically significantly more cases during the year following its explicit implementation than in the year before (P = 0.0025). Furthermore, 38% of patients treated after the new constraint developed symptomatic AE during their treatment as opposed to 48% of the patients treated before. This is a clinically desirable endpoint although the observed difference was not statistically significant. A subsequent power calculation suggests that this is due to the relatively small number of patients in the study. [ABSTRACT FROM AUTHOR]

Acute esophagitis (AE) occurs among a significant number of patients with locally advanced lung cancer treated with radiotherapy. Early prediction of AE, indicated by esophageal wall expansion, is critical, as it can facilitate the redesign of treatment plans to reduce radiation-induced esophageal toxicity in an adaptive radiotherapy (ART) workflow. We have developed a novel machine learning framework to predict the patient-specific spatial presentation of the esophagus in the weeks following treatment, using magnetic resonance imaging (MRI)/ cone-beam CT (CBCT) scans acquired earlier in the 6 week radiotherapy course. Our algorithm captures the response patterns of the esophagus to radiation on a patch level, using a convolutional neural network. A recurrence neural network then parses the evolutionary patterns of the selected features in the time series, and produces a predicted esophagus-or-not label for each individual patch over future weeks. Finally, the esophagus is reconstructed, using all the predicted labels. The algorithm is trained and validated by means of ∼ 250 000 patches taken from MRI scans acquired weekly from a variety of patients, and tested using both weekly MRI and CBCT scans under a leave-one-patient-out scheme. In addition, our approach is externally validated using a publicly available dataset (Hugo 2017). Using the first three weekly scans, the algorithm can predict the condition of the esophagus over the succeeding 3 weeks with a Dice coefficient of 0.83 ± 0.04, estimate esophagus volume highly (0.98), correlated with the actual volume, using our institutional MRI/CBCT data. When evaluated using the external weekly CBCT data, the averaged Dice coefficient is 0.89 ± 0.03. Our novel algorithm may prove useful in enabling radiation oncologists to monitor and detect AE in its early stages, and could potentially play an important role in the ART decision-making process. [ABSTRACT FROM AUTHOR]

We developed a new joint probabilistic segmentation and image distribution matching generative adversarial network (PSIGAN) for unsupervised domain adaptation (UDA) and multi-organ segmentation from magnetic resonance (MRI) images. Our UDA approach models the co-dependency between images and their segmentation as a joint probability distribution using a new structure discriminator. The structure discriminator computes structure of interest focused adversarial loss by combining the generated pseudo MRI with probabilistic segmentations produced by a simultaneously trained segmentation sub-network. The segmentation sub-network is trained using the pseudo MRI produced by the generator sub-network. This leads to a cyclical optimization of both the generator and segmentation sub-networks that are jointly trained as part of an end-to-end network. Extensive experiments and comparisons against multiple state-of-the-art methods were done on four different MRI sequences totalling 257 scans for generating multi-organ and tumor segmentation. The experiments included, (a) 20 T1-weighted (T1w) in-phase mdixon and (b) 20 T2-weighted (T2w) abdominal MRI for segmenting liver, spleen, left and right kidneys, (c) 162 T2-weighted fat suppressed head and neck MRI (T2wFS) for parotid gland segmentation, and (d) 75 T2w MRI for lung tumor segmentation. Our method achieved an overall average DSC of 0.87 on T1w and 0.90 on T2w for the abdominal organs, 0.82 on T2wFS for the parotid glands, and 0.77 on T2w MRI for lung tumors. [ABSTRACT FROM AUTHOR]

Objective: To assess the impact of a migraine management program offered as a complimentary service by a company within its corporate well‐being program. Background: Migraine imposes a substantial burden on patients, families, employers, and societies. As migraine primarily affects working‐age adults, this has important implications for both employees and employers. Workplace educational and well‐being programs positively contribute to employees' productivity, reduce costs related to absenteeism, and improve the quality of life of the employees living with migraine. Methods: This was a non‐interventional cohort study, which followed employees and their family members over time. Participants received 1 telemedicine consultation to determine migraine diagnosis or a high probability of having migraine and 6 sessions of individualized telecoaching from a specialized nurse via a specially developed smartphone application to optimize their migraine management leveraging all appropriate medical and lifestyle options. Participants were evaluated during the program and at 3 months after completion through a series of validated questionnaires including Migraine Disability Assessment (MIDAS), Patient Activation Measure (PAM), and satisfaction with the services offered. A cost analysis was also performed to determine the economic benefit of the program considering the number of completers, dropouts, their associated program costs, MIDAS data, average salary of a Swiss employee in the pharma sector, and working days per year. Results: Of the 141 participants enrolled in the program, 79 completed 6‐month and 42 completed 9‐month assessments. The total MIDAS scores (mean, standard deviation [SD]) significantly improved from baseline by 54% at Month 6 (15.0 [13.6] vs 6.9 [8.2]; mean [SD] reduction: 8.1 [12.9], 95% confidence interval [CI]: 5.6‐10.6; P <.0001) and by 64% at Month 9 (15.4 [14.7] vs 5.6 [6.0]; mean [SD] reduction: 9.8 [14.0], 95% CI: 6.6‐13.0; P <.0001). The PAM scores also significantly improved from baseline by 8% at Month 6 (63.8 [10.9] vs 69.6 [12.8]; mean [SD] increase: 5.8 [12.8], 95% CI: 3.2‐8.4; P =.003) and 11% at Month 9 (63.5 [10.7] vs 71.3 [12.2]; mean [SD] increase: 7.8 [11.0], 95% CI: 4.3‐11.2; P =.003). At Month 6, common coaching lessons and respective action plans focused on progressive muscle relaxation, sleep, hydration, nutrition, general disease education, and stress management. The exit survey showed that the majority of the participants who completed the program had a meaningful and sustained improvement in their overall health and reported a high level of satisfaction with the program. The cost analysis revealed that on average participants gained 10.8 (95% CI: 9.3‐12.3) working days/year that were previously lost due to migraine, resulting in a positive return on investment (ROI) of 490% (95% CI: 410%‐570%), indicating a higher magnitude of savings that could be achieved by the implementation of such program. In addition to ROI and work productivity gained, participants also gained on average 13.6 (95% CI: 9.9‐17.3) migraine‐free days/year for their private and social life. Conclusion: The employer‐sponsored disease management program provided a better understanding of migraine, promoted methods and approaches to improve management by combining medical and lifestyle options leading to significant improvements in migraine symptoms that sustained beyond the intervention, supporting prolonged effectiveness of such programs. The program also provided a high ROI to the employer, supporting that the systematic inclusion of such programs into corporate well‐being initiatives can be of significant benefit not only to the impacted individuals but to the employers as well. [ABSTRACT FROM AUTHOR]

Purpose: Deformable image registration (DIR) in low‐contrast tissues is often suboptimal because of low visibility of landmarks, low driving‐force to deform, and low penalty for misalignment. We aim to overcome the shortcomings for improved reconstruction of time‐resolved four‐dimensional magnetic resonance imaging (TR‐4DMRI). Methods and Materials: Super‐resolution TR‐4DMRI reconstruction utilizes DIR to combine high‐resolution (highR:2x2x2mm3) breath‐hold (BH) and low‐resolution (lowR:5x5x5mm3) free‐breathing (FB) 3D cine (2Hz) images to achieve clinically acceptable spatiotemporal resolution. A 2‐step hybrid DIR approach was developed to segment low‐dynamic‐range (LDR) regions: low‐intensity lungs and high‐intensity "bodyshell" (=body‐lungs) for DIR refinement after conventional DIR. The intensity in LDR regions was renormalized to the full dynamic range (FDR) to enhance local tissue contrast. A T1‐mapped 4D XCAT digital phantom was created, and seven volunteers and five lung cancer patients were scanned with two BH and one 3D cine series per subject to compare the 1‐step conventional and 2‐step hybrid DIR using: (a) the ground truth in the phantom, (b) highR‐BH references, which were used to simulate 3D cine images by down‐sampling and Rayleigh‐noise‐adding, and (c) cross‐verification between two TR‐4DMRI images reconstructed from two BHs. To assess DIR improvement, 8‐17 blood vessel bifurcations were used in volunteers, and lung tumor position, size, and shape were used in phantom and patients, together with the voxel intensity correlation (VIC), structural similarity (SSIM), and cross‐consistency check (CCC). Results: The 2‐step hybrid DIR improves contrast and DIR accuracy. In volunteers, it improves low‐contrast alignment from 6.5 ± 1.8 mm to 3.3 ± 1.0 mm. In phantom, it improves tumor center of mass alignment (COM = 1.3 ± 0.2 mm) and minimizes DIR directional difference. In patients, it produces almost‐identical tumor COM, size, and shape (dice> 0.85) as the reference. The VIC and SSIM are significantly increased and the number of CCC outliers are reduced by half. Conclusion: The 2‐step hybrid DIR improves low‐contrast‐tissue alignment and increases lung tumor fidelity. It is recommended to adopt the 2‐step hybrid DIR for TR‐4DMRI reconstruction. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study was to develop T2‐weighted (T2w) time‐resolved (TR) four‐dimensional magnetic resonance imaging (4DMRI) reconstruction technique with higher soft‐tissue contrast for multiple breathing cycle motion assessment by building a super‐resolution (SR) framework using the T1w TR‐4DMRI reconstruction as guidance. Methods: The multi‐breath T1w TR‐4DMRI was reconstructed by deforming a high‐resolution (HR: 2 × 2 × 2 mm3) volumetric breath‐hold (BH, 20s) three‐dimensional magnetic resonance imaging (3DMRI) image to a series of low‐resolution (LR: 5 × 5 × 5 mm3) 3D cine images at a 2Hz frame rate in free‐breathing (FB, 40 s) using an enhanced Demons algorithm, namely [T1BH→FB] reconstruction. Within the same imaging session, respiratory‐correlated (RC) T2w 4DMRI (2 × 2 × 2 mm3) was acquired based on an internal navigator to gain HR T2w (T2HR) in three states (full exhalation and mid and full inhalation) in ~5 min. Minor binning artifacts in the RC‐4DMRI were automatically identified based on voxel intensity correlation (VIC) between consecutive slices as outliers (VIC < VICmean‐σ) and corrected by deforming the artifact slices to interpolated slices from the adjacent slices iteratively until no outliers were identified. A T2HR image with minimal deformation (<1 cm at the diaphragm) from the T1BH image was selected for multi‐modal B‐Spline deformable image registration (DIR) to establish the T2HR‐T1BH voxel correspondence. Two approaches to reconstruct T2w TR‐4DMRI were investigated: (A) T2HR→[T1BH→FB]: to deform T2w HR to T1w BH only as T1w TR‐4DMRI was reconstructed, and combine the two displacement vector fields (DVFs) to reconstruct T2w TR‐4DMRI, and (B) [T2HR←T1BH]→FB: to deform T1w BH to T2w HR first and apply the deformed T1w BH to reconstruct T2w TR‐4DMRI. The reconstruction times were similar, 8–12 min per volume. To validate the two methods, T2w‐ and T1w‐mapped 4D XCAT digital phantoms were utilized with three synthetic spherical tumors (ϕ = 2.0, 3.0, and 4.0 cm) in the lower or mid lobes as the ground truth to evaluate the tumor location (the center of mass, COM), size (volume ratio, %V), and shape (Dice index). Six lung cancer patients were scanned under an IRB‐approved protocol and the T2w TR‐4DMRI images reconstructed from the two methods were compared based on the preservation of the three tumor characteristics. The local tumor‐contained image quality was also characterized using the VIC and structure similarity (SSIM) indexes. Results: In the 4D digital phantom, excellent tumor alignment after T2HR‐T1HR DIR is achieved: ∆COM = 0.8 ± 0.5 mm, %V = 1.06 ± 0.02, and Dice = 0.91 ± 0.03, in both deformation directions using the DIR‐target image as the reference. In patients, binning artifacts are corrected with improved image quality: average VIC increases from 0.92 ± 0.03 to 0.95 ± 0.01. Both T2w TR‐4DMRI reconstruction methods produce similar tumor alignment errors ∆COM = 2.9 ± 0.6 mm. However, method B ([T2HR←T1BH]→FB) produces superior results in preserving more T2w tumor features with a higher %V = 0.99 ± 0.03, Dice = 0.81 ± 0.06, VIC = 0.85 ± 0.06, and SSIM = 0.65 ± 0.10 in the T2w TR‐4DMRI images. Conclusions: This study has demonstrated the feasibility of T2w TR‐4DMRI reconstruction with high soft‐tissue contrast and adequately‐preserved tumor position, size, and shape in multiple breathing cycles. The T2w‐centric DIR (method B) produces a superior solution for the SR‐based framework of T2w TR‐4DMRI reconstruction with highly preserved tumor characteristics and local image features, which are useful for tumor delineation and motion management in radiation therapy. [ABSTRACT FROM AUTHOR]

Introduction: Durvalumab after concurrent chemoradiation (cCRT) is now standard of care for unresected stage III non–small cell lung cancer (NSCLC). However, there is limited data on radiation pneumonitis (RP) with this regimen. Therefore, we assessed RP and evaluated previously validated toxicity models in predicting for RP in patients treated with cCRT and durvalumab. Methods: Patients treated with cCRT and ≥ 1 dose of durvalumab were evaluated to identify cases of ≥ grade 2 RP. The validity of previously published RP models was assessed in this cohort as well a reference cohort treated with cCRT alone. The timing and incidence of RP was compared between cohorts. Results: In total, 11 (18%) of the 62 patients who received cCRT and durvalumab developed ≥ grade 2 RP a median of 3.4 months after cCRT. The onset of RP among patients treated with cCRT and durvalumab was significantly longer vs the reference cohort (3.4 vs 2.1 months; P =.01). Numerically more patients treated with cCRT and durvalumab developed RP than patients in the reference cohort (18% vs 9%, P =.09). Among patients treated with cCRT and durvalumab, 82% (n = 9) were responsive to treatment with high‐dose glucocorticoids. Previously published RP models widely underestimated the rate of RP in patients treated with cCRT and durvalumab [AUC ~ 0.50; p(Hosmer‐Lemeshow): 0.98‐1.00]. Conclusions: Our data suggest a delayed onset of RP in patients treated with cCRT and durvalumab vs cCRT alone, and for RP to develop in a greater number of patients treated with cCRT and durvalumab. Previously published RP models significantly underestimate the rate of symptomatic RP among patients treated with cCRT and durvalumab. [ABSTRACT FROM AUTHOR]

Purpose: To design a convolutional recurrent neural network (CRNN) that calculates three‐dimensional (3D) positions of lung tumors from continuously acquired cone beam computed tomography (CBCT) projections, and facilitates the sorting and reconstruction of 4D‐CBCT images. Method: Under an IRB‐approved clinical lung protocol, kilovoltage (kV) projections of the setup CBCT were collected in free‐breathing. Concurrently, an electromagnetic signal‐guided system recorded motion traces of three transponders implanted in or near the tumor. Convolutional recurrent neural network was designed to utilize a convolutional neural network (CNN) for extracting relevant features of the kV projections around the tumor, followed by a recurrent neural network for analyzing the temporal patterns of the moving features. Convolutional recurrent neural network was trained on the simultaneously collected kV projections and motion traces, subsequently utilized to calculate motion traces solely based on the continuous feed of kV projections. To enhance performance, CRNN was also facilitated by frequent calibrations (e.g., at 10° gantry rotation intervals) derived from cross‐correlation‐based registrations between kV projections and templates created from the planning 4DCT. Convolutional recurrent neural network was validated on a leave‐one‐out strategy using data from 11 lung patients, including 5500 kV images. The root‐mean‐square error between the CRNN and motion traces was calculated to evaluate the localization accuracy. Result: Three‐dimensional displacement around the simulation position shown in the Calypso traces was 3.4 ± 1.7 mm. Using motion traces as ground truth, the 3D localization error of CRNN with calibrations was 1.3 ± 1.4 mm. CRNN had a success rate of 86 ± 8% in determining whether the motion was within a 3D displacement window of 2 mm. The latency was 20 ms when CRNN ran on a high‐performance computer cluster. Conclusions: CRNN is able to provide accurate localization of lung tumors with aid from frequent recalibrations using the conventional cross‐correlation‐based registration approach, and has the potential to remove reliance on the implanted fiducials. [ABSTRACT FROM AUTHOR]

Background: Patients with unresectable locally advanced NSCLC who refuse or are not candidates for chemotherapy often receive radiation therapy (RT) alone. Hypofractionated RT (HFRT) regimens are becoming increasingly common. An analysis of the National Cancer Database (NCDB) was performed to evaluate the practice patterns and outcomes of HFRT vs. conventionally fractionated RT (CFRT) in patients with stage III NSCLC undergoing definitive RT alone. Material and methods: The NCDB was queried for all patients with stage III NSCLC diagnosed between 2004 and 2014 who received RT alone. CFRT was defined as patients treated to a total dose of 60–80 Gy in 1.8–2 Gy daily fractions. HFRT was defined as patients treated to a total dose of 50–80 Gy in 2.25–4 Gy fractions. Logistic regression, univariable and multivariable analyses (MVAs) for overall survival (OS) and propensity score matched analyses (PSMAs) were performed. Results: A total of 6490 patients were evaluated: 5378 received CFRT and 1112 received HFRT. Median CFRT dose was 66 Gy in 2 Gy fractions vs. 58.5 Gy in 2.5 Gy fractions for HFRT. HFRT was associated with older age, lower biological effective dose (BED10), academic facility type, higher T-stage and lower N-stage. On initial analysis, HFRT was associated with inferior OS (median 9.9 vs. 11.1 months, p<.001), but after adjusting for the imbalance in covariates such as age, BED10, T-stage and N-stage using PSMA, the difference in survival was no longer significant (p=.1). Conclusions: In the appropriate clinical context, HFRT can be an option for patients with locally advanced NSCLC who are not candidates for chemotherapy or surgical resection. HFRT needs to be further studied in prospective trials to evaluate toxicity and tumor control. [ABSTRACT FROM AUTHOR]

Purpose: Conventional radiotherapy for large lung tumors is given over several weeks, during which the tumor typically regresses in a highly nonuniform and variable manner. Adaptive radiotherapy would ideally follow these shape changes, but we need an accurate method to extrapolate tumor shape changes. We propose a computationally efficient algorithm to quantitate tumor surface shape changes that makes minimal assumptions, identifies fixed points, and can be used to predict future tumor geometrical response. Methods: A novel combination of nonrigid iterative closest point (ICP) and local shape‐preserving map algorithms, LDeform, is developed to enable visualization, prediction, and categorization of both diffeomorphic and nondiffeomorphic tumor deformations during an extended course of radiotherapy. Results: We tested and validated our technique on 31 longitudinal CT/MRI subjects, with five to nine time points each. Based on this tumor deformation analysis, regions of local growth, shrinkage, and anchoring are identified and tracked across multiple time points. This categorization in turn represents a rational biomarker of local response. Results demonstrate useful predictive power, with an averaged Dice coefficient and surface mean‐squared error of 0.85 and 2.8 mm, respectively, over all images. Conclusions: We conclude that the LDeform algorithm can facilitate the adaptive decision‐making process during lung cancer radiotherapy. [ABSTRACT FROM AUTHOR]

Pulmonary perfusion with dynamic contrast‐enhanced (DCE‐) MRI is typically assessed using a single‐input tracer kinetic model. Preliminary studies based on perfusion CT are indicating that dual‐input perfusion modeling of lung tumors may be clinically valuable as lung tumors have a dual blood supply from the pulmonary and aortic system. This study aimed to investigate the feasibility of fitting dual‐input tracer kinetic models to DCE‐MRI datasets of thoracic malignancies, including malignant pleural mesothelioma (MPM) and nonsmall cell lung cancer (NSCLC), by comparing them to single‐input (pulmonary or systemic arterial input) tracer kinetic models for the voxel‐level analysis within the tumor with respect to goodness‐of‐fit statistics. Fifteen patients (five MPM, ten NSCLC) underwent DCE‐MRI prior to radiotherapy. DCE‐MRI data were analyzed using five different single‐ or dual‐input tracer kinetic models: Tofts‐Kety (TK), extended TK (ETK), two compartment exchange (2CX), adiabatic approximation to the tissue homogeneity (AATH) and distributed parameter (DP) models. The pulmonary blood flow (BF), blood volume (BV), mean transit time (MTT), permeability‐surface area product (PS), fractional interstitial volume (vI), and volume transfer constant (KTrans) were calculated for both single‐ and dual‐input models. The pulmonary arterial flow fraction (γ), pulmonary arterial blood flow (BFPA) and systemic arterial blood flow (BFA) were additionally calculated for only dual‐input models. The competing models were ranked and their Akaike weights were calculated for each voxel according to corrected Akaike information criterion (cAIC). The optimal model was chosen based on the lowest cAIC value. In both types of tumors, all five dual‐input models yielded lower cAIC values than their corresponding single‐input models. The 2CX model was the best‐fitted model and most optimal in describing tracer kinetic behavior to assess microvascular properties in both MPM and NSCLC. The dual‐input 2CX‐model‐derived BFA was the most significant parameter in differentiating adenocarcinoma from squamous cell carcinoma histology for NSCLC patients. [ABSTRACT FROM AUTHOR]

Purpose: To predict the spatial and temporal trajectories of lung tumor during radiotherapy monitored under a longitudinal magnetic resonance imaging (MRI) study via a deep learning algorithm for facilitating adaptive radiotherapy (ART). Methods: We monitored 10 lung cancer patients by acquiring weekly MRI‐T2w scans over a course of radiotherapy. Under an ART workflow, we developed a predictive neural network (P‐net) to predict the spatial distributions of tumors in the coming weeks utilizing images acquired earlier in the course. The three‐step P‐net consisted of a convolutional neural network to extract relevant features of the tumor and its environment, followed by a recurrence neural network constructed with gated recurrent units to analyze trajectories of tumor evolution in response to radiotherapy, and finally an attention model to weight the importance of weekly observations and produce the predictions. The performance of P‐net was measured with Dice and root mean square surface distance (RMSSD) between the algorithm‐predicted and experts‐contoured tumors under a leave‐one‐out scheme. Results: Tumor shrinkage was 60% ± 27% (mean ± standard deviation) by the end of radiotherapy across nine patients. Using images from the first three weeks, P‐net predicted tumors on future weeks (4, 5, 6) with a Dice and RMSSD of (0.78 ± 0.22, 0.69 ± 0.24, 0.69 ± 0.26), and (2.1 ± 1.1 mm, 2.3 ± 0.8 mm, 2.6 ± 1.4 mm), respectively. Conclusion: The proposed deep learning algorithm can capture and predict spatial and temporal patterns of tumor regression in a longitudinal imaging study. It closely follows the clinical workflow, and could facilitate the decision‐making of ART. A prospective study including more patients is warranted. [ABSTRACT FROM AUTHOR]

Purpose: Accurate tumor segmentation is a requirement for magnetic resonance (MR)‐based radiotherapy. Lack of large expert annotated MR datasets makes training deep learning models difficult. Therefore, a cross‐modality (MR‐CT) deep learning segmentation approach that augments training data using pseudo MR images produced by transforming expert‐segmented CT images was developed. Methods: Eighty‐one T2‐weighted MRI scans from 28 patients with non‐small cell lung cancers (nine with pretreatment and weekly MRI and the remainder with pre‐treatment MRI scans) were analyzed. Cross‐modality model encoding the transformation of CT to pseudo MR images resembling T2w MRI was learned as a generative adversarial deep learning network. This model was used to translate 377 expert segmented non‐small cell lung cancer CT scans from the Cancer Imaging Archive into pseudo MRI that served as additional training set. This method was benchmarked against shallow learning using random forest, standard data augmentation, and three state‐of‐the art adversarial learning‐based cross‐modality data (pseudo MR) augmentation methods. Segmentation accuracy was computed using Dice similarity coefficient (DSC), Hausdorff distance metrics, and volume ratio. Results: The proposed approach produced the lowest statistical variability in the intensity distribution between pseudo and T2w MR images measured as Kullback–Leibler divergence of 0.069. This method produced the highest segmentation accuracy with a DSC of (0.75 ± 0.12) and the lowest Hausdorff distance of (9.36 mm ± 6.00 mm) on the test dataset using a U‐Net structure. This approach produced highly similar estimations of tumor growth as an expert (P = 0.37). Conclusions: A novel deep learning MR segmentation was developed that overcomes the limitation of learning robust models from small datasets by leveraging learned cross‐modality information using a model that explicitly incorporates knowledge of tumors in modality translation to augment segmentation training. The results show the feasibility of the approach and the corresponding improvement over the state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate clinical utility of respiratory‐correlated (RC) four‐dimensional magnetic resonance imaging (4DMRI) for lung tumor delineation and motion assessment, in comparison with the current clinical standard of 4D computed tomography (4DCT). Methods and Materials: A prospective T2‐weighted (T2w) RC‐4DMRI technique was applied to acquire coronal 4DMRI images for 14 lung cancer patients (16 lesions) during free breathing (FB) under an IRB‐approved protocol, together with a breath‐hold (BH) T1w 3DMRI and axial 4DMRI. Clinical simulation CT and 4DCT were acquired within 2 h. An internal navigator was applied to trigger amplitude‐binned 4DMRI acquisition whereas a bellows or real‐time position management (RPM) was used in the 4DCT reconstruction. Six radiation oncologists manually delineated the gross and internal tumor volumes (GTV and ITV) in 399 3D images using programmed clinical workflows under a tumor delineation guideline. The ITV was the union of GTVs within the breathing cycle without margin. Average GTV and motion range were assessed and ITV variation between 4DMRI and 4DCT was evaluated using the Dice similarity index, mean distance agreement (MDA), and volume difference. Results: The mean tumor volume is similar between 4DCT (GTV4DCT = 1.0, as the reference) and T2w‐4DMRI (GTVT2wMR = 0.97), but smaller in T1w MRI (GTVT1wMR = 0.76), suggesting possible peripheral edema around the tumor. Average GTV variation within the breathing cycle (22%) in 4DMRI is slightly greater than 4DCT (17%). GTV motion variation (−4 to 12 mm) and ITV variation (∆VITV=−25 to 95%) between 4DCT and 4DMRI are large, confirmed by relatively low ITV similarity (Dice = 0.72 ± 0.11) and large MDA = 2.9 ± 1.5 mm. Conclusion: Average GTVs are similar between T2w‐4DMRI and 4DCT, but smaller by 25% in T1w BH MRI. Physician training and breathing coaching may be necessary to reduce ITV variability between 4DMRI and 4DCT. Four‐dimensional magnetic resonance imaging is a promising and viable technique for clinical lung tumor delineation and motion assessment. [ABSTRACT FROM AUTHOR]

Objective: This study was conducted in order to describe the computed tomography (CT) features of local pleural recurrence in patients with malignant pleural mesothelioma undergoing intensity-modulated pleural radiation therapy (IMPRINT) as part of multimodality treatment.Methods: In this observational study, 58 patients treated with IMPRINT between September 21, 2004, and December 1, 2014 were included. Baseline and follow-up CT scans were qualitatively assessed. On follow-up scans, pleural thickening was categorized as unchanged, decreased, or new/increased. New/increased pleural abnormality was subcategorized as diffuse smooth pleural thickening, diffuse nodular pleural thickening, focal pleural nodule, or multiple pleural nodules. To identify features more frequently present at the time of local recurrence, follow-up scans with local recurrence were matched to four control scans; exact conditional logistic regression was performed.Results: Twenty-one (36%) patients had local pleural recurrence and 20 (34%) patients had nonpleural recurrence; 3 patients had both types of recurrence. The 1-year cumulative incidence rate of local recurrence was 27% (95% confidence interval 15, 39). On follow-up scans, three patterns of pleural abnormality were significantly associated with local recurrence: new/increased multiple pleural nodules (10 (48%) positive scans vs 0 control scans), new/increased diffuse nodular pleural thickening (7 (33%) positive scans vs 1 (1%) control scans), and new/increased focal pleural nodule (3 (14%) positive scans vs 1 (1%) control scan) (p < 0.001 for all).Conclusions: Multiple new/increased pleural nodules are the feature most commonly present at local recurrence following IMPRINT; however, any pattern of increased nodular pleural thickening is suspicious.Key Points: • In patients with mesothelioma receiving intensity-modulated pleural radiation as part of multimodality therapy, increasing multiple pleural nodules is the computed tomography feature most commonly present at local recurrence. • In these patients, any CT pattern of increased nodular pleural thickening should be considered suspicious for local recurrence. • The most common sites of nonpleural recurrence were lung parenchyma, thoracic lymph nodes, and peritoneum. [ABSTRACT FROM AUTHOR]

Purpose: To compare single‐shot echo‐planar (SS‐EPI)‐based and turbo spin‐echo (SS‐TSE)‐based diffusion‐weighted imaging (DWI) in Non‐Small Cell Lung Cancer (NSCLC) patients and to characterize the distributions of apparent diffusion coefficient (ADC) values generated by the two techniques. Methods: Ten NSCLC patients were enrolled in a prospective IRB‐approved study to compare and optimize DWI using EPI and TSE‐based techniques for radiotherapy planning. The imaging protocol included axial T2w, EPI‐based DWI and TSE‐based DWI on a 3 T Philips scanner. Both EPI‐based and TSE‐based DWI sequences used three b values (0, 400, and 800 s/mm2). The acquisition times for EPI‐based and TSE‐based DWI were 5 and 8 min, respectively. DW‐MR images were manually coregistered with axial T2w images, and tumor volume contoured on T2w images were mapped onto the DWI scans. A pixel‐by‐pixel fit of tumor ADC was calculated based on monoexponential signal behavior. Tumor ADC mean, standard deviation, kurtosis, and skewness were calculated and compared between EPI and TSE‐based DWI. Image distortion and ADC values between the two techniques were also quantified using fieldmap analysis and a NIST traceable ice‐water diffusion phantom, respectively. Results: The mean ADC for EPI and TSE‐based DWI were 1.282 ± 0.42 × 10−3 and 1.211 ± 0.31 × 10−3 mm2/s. The average skewness and kurtosis were 0.14 ± 0.4 and 2.43 ± 0.40 for DWI‐EPI and −0.06 ± 0.69 and 2.89 ± 0.62 for DWI‐TSE. Fieldmap analysis showed a mean distortion of 13.72 ± 8.12 mm for GTV for DWI‐EPI and 0.61 ± 0.4 mm for DWI‐TSE. ADC values obtained using the diffusion phantom for the two techniques were within 0.03 × 10−3 mm2/s with respect to each other as well as the established values. Conclusions: Diffusion‐weighted turbo spin‐echo shows better geometrical accuracy compared to DWI‐EPI. Mean ADC values were similar with both acquisitions but the shape of the histograms was different based on the skewness and kurtosis values. The impact of differences in respiratory technique on ADC values requires further investigation. [ABSTRACT FROM AUTHOR]

Purpose: Localizing lung tumors during treatment delivery is critical for managing respiratory motion, ensuring tumor coverage, and reducing toxicities. The purpose of this project is to develop a real‐time system that performs markerless tracking of lung tumors using simultaneously acquired MV and kV images during radiotherapy of lung cancer with volumetric modulated arc therapy. Method: Continuous MV/kV images were simultaneously acquired during dose delivery. In the subsequent analysis, a gantry angle‐specific region of interest was defined according to the treatment aperture. After removing imaging artifacts, processed MV/kV images were directly registered to the corresponding daily setup cone‐beam CT (CBCT) projections that served as reference images. The registration objective function consisted of a sum of normalized cross‐correlation, weighted by the contrast‐to‐noise ratio of each MV and kV image. The calculated 3D shifts of the tumor were corrected by the displacements between the CBCT projections and the planning respiratory correlated CT (RCCT) to generate motion traces referred to a specific respiratory phase. The accuracy of the algorithm was evaluated on both anthropomorphic phantom and patient studies. The phantom consisted of localizing a 3D printed tumor, embedded in a thorax phantom, in an arc delivery. In an IRB‐approved study, data were obtained from VMAT treatments of two lung cancer patients with three electromagnetic (Calypso) beacon transponders implanted in airways near the lung tumor. Result: In the phantom study, the root mean square error (RMSE) between the registered and actual (programmed couch movement) target position was 1.2 mm measured by the MV/kV imaging system, which was smaller compared to the MV or kV alone, of 4.1 and 1.3 mm, respectively. In the patient study, the mean and standard deviation discrepancy between electromagnetic‐based tumor position and the MV/KV‐markerless approach was −0.2 ± 0.6 mm, 0.2 ± 1.0 mm, and −1.2 ± 1.5 mm along the superior‐inferior, anterior‐posterior, and left‐right directions, respectively; resulting in a 3D displacement discrepancy of 2.0 ± 1.1 mm. Poor contrast around the tumor was the main contribution to registration uncertainties. Conclusion: The combined MV/kV imaging system can provide real‐time 3D localization of lung tumor, with comparable accuracy to the electromagnetic‐based system when features of tumors are detectable. Careful design of a registration algorithm and a VMAT plan that maximizes the tumor visibility are key elements for a successful MV/KV localization strategy. [ABSTRACT FROM AUTHOR]