Dual convolution-transformer UNet (DCT-UNet) for organs at risk and clinical target volume segmentation in MRI for cervical cancer brachytherapy.

Objective. MRI is the standard imaging modality for high-dose-rate brachytherapy of cervical cancer. Precise contouring of organs at risk (OARs) and high-risk clinical target volume (HR-CTV) from MRI is a crucial step for radiotherapy planning and treatment. However, conventional manual contouring has limitations in terms of accuracy as well as procedural time. To overcome these, we propose a deep learning approach to automatically segment OARs (bladder, rectum, and sigmoid colon) and HR-CTV from female pelvic MRI.Approach. In the proposed pipeline, a coarse multi-organ segmentation model first segments all structures, from which a region of interest is computed for each structure. Then, each organ is segmented using an organ-specific fine segmentation model separately trained for each organ. To account for variable sizes of HR-CTV, a size-adaptive multi-model approach was employed. For coarse and fine segmentations, we designed a dual convolution-transformer UNet (DCT-UNet) which uses dual-path encoder consisting of convolution and transformer blocks. To evaluate our model, OAR segmentations were compared to the clinical contours drawn by the attending radiation oncologist. For HR-CTV, four sets of contours (clinical + three additional sets) were obtained to produce a consensus ground truth as well as for inter/intra-observer variability analysis.Main results. DCT-UNet achieved dice similarity coefficient (mean ± SD) of 0.932 ± 0.032 (bladder), 0.786 ± 0.090 (rectum), 0.663 ± 0.180 (sigmoid colon), and 0.741 ± 0.076 (HR-CTV), outperforming other state-of-the-art models. Notably, the size-adaptive multi-model significantly improved HR-CTV segmentation compared to a single-model. Furthermore, significant inter/intra-observer variability was observed, and our model showed comparable performance to all observers. Computation time for the entire pipeline per subject was 12.59 ± 0.79 s, which is significantly shorter than the typical manual contouring time of >15 min.Significance. These experimental results demonstrate that our model has great utility in cervical cancer brachytherapy by enabling fast and accurate automatic segmentation, and has potential in improving consistency in contouring. DCT-UNet source code is available athttps://github.com/JHU-MICA/DCT-UNet.

Comprehensive Clinical Usability-Oriented Contour Quality Evaluation for Deep Learning Auto-segmentation: Combining Multiple Quantitative Metrics Through Machine Learning.

PURPOSE: The current commonly used metrics for evaluating the quality of auto-segmented contours have limitations and do not always reflect the clinical usefulness of the contours. This work aims to develop a novel contour quality classification (CQC) method by combining multiple quantitative metrics for clinical usability-oriented contour quality evaluation for deep learning-based auto-segmentation (DLAS). METHODS AND MATERIALS: The CQC was designed to categorize contours on slices as acceptable, minor edit, or major edit based on the expected editing effort/time with supervised ensemble tree classification models using 7 quantitative metrics. Organ-specific models were trained for 5 abdominal organs (pancreas, duodenum, stomach, small, and large bowels) using 50 magnetic resonance imaging (MRI) data sets. Twenty additional MRI and 9 computed tomography (CT) data sets were employed for testing. Interobserver variation (IOV) was assessed among 6 observers and consensus labels were established through majority vote for evaluation. The CQC was also compared with a threshold-based baseline approach. RESULTS: For the 5 organs, the average area under the curve was 0.982 ± 0.01 and 0.979 ± 0.01, the mean accuracy was 95.8% ± 1.7% and 94.3% ± 2.1%, and the mean risk rate was 0.8% ± 0.4% and 0.7% ± 0.5% for MRI and CT testing data set, respectively. The CQC results closely matched the IOV results (mean accuracy of 94.2% ± 0.8% and 94.8% ± 1.7%) and were significantly higher than those obtained using the threshold-based method (mean accuracy of 80.0% ± 4.7%, 83.8% ± 5.2%, and 77.3% ± 6.6% using 1, 2, and 3 metrics). CONCLUSIONS: The CQC models demonstrated high performance in classifying the quality of contour slices. This method can address the limitations of existing metrics and offers an intuitive and comprehensive solution for clinically oriented evaluation and comparison of DLAS systems.

Patterns of Locoregional Pancreatic Cancer Recurrence After Total Neoadjuvant Therapy and Implications on Optimal Neoadjuvant Radiation Treatment Volumes.

PURPOSE: To generate a map of local recurrences after neoadjuvant chemotherapy and radiation (total neoadjuvant therapy or TNT) followed by surgical resection for pancreatic ductal adenocarcinoma (PDAC). Such recurrence patterns will serve to inform radiation treatment planning volumes that should be given in the neoadjuvant setting. METHODS: Locoregional recurrences following TNT followed by surgery treated between 2009-2022 were radiologically identified. Recurrences were individually segmented using MIM software and complied in a single base scan. All contour compilations were used to create a threshold contour encompassing 80% of recurrences among all patients, head only, and body/tail only. The distance between organs at risk and the threshold contour were measured to design an optimal clinical target volume (CTV) contour for patients treated with TNT. Recurrence patterns were also compared to existing adjuvant guidelines to assess coverage. RESULTS: A database of 484 patients managed with TNT for PDAC was queried. While locoregional recurrences were rare in this cohort, we identified eighty patients with either isolated locoregional or simultaneous local and distant recurrences. Patients with diagnostic imaging at the time of recurrence were identified. The majority of recurrences were partially in the field of published contouring guidelines or volumetric expansions off of vessels, and volumetric coverage was low for all. Common areas of recurrence include the aortico-diaphragmatic junction, retro-pancreatic duodenal nodal basin, and the region to the right of the superior mesenteric artery. A novel set of proposed neoadjuvant contours was designed to cover the central-most 80% of recurrences. CONCLUSIONS: This is the largest collection of local/regional PDAC recurrences from a cohort of patients treated exclusively with TNT. Patterns of local/regional recurrence using TNT in PDAC vary significantly from those patients with PDAC treated with a surgery-first approach. Novel contouring guidelines presented herein can help to ensure optimal coverage of high risk regions and avoid reliance on the current adjuvant guidelines to guide treatment planning.

Treatment planning for MR-guided SBRT of pancreatic tumors on a 1.5 T MR-Linac: A global consensus protocol.

Background and purpose: Treatment planning for MR-guided stereotactic body radiotherapy (SBRT) for pancreatic tumors can be challenging, leading to a wide variation of protocols and practices. This study aimed to harmonize treatment planning by developing a consensus planning protocol for MR-guided pancreas SBRT on a 1.5 T MR-Linac. Materials and methods: A consortium was founded of thirteen centers that treat pancreatic tumors on a 1.5 T MR-Linac. A phased planning exercise was conducted in which centers iteratively created treatment plans for two cases of pancreatic cancer. Each phase was followed by a meeting where the instructions for the next phase were determined. After three phases, a consensus protocol was reached. Results: In the benchmarking phase (phase I), substantial variation between the SBRT protocols became apparent (for example, the gross tumor volume (GTV) D99% ranged between 36.8 - 53.7 Gy for case 1, 22.6 - 35.5 Gy for case 2). The next phase involved planning according to the same basic dosimetric objectives, constraints, and planning margins (phase II), which led to a large degree of harmonization (GTV D99% range: 47.9-53.6 Gy for case 1, 33.9-36.6 Gy for case 2). In phase III, the final consensus protocol was formulated in a treatment planning system template and again used for treatment planning. This not only resulted in further dosimetric harmonization (GTV D99% range: 48.2-50.9 Gy for case 1, 33.5-36.0 Gy for case 2) but also in less variation of estimated treatment delivery times. Conclusion: A global consensus protocol has been developed for treatment planning for MR-guided pancreatic SBRT on a 1.5 T MR-Linac. Aside from harmonizing the large variation in the current clinical practice, this protocol can provide a starting point for centers that are planning to treat pancreatic tumors on MR-Linac systems.

Safety and Tolerability of Online Adaptive High-Field Magnetic Resonance-Guided Radiotherapy.

Importance: In 2018, the first online adaptive magnetic resonance (MR)-guided radiotherapy (MRgRT) system using a 1.5-T MR-equipped linear accelerator (1.5-T MR-Linac) was clinically introduced. This system enables online adaptive radiotherapy, in which the radiation plan is adapted to size and shape changes of targets at each treatment session based on daily MR-visualized anatomy. Objective: To evaluate safety, tolerability, and technical feasibility of treatment with a 1.5-T MR-Linac, specifically focusing on the subset of patients treated with an online adaptive strategy (ie, the adapt-to-shape [ATS] approach). Design, Setting, and Participants: This cohort study included adults with solid tumors treated with a 1.5-T MR-Linac enrolled in Multi Outcome Evaluation for Radiation Therapy Using the MR-Linac (MOMENTUM), a large prospective international study of MRgRT between February 2019 and October 2021. Included were adults with solid tumors treated with a 1.5-T MR-Linac. Data were collected in Canada, Denmark, The Netherlands, United Kingdom, and the US. Data were analyzed in August 2023. Exposure: All patients underwent MRgRT using a 1.5-T MR-Linac. Radiation prescriptions were consistent with institutional standards of care. Main Outcomes and Measures: Patterns of care, tolerability, and technical feasibility (ie, treatment completed as planned). Acute high-grade radiotherapy-related toxic effects (ie, grade 3 or higher toxic effects according to Common Terminology Criteria for Adverse Events version 5.0) occurring within the first 3 months after treatment delivery. Results: In total, 1793 treatment courses (1772 patients) were included (median patient age, 69 years [range, 22-91 years]; 1384 male [77.2%]). Among 41 different treatment sites, common sites were prostate (745 [41.6%]), metastatic lymph nodes (233 [13.0%]), and brain (189 [10.5%]). ATS was used in 1050 courses (58.6%). MRgRT was completed as planned in 1720 treatment courses (95.9%). Patient withdrawal caused 5 patients (0.3%) to discontinue treatment. The incidence of radiotherapy-related grade 3 toxic effects was 1.4% (95% CI, 0.9%-2.0%) in the entire cohort and 0.4% (95% CI, 0.1%-1.0%) in the subset of patients treated with ATS. There were no radiotherapy-related grade 4 or 5 toxic effects. Conclusions and Relevance: In this cohort study of patients treated on a 1.5-T MR-Linac, radiotherapy was safe and well tolerated. Online adaptation of the radiation plan at each treatment session to account for anatomic variations was associated with a low risk of acute grade 3 toxic effects.

Chemotherapy-free treatment targeting fusions and driver mutations in KRAS wild-type pancreatic ductal adenocarcinoma, a case series.

Background: KRAS wild-type (WT) pancreatic ductal adenocarcinoma (PDAC) represents a distinct entity with unique biology. The therapeutic impact of matched targeted therapy in these patients in a real-world setting, to date, is less established. Objectives: The aim of our study was to review our institutional database to identify the prevalence of actionable genomic alterations in patients with KRAS-WT tumors and to evaluate the therapeutic impact of matched targeted therapy in these patients. Design: We reviewed electronic medical records of patients with KRAS-WT PDAC and advanced disease (n = 14) who underwent clinical-grade tissue ± liquid next-generation sequencing (315-648 genes for tissue) between years 2015 and 2021. Methods: Demographic and disease characteristics were summarized using descriptive parameters. Progression-free survival (PFS) and overall survival (OS) were estimated using the Kaplan-Meier method. Results: Of 236 PDAC patients, 14 had advanced/metastatic disease with KRAS-WT tumors. Median age at diagnosis was 66 years. There was a high frequency of potentially actionable genomic alterations, including three (21%) with BRAF alterations, two (14%) with fusions [RET-PCM1 and FGFR2-POC1B (N = 1 each)]; and one with a druggable EGFR (EGFR E746_A755delISERD) variant; two other patients had an STK11 and a MUTYH alteration. Five patients were treated with matched targeted therapy, with three having durable benefit: (i) erlotinib for EGFR-altered tumor, followed by osimertinib/capmatinib when MET amplification emerged (first-line therapy); (ii) pralsetinib for RET fusion (fifth line); and (iii) dabrafenib/trametinib for BRAF N486_P490del (third line). Duration of time on chemotherapy-free matched targeted therapy for these patients was 17+, 11, and 18+ months, respectively. Conclusion: Sustained therapeutic benefit can be achieved in a real-world setting in a subset of patients with advanced/metastatic KRAS-WT PDAC treated with chemotherapy-free matched targeted agents. Prospective studies are warranted.

Changes in Daily Apparent Diffusion Coefficient on Fully Quantitative Magnetic Resonance Imaging Correlate With Established Genomic Pathways of Radiation Sensitivity and Reveal Novel Biologic Associations.

PURPOSE: Changes in quantitative magnetic resonance imaging (qMRI) are frequently observed during chemotherapy or radiation therapy (RT). It is hypothesized that qMRI features are reflective of underlying tissue responses. It's unknown what underlying genomic characteristics underly qMRI changes. We hypothesized that qMRI changes may correlate with DNA damage response (DDR) capacity within human tumors. Therefore, we designed the current study to correlate qMRI changes from daily RT treatment with underlying tumor transcriptomic profiles. METHODS AND MATERIALS: Study participants were prospectively enrolled (National Clinical Trial 03500081). RNA expression levels for 757 genes from pretreatment biopsies were obtained using a custom panel that included signatures of radiation sensitivity and DDR. Daily qMRI data were obtained from a 1.5 Tesla MR linear accelerator. Using these images, d-slow, d-star, perfusion, and apparent diffusion coefficient-mean values in tumors were plotted per-fraction, over time, and associated with genomic pathways. RESULTS: A total of 1022 qMRIs were obtained from 39 patients and both genomic data and qMRI data from 27 total patients. For 20 of those patients, we also generated normal tissue transcriptomic data. Radio sensitivity index values most closely associated with tissue of origin. Multiple genomic pathways including DNA repair, peroxisome, late estrogen receptor responses, KRAS signaling, and UV response were significantly associated with qMRI feature changes (P < .001). CONCLUSIONS: Genomic pathway associations across metabolic, RT sensitivity, and DDR pathways indicate common tumor biology that may correlate with qMRI changes during a course of treatment. Such data provide hypothesis-generating novel mechanistic insight into the biologic meaning of qMRI changes during treatment and enable optimal selection of imaging biomarkers for biologically MR-guided RT.

Transcriptomic-Based Microenvironment Classification Reveals Precision Medicine Strategies for Pancreatic Ductal Adenocarcinoma.

BACKGROUND & AIMS: The complex tumor microenvironment (TME) of pancreatic ductal adenocarcinoma (PDAC) has hindered the development of reliable predictive biomarkers for targeted therapy and immunomodulatory strategies. A comprehensive characterization of the TME is necessary to advance precision therapeutics in PDAC. METHODS: A transcriptomic profiling platform for TME classification based on functional gene signatures was applied to 14 publicly available PDAC datasets (n = 1657) and validated in a clinically annotated independent cohort of patients with PDAC (n = 79). Four distinct subtypes were identified using unsupervised clustering and assessed to evaluate predictive and prognostic utility. RESULTS: TME classification using transcriptomic profiling identified 4 biologically distinct subtypes based on their TME immune composition: immune enriched (IE); immune enriched, fibrotic (IE/F); fibrotic (F); and immune depleted (D). The IE and IE/F subtypes demonstrated a more favorable prognosis and potential for response to immunotherapy compared with the F and D subtypes. Most lung metastases and liver metastases were subtypes IE and D, respectively, indicating the role of clonal phenotype and immune milieu in developing personalized therapeutic strategies. In addition, distinct TMEs with potential therapeutic implications were identified in treatment-naive primary tumors compared with tumors that underwent neoadjuvant therapy. CONCLUSIONS: This novel approach defines a distinct subgroup of PADC patients that may benefit from immunotherapeutic strategies based on their TME subtype and provides a framework to select patients for prospective clinical trials investigating precision immunotherapy in PDAC. Further, the predictive utility and real-world clinical applicability espoused by this transcriptomic-based TME classification approach will accelerate the advancement of precision medicine in PDAC.

Characterization of an oligometastatic state in patients with metastatic pancreatic adenocarcinoma undergoing systemic chemotherapy.

PURPOSE/OBJECTIVES: Most patients with pancreatic adenocarcinoma (PDAC) will present with distant metastatic disease at diagnosis. We sought to identify clinical characteristics associated with prolonged overall survival (OS) in patients presenting with metastatic PDAC. MATERIALS/METHODS: Patients presenting with metastatic PDAC that received treatment at our institution with FOLFIRINOX or gemcitabine-based chemotherapies between August 1, 2011 and September 1, 2017 were included in the study. Metastatic disease burden was comprehensively characterized radiologically via individual diagnostic imaging segmentation. Landmark analysis was performed at 18 months, and survival curves were estimated using the Kaplan-Meier method and compared between groups via the log-rank test. ECOG and Charlson Comorbidity Index (CCI) were calculated for all patients. RESULTS: 121 patients were included with a median age of 62 years (37-86), 40% were female, 25% had ECOG 0 at presentation. Of the 121 patients included, 33% (n = 41) were alive at 12 months and 25% (n = 31) were alive at 18 months. Landmark analysis demonstrated a significant difference between patients surviving <18 months and ≥18 months regarding the presence of lung only metastases (36% vs. 16%, p = 0.04), number of organs with metastases (≥2 vs. 1, p = 0.04), and disease volume (mean of 19.1 cc vs. 1.4 cc, p = 0.04). At Year 1, predictors for improved OS included ECOG status at diagnosis (ECOG 0 vs. ECOG 1, p = 0.04), metastatic disease volume at diagnosis (≤0.1 cc vs. >60 cc, p = 0.004), metastasis only in the liver (p = 0.04), and normalization of CA 19-9 (p < 0.001). At Year 2, the only predictor of improved OS was normalization of the CA 19-9 (p = 0.03). In those patients that normalized their CA 19-9, median overall survival was 16 months. CONCLUSIONS: In this exploratory analysis normalization of CA-19-9 or volumetric metastatic disease burden less than 0.2 cc demonstrated a remarkable OS, similar to that of patients with non-metastatic disease. These metrics are useful for counseling patients and identifying cohorts that may be optimal for trials exploring metastatic and/or local tumor-directed interventions.

Clinical outcomes after online adaptive MR-guided stereotactic body radiotherapy for pancreatic tumors on a 1.5 T MR-linac.

Introduction: Online adaptive magnetic resonance-guided radiotherapy (MRgRT) is a promising treatment modality for pancreatic cancer and is being employed by an increasing number of centers worldwide. However, clinical outcomes have only been reported on a small scale, often from single institutes and in the context of clinical trials, in which strict patient selection might limit generalizability of outcomes. This study presents clinical outcomes of a large, international cohort of patients with (peri)pancreatic tumors treated with online adaptive MRgRT. Methods: We evaluated clinical outcomes and treatment details of patients with (peri)pancreatic tumors treated on a 1.5 Tesla (T) MR-linac in two large-volume treatment centers participating in the prospective MOMENTUM cohort (NCT04075305). Treatments were evaluated through schematics, dosage, delivery strategies, and success rates. Acute toxicity was assessed until 3 months after MRgRT started, and late toxicity from 3-12 months of follow-up (FU). The EORTC QLQ-C30 questionnaire was used to evaluate the quality of life (QoL) at baseline and 3 months of FU. Furthermore, we used the Kaplan-Meier analysis to calculate the cumulative overall survival. Results: A total of 80 patients were assessed with a median FU of 8 months (range 1-39 months). There were 34 patients who had an unresectable primary tumor or were medically inoperable, 29 who had an isolated local recurrence, and 17 who had an oligometastasis. A total of 357 of the 358 fractions from all hypofractionated schemes were delivered as planned. Grade 3-4 acute toxicity occurred in 3 of 59 patients (5%) with hypofractionated MRgRT and grade 3-4 late toxicity in 5 of 41 patients (12%). Six patients died within 3 months after MRgRT; in one of these patients, RT attribution could not be ruled out as cause of death. The QLQ-C30 global health status remained stable from baseline to 3 months FU (70.5 at baseline, median change of +2.7 [P = 0.5]). The 1-year cumulative overall survival for the entire cohort was 67%, and that for the primary tumor group was 66%. Conclusion: Online adaptive MRgRT for (peri)pancreatic tumors on a 1.5 T MR-Linac could be delivered as planned, with low numbers of missed fractions. In addition, treatments were associated with limited grade 3-4 toxicity and a stable QoL at 3 months of FU.

Stereotactic Body Radiation Therapy for Gynecologic Malignancies: A Case-Based Radiosurgery Society Practice Review.

PURPOSE: The use of stereotactic body radiation therapy (SBRT) for gynecologic malignancies is controversial. We discuss certain circumstances when highly precise SBRT may be a useful tool to consider in the management of selected patients. METHODS AND MATERIALS: Case selection included the following scenarios, the first 2 with palliative intent, para-aortic nodal oligorecurrence of ovarian cancer, pelvic sidewall oligorecurrence of cervical cancer, and inoperable endometrial cancer boost after intensity modulated radiation to the pelvis treated with curative intent. Patient characteristics, fractionation, prescription dose, treatment technique, and dose constraints were discussed. Relevant literature to these cases was summarized to provide a framework for treatment of similar patients. RESULTS: Treatment of gynecologic malignancies with SBRT requires many considerations, including treatment intent, optimal patient selection, fractionation selection, tumor localization, and plan optimization. Although other treatment paradigms including conventionally fractionated radiation therapy and brachytherapy remain the standard-of-care for definitive treatment of gynecologic malignancies, SBRT may have a role in palliative cases or those where high doses are not required due to the unacceptable toxicity that may occur with SBRT. CONCLUSIONS: A case-based practice review was developed by the Radiosurgery Society to provide a practical guide to the common scenarios noted above affecting patients with gynecologic malignancies.

A general framework to develop a radiomic fingerprint for progression-free survival in cervical cancer.

PURPOSE: Treatment of locally advanced cervical cancer patients includes chemoradiation followed by brachytherapy. Our aim is to develop a delta radiomics (DRF) model from MRI-based brachytherapy treatment and assess its association with progression free survival (PFS). MATERIALS AND METHODS: A retrospective analysis of FIGO stage IB- IV cervical cancer patients between 2012 and 2018 who were treated with definitive chemoradiation followed by MRI-based intracavitary brachytherapy was performed. Clinical factors together with 18 radiomic features extracted from different radiomics matrices were analyzed. The delta radiomic features (DRFs) were extracted from MRI on the first and last brachytherapy fractions. Support Vector Machine (SVM) models were fitted to combinations of 2-3 DRFs found significant after Spearman correlation and Wilcoxon rank sum test statistics. Additional models were tested that included clinical factors together with DRFs. RESULTS: A total of 39 patients were included in the analysis with a median patient age of 52 years. Progression occurred in 20% of patients (8/39). The significant DRFs using two DRF feature combinations was a model using auto correlation (AC) and sum variance (SV). The best performing three feature model combined mean, AC & SV. Additionally, the inclusion of FIGO stages with the 2- and 3 DRF combination model(s) improved performance compared to models with only DRFs. However, all the clinical factor + DRF models were not significantly different from one another (all AUCs were 0.77). CONCLUSIONS: Our study shows promising evidence that radiomics metrics are associated with progression free survival in cervical cancer.

Considerations for pharmacologic thromboprophylaxis following inpatient brachytherapy for gynecologic malignancies.

PURPOSE: Brachytherapy irradiation carries risks of both bleeding and venous thromboembolism (VTE). No screening or management recommendations for VTE in this setting have been developed. Our study aims to understand the incidence of VTE, compile published anticoagulation guidelines, and call for future guidelines to address thromboprophylaxis in this population. METHODS AND MATERIALS: A retrospective, single institution study of patients undergoing brachytherapy irradiation between 2012 and 2022 was undertaken. We analyzed 2 cohorts: 87 patients undergoing brachytherapy with an inpatient admission, and 66 patients assessed for risk of VTE or bleeding after discharge from an inpatient admission for brachytherapy. Caprini risk scores were calculated for each patient, and statistical analyses were performed. RESULTS: Eighty-seven patients were included, and 25% had a VTE diagnosis. Forty-seven (54%) of patients included underwent brachytherapy as definitive treatment of cervical cancer, and 16 (18%) received brachytherapy irradiation to treat recurrent endometrial cancer. In the cohort of 66 patients assessed for risk of VTE or bleeding after brachytherapy discharge, 23 (34.8%) were discharged with thromboprophylaxis, and 43 (65.2%) were discharged without thromboprophylaxis. None of the patients discharged on thromboprophylaxis were diagnosed with a VTE within 90 days of discharge after brachytherapy, whereas 3 of 43 (7%) discharged without thromboprophylaxis were diagnosed with a VTE, OR and 95% CI: 0.25 (0.01-5.29), p = 0.37. Of the 23 patients discharged on thromboprophylaxis, 1 was readmitted for bleeding OR and 95% CI: 5.8 (0.22-155.18), p = 0.29. The median Caprini score was 11. CONCLUSIONS: VTE is a common occurrence in patients undergoing brachytherapy. Patients undergoing brachytherapy irradiation who require inpatient admission represent a unique population, and specialty organizations should develop consensus recommendations to address these clinical challenges.

Deep learning auto-segmentation on multi-sequence magnetic resonance images for upper abdominal organs.

Introduction: Multi-sequence multi-parameter MRIs are often used to define targets and/or organs at risk (OAR) in radiation therapy (RT) planning. Deep learning has so far focused on developing auto-segmentation models based on a single MRI sequence. The purpose of this work is to develop a multi-sequence deep learning based auto-segmentation (mS-DLAS) based on multi-sequence abdominal MRIs. Materials and methods: Using a previously developed 3DResUnet network, a mS-DLAS model using 4 T1 and T2 weighted MRI acquired during routine RT simulation for 71 cases with abdominal tumors was trained and tested. Strategies including data pre-processing, Z-normalization approach, and data augmentation were employed. Additional 2 sequence specific T1 weighted (T1-M) and T2 weighted (T2-M) models were trained to evaluate performance of sequence-specific DLAS. Performance of all models was quantitatively evaluated using 6 surface and volumetric accuracy metrics. Results: The developed DLAS models were able to generate reasonable contours of 12 upper abdomen organs within 21 seconds for each testing case. The 3D average values of dice similarity coefficient (DSC), mean distance to agreement (MDA mm), 95 percentile Hausdorff distance (HD95% mm), percent volume difference (PVD), surface DSC (sDSC), and relative added path length (rAPL mm/cc) over all organs were 0.87, 1.79, 7.43, -8.95, 0.82, and 12.25, respectively, for mS-DLAS model. Collectively, 71% of the auto-segmented contours by the three models had relatively high quality. Additionally, the obtained mS-DLAS successfully segmented 9 out of 16 MRI sequences that were not used in the model training. Conclusion: We have developed an MRI-based mS-DLAS model for auto-segmenting of upper abdominal organs on MRI. Multi-sequence segmentation is desirable in routine clinical practice of RT for accurate organ and target delineation, particularly for abdominal tumors. Our work will act as a stepping stone for acquiring fast and accurate segmentation on multi-contrast MRI and make way for MR only guided radiation therapy.

Evolution in the Presence and Evidence Category of Radiation Therapy Treatment Recommendations in the National Comprehensive Cancer Network Clinical Practice Guidelines in Oncology.

Purpose: The changes in the recommended use of radiation therapy (RT) in the presence of expanding systemic cancer therapies and technological advances are poorly characterized. We sought to understand the recommended utilization of RT across a broad range of malignancies by examining National Comprehensive Cancer Network (NCCN) Guidelines. Methods and Materials: We conducted a comprehensive review and categorization of RT recommendations, with their subsequent supporting evidence categories, in 3 versions of NCCN Guidelines, specifically years 2000, 2009, and 2019. These NCCN Guidelines were individually examined for RT-specific recommendations among the 10 most common tumors. The presence of RT as a recommended modality was recorded for each tumor type in each guideline. Recommendation categories including Category 1, 2A, 2B, and 3 were tallied and compared with examine totals and percentage distributions in each tumor type. Results: A total of 3858 NCCN recommendations were individually reviewed. The presence of a recommendation inclusive of RT increased from incidence of 205 in the year 2000 to 992 in the year 2019 (383%). In the 2019 NCCN Guidelines, the most Category 1 RT recommendations were found within small cell lung (13%), non-small cell lung (5%), breast (5%), bladder (2%), rectal (2%), and non-Hodgkin lymphoma (1%). Pancreatic, uterine, prostate, melanoma, kidney, and colon cancer guidelines had no Category 1 RT recommendations. Rectal cancer had 31 (27%) preferred recommendations. The majority (89%) of 2019 RT recommendations were for initial therapy, and 9% were specific to salvage therapy. Tumor sites with the highest proportion of RT Category 1 evidence were small cell lung (29%), non-small cell lung (24%), and breast cancer (24%). Conclusions: The frequency of recommendations for using RT in NCCN Guidelines has increased by >300% in the past 20 years among the 10 most common malignancies. Consideration of the quality of evidence supporting these recommendations by tumor type is useful to identify specific malignancies in need of higher-level evidence supporting the role of RT.

Biliary Adverse Events During Neoadjuvant Therapy for Pancreatic Cancer.

OBJECTIVE: To describe a high-volume experience with biliary drainage before neoadjuvant therapy (NAT) for patients with operable pancreatic cancer (PC) and characterize the association between biliary adverse events (BAEs) and patient outcome. BACKGROUND: Patients with PC presenting with biliary obstruction require durable decompression before NAT. METHODS: Patients with operable PC and tumor-associated biliary obstruction were examined and grouped by the presence or absence of a BAE during NAT. The incidence, timing, and management of BAEs are described, and outcomes, including the completion of all treatment and overall survival (OS), were compared. RESULTS: Of 426 patients who received pretreatment biliary decompression, 92 (22%) experienced at least 1 BAE during NAT, and 56 (13%) required repeat intervention on their biliary stent. The median duration of NAT was 161 days for all patients and was not different in the group that experienced BAEs. The median time from initial stent placement to BAE was 64 days. An interruption in the delivery of NAT (median 7 days) occurred in 25 (6%) of 426 patients. Among 426 patients, 290 (68%) completed all NAT, including surgery: 60 (65%) of 92 patients with BAE and 230 (69%) of 334 patients without BAE ( P =0.51). Among 290 patients who completed NAT and surgery, the median OS was 39 months, 26 months for the 60 patients with BAE, and 43 months for the 230 patients without BAE ( P =0.02). CONCLUSIONS: During extended multimodal NAT for PC, 22% of patients experienced a BAE. Although BAEs were not associated with a significant interruption of treatment, patients who experienced a BAE had worse OS.