A randomized patient education trial investigating treatment-related distress and satisfaction with the use of an at-home gynecologic brachytherapy educational video.

BACKGROUND: Physician explanation of gynecologic brachytherapy can be overwhelming or induce patient anxiety, and may be time-constrained given clinical limitations. We report the first randomized trial of an educational video intervention in gynecologic brachytherapy on patient-reported outcomes. METHODS: Between February 2020 and January 2022, 80 gynecologic cancer patients prescribed brachytherapy were randomly assigned to either standard informed consent (Arm A) or a supplemental 16 min brachytherapy educational video (https://vimeo.com/403385455/d0716e3cc8) via the internet (Arm B). Primary outcome was treatment-related distress (National Comprehensive Cancer Network (NCCN) distress scale scored 0 (no distress) to 10 (maximum distress)). Secondary outcome was patient satisfaction (summated Likert-scale scored 11-55). Surveys were administered at baseline, after first treatment, and prior to brachytherapy completion. RESULTS: All patients completed the prescribed brachytherapy. In Arm B, 19/40 (48%) patients and 10/40 (25%) patients' family/friends viewed the video. For patients that completed all surveys (Arm A n=29, Arm B n=28), there was no difference between arms in the sociodemographic, clinical, or treatment variables. Distress scores were low at baseline (Arm A median 4, Arm B median 4, p=0.65) and there was no detectable change in distress between arms on surveys 1 and 2 (ß 0.36, p=0.67) or surveys 1 and 3 (ß -1.02, p=0.29) in multivariable analysis. Satisfaction scores were high at baseline (Arm A median 54, Arm B median 54.5, p=0.64) and there was no detectable change in satisfaction between arms on surveys 1 and 2 (ß 0.22, p=0.93) or surveys 1 and 3 (ß 0.63, p=0.85) in multivariable analysis. CONCLUSIONS: Among patients randomized to an educational video tool for gynecologic brachytherapy, approximately 50% of the cohort and 25% of the cohort's family/friends used the video. Overall, patients had low distress scores and high satisfaction scores with no significant differences between the standard and video intervention arms. Further work is needed to understand factors contributing to gynecologic brachytherapy anxiety. TRIAL REGISTRATION NUMBER: NCT04363957.

Immunotherapy and radiation therapy sequencing: State of the data on timing, efficacy, and safety.

Radiation therapy exerts a tumoricidal local effect as well as both local and systemic immunomodulation. Immune checkpoint blockade has become a widely used treatment modality across cancer types with a rapidly growing list of agents and US Food and Drug Administration-approved indications. Moreover, there may be synergy between radiation therapy and immune checkpoint blockade. Various strategies have been used, but the optimal sequencing of these therapies is unclear. In this review, the authors discuss the major mechanisms of available immune checkpoint inhibitors and explore the available preclinical and clinical evidence regarding treatment sequencing. They also review safety considerations and conclude with possible future directions.

Technical note: Atlas-based Auto-segmentation of masticatory muscles for head and neck cancer radiotherapy.

PURPOSE: The study aimed to use quantitative geometric and dosimetric metrics to assess the accuracy of atlas-based auto-segmentation of masticatory muscles (MMs) compared to manual drawn contours for head and neck cancer (HNC) radiotherapy (RT). MATERIALS AND METHODS: Fifty-eight patients with HNC treated with RT were analyzed. Paired MMs (masseter, temporalis, and medial and lateral pterygoids) were manually delineated on planning computed tomography (CT) images for all patients. Twenty-nine patients were used to generate the MM atlas. Using this atlas, automatic segmentation of the MMs was performed for the remaining 29 patients without manual correction. Auto-segmentation accuracy for MMs was compared using dice similarity coefficients (DSCs), Hausdorff distance (HD), HD95, and variation in the center of mass (∆COM). The dosimetric impact on MMs was calculated (∆dose) using dosimetric parameters (D99%, D95%, D50%, and D1%), and compared with the geometric indices to test correlation. RESULTS: DSCmean ranges from 0.79 ± 0.04 to 0.85 ± 0.04, HDmean from 0.43 ± 0.08 to 0.82 ± 0.26 cm, HD95mean from 0.32 ± 0.08 to 0.42 ± 0.16 cm, and ∆COMmean from 0.18 ± 0.11 to 0.33 ± 0.23 cm. The mean MM volume difference was < 15%. The correlation coefficient (r) of geometric and dosimetric indices for the four MMs ranges between -0.456 and 0.300. CONCLUSIONS: Atlas-based auto-segmentation for masticatory muscles provides geometrically accurate contours compared to manual drawn contours. Dose obtained from those auto-segmented contours is comparable to that from manual drawn contours. Atlas-based auto-segmentation strategy for MM in HN radiotherapy is readily availalbe for clinical implementation.

Role of Immunotherapy in the Management of Locally Advanced and Recurrent/Metastatic Cervical Cancer.

Despite combined therapeutic approaches, there is an unmet clinical need to identify effective strategies for improved patient outcomes in treating locally advanced and metastatic cervical cancer (CC). Immunotherapy is emerging as a novel therapeutic approach in this disease for which the causative agent, human papillomavirus (HPV), has dynamic, complex immunomodulatory effects. This review explores the biologic rational of immuno-oncology in the treatment of CC and discusses the initial clinical efficacy, ongoing clinical trials, and rationale for combined multimodal treatment approaches for locally advanced and recurrent/metastatic CC. The utility of immune checkpoint inhibitors is explored, including anti-cytotoxic T-lymphocyte antigen-4 (CTLA-4), PD-1, and PD-L1. Preliminary data supporting the combination of radiotherapy and immunotherapy and areas of active drug development for CC are also reviewed.

Characterizing mechanical and medical imaging properties of polyvinyl chloride-based tissue-mimicking materials.

Polyvinyl chloride (PVC) is a commonly used tissue-mimicking material (TMM) for phantom construction using 3D printing technology. PVC-based TMMs consist of a mixture of PVC powder and dioctyl terephthalate as a softener. In order to allow the clinical use of a PVC-based phantom use across CT and magnetic resonance imaging (MRI) imaging platforms, we evaluated the mechanical and physical imaging characteristics of ten PVC samples. The samples were made with different PVC-softener ratios to optimize phantom bioequivalence with physiologic human tissue. Phantom imaging characteristics, including computed tomography (CT) number, MRI relaxation time, and mechanical properties (e.g., Poisson's ratio and elastic modulus) were quantified. CT number varied over a range of approximately -10 to 110 HU. The relaxation times of the T1-weighted and T2-weighted images were 206.81 ± 17.50 and 20.22 ± 5.74 ms, respectively. Tensile testing was performed to evaluate mechanical properties on the three PVC samples that were closest to human tissue. The elastic moduli for these samples ranged 7.000-12.376 MPa, and Poisson's ratios were 0.604-0.644. After physical and imaging characterization of the various PVC-based phantoms, we successfully produced a bioequivalent phantom compatible with multimodal imaging platforms for machine calibration and image optimization/benchmarking. By combining PVC with 3D printing technologies, it is possible to construct imaging phantoms simulating human anatomies with tissue equivalency.

Estimation of daily interfractional larynx residual setup error after isocentric alignment for head and neck radiotherapy: quality assurance implications for target volume and organs-at-risk margination using daily CT on- rails imaging.

Larynx may alternatively serve as a target or organs at risk (OAR) in head and neck cancer (HNC) image-guided radiotherapy (IGRT). The objective of this study was to estimate IGRT parameters required for larynx positional error independent of isocentric alignment and suggest population-based compensatory margins. Ten HNC patients receiving radiotherapy (RT) with daily CT on-rails imaging were assessed. Seven landmark points were placed on each daily scan. Taking the most superior-anterior point of the C5 vertebra as a reference isocenter for each scan, residual displacement vectors to the other six points were calculated postisocentric alignment. Subsequently, using the first scan as a reference, the magnitude of vector differences for all six points for all scans over the course of treatment was calculated. Residual systematic and random error and the necessary compensatory CTV-to-PTV and OAR-to-PRV margins were calculated, using both observational cohort data and a bootstrap-resampled population estimator. The grand mean displacements for all anatomical points was 5.07 mm, with mean systematic error of 1.1 mm and mean random setup error of 2.63 mm, while bootstrapped POIs grand mean displacement was 5.09 mm, with mean systematic error of 1.23 mm and mean random setup error of 2.61 mm. Required margin for CTV-PTV expansion was 4.6 mm for all cohort points, while the bootstrap estimator of the equivalent margin was 4.9 mm. The calculated OAR-to-PRV expansion for the observed residual setup error was 2.7 mm and bootstrap estimated expansion of 2.9 mm. We conclude that the interfractional larynx setup error is a significant source of RT setup/delivery error in HNC, both when the larynx is considered as a CTV or OAR. We estimate the need for a uniform expansion of 5 mm to compensate for setup error if the larynx is a target, or 3 mm if the larynx is an OAR, when using a nonlaryngeal bony isocenter.

Evaluating Automatic Segmentation for Swallowing-Related Organs for Head and Neck Cancer.

Purpose: To evaluate the accuracy of deep-learning-based auto-segmentation of the superior constrictor, middle constrictor, inferior constrictor, and larynx in comparison with a traditional multi-atlas-based method. Methods and Materials: One hundred and five computed tomography image datasets from 83 head and neck cancer patients were retrospectively collected and the superior constrictor, middle constrictor, inferior constrictor, and larynx were analyzed for deep-learning versus multi-atlas-based segmentation. Eighty-three computed tomography images (40 diagnostic computed tomography and 43 planning computed tomography) were used for training the convolutional neural network, and for atlas-based model training. The remaining 22 computed tomography datasets were used for validation of the atlas-based auto-segmentation versus deep-learning-based auto-segmentation contours, both of which were compared with the corresponding manual contours. Quantitative measures included Dice similarity coefficient, recall, precision, Hausdorff distance, 95th percentile of Hausdorff distance, and mean surface distance. Dosimetric differences between the auto-generated contours and manual contours were evaluated. Subjective evaluation was obtained from 3 clinical observers to blindly score the autosegmented structures based on the percentage of slices that require manual modification. Results: The deep-learning-based auto-segmentation versus atlas-based auto-segmentation results were compared for the superior constrictor, middle constrictor, inferior constrictor, and larynx. The mean Dice similarity coefficient values for the 4 structures were 0.67, 0.60, 0.65, and 0.84 for deep-learning-based auto-segmentation, whereas atlas-based auto-segmentation has Dice similarity coefficient results at 0.45, 0.36, 0.50, and 0.70, respectively. The mean 95th percentile of Hausdorff distance (cm) for the 4 structures were 0.41, 0.57, 0.59, and 0.54 for deep-learning-based auto-segmentation, but 0.78, 0.95, 0.96, and 1.23 for atlas-based auto-segmentation results, respectively. Similar mean dose differences were obtained from the 2 sets of autosegmented contours compared to manual contours. The dose-volume discrepancies and the average modification rates were higher with the atlas-based auto-segmentation contours. Conclusion: Swallowing-related structures are more accurately generated with DL-based versus atlas-based segmentation when compared with manual contours.

Contemporary image-guided cervical cancer brachytherapy: Consensus imaging recommendations from the Society of Abdominal Radiology and the American Brachytherapy Society.

PURPOSE: To present recommendations for the use of imaging for evaluation and procedural guidance of brachytherapy for cervical cancer patients. METHODS: An expert panel comprised of members of the Society of Abdominal Radiology Uterine and Ovarian Cancer Disease Focused Panel and the American Brachytherapy Society jointly assessed the existing literature and provide data-driven guidance on imaging protocol development, interpretation, and reporting. RESULTS: Image-guidance during applicator implantation reduces rates of uterine perforation by the tandem. Postimplant images may be acquired with radiography, computed tomography (CT), or magnetic resonance imaging (MRI), and CT or MRI are preferred due to a decrease in severe complications. Pre-brachytherapy T2-weighted MRI may be used as a reference for contouring the high-risk clinical target volume (HR-CTV) when CT is used for treatment planning. Reference CT and MRI protocols are provided for reference. CONCLUSIONS: Image-guided brachytherapy in locally advanced cervical cancer is essential for optimal patient management. Various imaging modalities, including orthogonal radiographs, ultrasound, computed tomography, and magnetic resonance imaging, remain integral to the successful execution of image-guided brachytherapy.

Fitting experimental transcription data with a comprehensive template-dependent modular kinetic model.

In the companion article, we developed a modular scheme for representing the kinetics of transcription elongation by RNA polymerase. As an example of how to use these approaches, in this article we use a comprehensive modular model of this sort to fit experimental transcript elongation results obtained on the canonical tR2 template of phage λ by means of complementary bulk gel electrophoresis and surface plasmon resonance assays. The gel electrophoresis results, obtained in experiments quenched at various times after initiation of transcription, provide distributions of RNA lengths as a function of time. The surface plasmon resonance methods were used to monitor increases and decreases in the total mass of transcription elongation complexes in the same experiments. The different measures of transcription dynamics that these methods provide allow us to use them in combination to obtain a set of largely robust and well-defined kinetic parameters. The results show that our modular approach can be used to develop and test predictive kinetic schemes that can be fit to real transcription elongation data. They also suggest that these approaches can be extended to simulate the kinetics of other processes that involve the processive extension or shortening of nucleic acid chains and related systems of sequential branching reaction events.

Management of locally advanced mesonephric carcinoma of the cervix in the setting of Mullerian Duct anomaly spectrum and unilateral renal agenesis: A case report and review of the literature.

Cervical mesonephric adenocarcinoma is a rare histologic cervical carcinoma variant arising from remnants of the mesonephric duct. Few clinical cases have been reported in the literature, and given the low rate of occurrence, the optimal management strategy is unknown. Most reported cases involve patients with either early stage (FIGO I) or metastatic disease. Herein, we report the only known case of locally advanced, node-positive cervical mesonephric carcinoma in a 55-year old woman with Mullerian duct anomaly of the uterus, obstructed hemivagina, and ipsilateral renal agenesis. To our knowledge, this would be the first case report with the concurrence of both rare entities. We review the treatment paradigm in this patient, and the literature, including radiotherapy and brachytherapy techniques.

Combination radiation and immunotherapy in gynecologic malignancies-a comprehensive review.

Definitive and adjuvant radiation and chemoradiation have been mainstays in the management of multiple gynecologic malignancies for decades. However, despite these treatments, the prognosis of patients with locally advanced, recurrent, refractory, and metastatic disease continues to be poor. Over the last decade, immune checkpoint inhibitors have emerged as a promising therapeutic modality, but response rates to monotherapy are low. Mounting basic science and translational research suggests that immunotherapy and radiation may act synergistically with the potential to improve clinical outcomes across multiple disease sites relative to monotherapy with either radiation or immunotherapy alone. Results from early clinical trials in other disease sites, and burgeoning trials within the gynecologic malignancies space hold promise for combined modality treatment. With increasing clinical data supporting combined modality therapy, there is interest in reevaluating treatment paradigms in gynecologic malignancies to improve the current standards of care. In this review, current proposed mechanisms, rationale, and evidence for treatment of gynecologic malignancies with combined radiation and immunotherapy, specifically immune checkpoint inhibitors, will be discussed. Additionally, although currently early and limited, existing clinical data will be summarized as it applies to cervical, endometrial, ovarian, and vulvar cancers. The status of current clinical trials investigating the sequencing, dosing, and fractionation of combined radiation and immunotherapy in these disease sites will also be reviewed.

The Case for Brachytherapy: Why It Deserves a Renaissance.

The recent global events related to the coronavirus disease of 2019 pandemic have significantly changed the medical landscape and led to a shift in oncologic treatment perspectives. There is a renewed focus on preserving treatment outcomes while maintaining medical accessibility and decreasing medical resource utilization. Brachytherapy, which is a vital part of the treatment course of many cancers (particularly prostate and gynecologic cancers), has the ability to deliver hypofractionated radiation and thus shorten treatment time. Studies in the early 2000s demonstrated a decline in brachytherapy usage despite data showing equivalent or even superior treatment outcomes for brachytherapy in disease sites, such as the prostate and cervix. However, newer data suggest that this trend may be reversing. The renewed call for shorter radiation courses based on data showing equivalent outcomes will likely establish hypofractionated radiation as the standard of care across multiple disease sites. With shifting reimbursement, brachytherapy represents the pinnacle in hypofractionated, conformal radiation therapy, and with extensive long-term data in support of the treatment modality brachytherapy is primed for a renaissance.

Prognostic Value of Computed Tomography and/or 18F-Fluorodeoxyglucose Positron Emission Tomography Radiomics Features in Locally Advanced Non-small Cell Lung Cancer.

INTRODUCTION: We investigated whether adding computed tomography (CT) and/or 18F-fluorodeoxyglucose (18F-FDG) PET radiomics features to conventional prognostic factors (CPFs) improves prognostic value in locally advanced non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: We retrospectively identified 39 cases with stage III NSCLC who received chemoradiotherapy and underwent planning CT and staging 18F-FDG PET scans. Seven CPFs were recorded. Feature selection was performed on 48 CT and 49 PET extracted radiomics features. A penalized multivariate Cox proportional hazards model was used to generate models for overall survival based on CPFs alone, CPFs with CT features, CPFs with PET features, and CPFs with CT and PET features. Linear predictors generated and categorized into 2 risk groups for which Kaplan-Meier survival curves were calculated. A log-rank test was performed to quantify the discrimination between the groups and calculated the Harrell's C-index to quantify the discriminatory power. A likelihood ratio test was performed to determine whether adding CT and/or PET features to CPFs improved model performance. RESULTS: All 4 models significantly discriminated between the 2 risk groups. The discriminatory power was significantly increased when CPFs were combined with PET features (C-index 0.82; likelihood ratio test P < .01) or with both CT and PET features (0.83; P < .01) compared with CPFs alone (0.68). There was no significant improvement when CPFs were combined with CT features (0.68). CONCLUSION: Adding PET radiomics features to CPFs yielded a significant improvement in the prognostic value in locally advanced NSCLC; adding CT features did not.

Current Status of Clinical Trials for Cervical and Uterine Cancer Using Immunotherapy Combined With Radiation.

Novel therapies combined with radiation continue to be of significant interest in the developmental treatment paradigm of gynecologic cancers. Clinical implementation of immunotherapy in oncology has rapidly changed the treatment landscape, options, paradigm, and outcomes through clinical trials. Immunotherapy has emerged as a therapeutic pillar in the treatment of solid tumors with demonstrable synergistic activity when combined with radiation therapy and chemoradiotherapy by an alteration or enhancement of the immune system. In solid tumors, radiation therapy induces migration of dendritic cells, T cell activation, and proliferation, and increases in tumor-infiltrating lymphocytes. These immunomodulatory effects in conjunction with immune checkpoint blockade are currently under active investigation in the adjuvant, definitive, and metastatic settings. Results from early phase trials demonstrate promising efficacy and overall tolerable toxicity profiles of combined modality treatment. There is significant interest in optimizing the treatment for patients with locally advanced cervical cancer beyond the standard of care-chemoradiation-which has been in place for the last 30 years. The majority of cervical cancer emerges after persistent infection with a high-risk subtype of the human papillomavirus, where viral oncoproteins lead to cellular changes and immortalization. As a result, immune tolerance can develop, resulting in cancer. Knowledge of the mechanism of human papillomavirus-related oncogenesis suggests that immune therapy or checkpoint blockade can reinvigorate an antitumor immune response. Current clinical trials are exploring the therapeutic potential of these approaches. Uterine cancers have been grouped into 4 molecular subclasses by their driver mutations, mutational burden, and copy-number alterations. Of these subgroups, the polymerase epsilon-mutated and microsatellite-unstable may represent up to 40% of endometrial cancers, and they have been shown to be immunogenic. Because of the inherent immunogenicity of these MSI-high tumors, combined immune modulation strategies, including chemotherapy, radiation, and immunotherapy and immune checkpoint inhibitor therapy, are being explored to improve treatment outcomes. In this review, we explore current immunomodulatory and multimodality therapeutic approaches in the treatment of cervical and uterine cancer through ongoing clinical trials investigating the combination of immunotherapy and radiation therapy.

Simulation-based learning for enhanced gynecologic brachytherapy training among radiation oncology residents.

PURPOSE: Brachytherapy is an irreplaceable component of gynecologic cancer treatment. Resident training has declined, and procedural exposure is variable. We evaluated whether simulation-based gynecologic brachytherapy training among radiation oncology residents could improve knowledge, confidence, and interest. METHODS AND MATERIALS: Before a brachytherapy workshop, radiation oncology residents without prior gynecologic brachytherapy experience completed a survey on brachytherapy knowledge, procedural confidence, plan evaluation, and quality/safety. Residents then participated in a gynecologic brachytherapy workshop. Lectures covered brachytherapy imaging and physics principles/quality assurance, followed by hands-on and individualized feedback regarding applicator selection and placement, target segmentation, and physics quality assurance. Afterward, preworkshop questions were recollected. Descriptive statistics and Fisher's exact tests were used for data analysis. RESULTS: After the workshop, resident responses regarding the learning environment and baseline knowledge questions improved overall. There was a 30% improvement in favorable responses to the learning environment statement "My residency has a formal process/curriculum to teach brachytherapy" and for baseline knowledge the greatest improvement was seen for "I am familiar with the anatomy and placement of the applicators in relation to the anatomy". "Lack of didactic or procedural training exposure" was identified as the main reason for declining brachytherapy use. Initially, 1/8 residents correctly completed the knowledge questions, and after the workshop, 6/7 (p < 0.001) residents correctly completed the questions. CONCLUSIONS: Domain-specific knowledge, procedural confidence, and brachytherapy interest improved after a gynecologic brachytherapy workshop. Integrated didactic and simulation-based brachytherapy training may serve as a valuable learning tool to augment resident knowledge, introduce practical skills, and spark resident interest in brachytherapy.

Dose Summation Strategies for External Beam Radiation Therapy and Brachytherapy in Gynecologic Malignancy: A Review from the NRG Oncology and NCTN Medical Physics Subcommittees.

Definitive, nonsurgical management of gynecologic malignancies involves external beam radiation therapy (EBRT) and/or brachytherapy (BT). Summation of the cumulative dose is critical to assess the total biologic effective dose to targets and organs at risk. Cumulative dose calculation from EBRT and BT can be performed with or without image registration (IR) and biologic dose summation. Among these dose summation strategies, linear addition of dose-volume histogram (DVH) parameters without IR is the global standard for composite dose reporting. This approach stems from an era without image guidance and simple external beam and brachytherapy treatment approaches. With technological advances, EBRT and high-dose-rate BT have evolved to allow for volume-based treatment planning and delivery. Modern conformal therapeutic radiation involves volumetric or intensity modulated EBRT, capable of simultaneously treating multiple targets at different specified dose levels. Therefore, given the complexity of modern radiation treatment, the linear addition of DVH parameters from EBRT and high-dose-rate BT is challenging to represent the combined dose distribution. Deformable image registration (DIR) between EBRT and image guided brachytherapy (IGBT) data sets may provide a more nuanced calculation of multimodal dose accumulation. However, DIR is still nascent in this regard, and needs further development for accuracy and efficiency for clinical use. Biologic dose summation can combine physical dose maps from EBRT and each IGBT fraction, thereby generating a composite DVH from the biologic effective dose. However, accurate radiobiologic parameters are tissue-dependent and not well characterized. A combination of voxel-based DIR and biologic weighted dose maps may be the best approximation of dose accumulation but remains invalidated. The purpose of this report is to review dose summation strategies for EBRT and BT, including conventional equivalent dose in 2-Gy fractions dose summation without image registration, physical dose summation using 3-dimensional rigid IR and DIR, and biologic dose summation. We also provide general clinical workflows for IGBT with a focus on cervical cancer.

Cone-beam computed tomography-based delta-radiomics for early response assessment in radiotherapy for locally advanced lung cancer.

Cone-beam computed tomography (CBCT) images acquired during radiotherapy may allow early response assessment. Previous studies have reported inconsistent findings on an association of CBCT-measured tumor volume changes with clinical outcomes. The purpose of this pilot study was twofold: (1) to characterize changes in CBCT-based radiomics features during treatment; and (2) to quantify the potential association of CBCT-based delta-radiomics features with overall survival in locally advanced lung cancer. We retrospectively identified 23 patients and calculated 658 radiomics features from each of 11 CBCT images per patient. Feature selection was performed based on repeatability, robustness against contouring uncertainties, and non-redundancy. We calculated the coefficient of determination (R 2) for the relationship between the actual feature value at the end of treatment and predicted value based on linear models fitted using features between the first and kth fractions. We also quantified the predictive ability for survival with two methods by: (1) comparing delta-radiomics features (defined as the mean change between the first and kth fractions) between two groups of patients divided by a cutoff survival time of 18 months using the t-test or Wilcoxon rank-sum test; and (2) quantifying univariate discrimination of two groups divided by the median of delta-radiomics feature. All selected seven radiomics features during treatment (as early as the 10th fraction) were predictive of those at the end of treatment (R 2 > 0.64). Three delta-radiomics features demonstrated significant differences (q < 0.05, as early as the 10th fraction) between the two groups of patients divided by the cutoff survival time. Two of those three features were also predictive of survival according to the log-rank statistics. We provided the first demonstration of a potential association of CBCT-based delta-radiomics features early during treatment with overall survival in locally advanced lung cancer. Our preliminary findings should be validated for a larger cohort of patients.

Convolutional neural network enhancement of fast-scan low-dose cone-beam CT images for head and neck radiotherapy.

To improve image quality and CT number accuracy of fast-scan low-dose cone-beam computed tomography (CBCT) through a deep-learning convolutional neural network (CNN) methodology for head-and-neck (HN) radiotherapy. Fifty-five paired CBCT and CT images from HN patients were retrospectively analysed. Among them, 15 patients underwent adaptive replanning during treatment, thus had same-day CT/CBCT pairs. The remaining 40 patients (post-operative) had paired planning CT and 1st fraction CBCT images with minimal anatomic changes. A 2D U-Net architecture with 27-layers in 5 depths was built for the CNN. CNN training was performed using data from 40 post-operative HN patients with 2080 paired CT/CBCT slices. Validation and test datasets include 5 same-day datasets with 260 slice pairs and 10 same-day datasets with 520 slice pairs, respectively. To examine the impact of differences in training dataset selection and network performance as a function of training data size, additional networks were trained using 30, 40 and 50 datasets. Image quality of enhanced CBCT images were quantitatively compared against the CT image using mean absolute error (MAE) of Hounsfield units (HU), signal-to-noise ratio (SNR) and structural similarity (SSIM). Enhanced CBCT images reduced artifact distortion and improved soft tissue contrast. Networks trained with 40 datasets had imaging performance comparable to those trained with 50 datasets and outperformed those trained with 30 datasets. Comparison of CBCT and enhanced CBCT images demonstrated improvement in average MAE from 172.73 to 49.28 HU, SNR from 8.27 to 14.25 dB, and SSIM from 0.42 to 0.85. The image processing time is 2 s per patient using a NVIDIA GeForce GTX 1080 Ti GPU. The proposed deep-leaning methodology was fast and effective for image quality enhancement of fast-scan low-dose CBCT. This method has potential to support fast online-adaptive re-planning for HN cancer patients.

Deep learning vs. atlas-based models for fast auto-segmentation of the masticatory muscles on head and neck CT images.

BACKGROUND: Impaired function of masticatory muscles will lead to trismus. Routine delineation of these muscles during planning may improve dose tracking and facilitate dose reduction resulting in decreased radiation-related trismus. This study aimed to compare a deep learning model with a commercial atlas-based model for fast auto-segmentation of the masticatory muscles on head and neck computed tomography (CT) images. MATERIAL AND METHODS: Paired masseter (M), temporalis (T), medial and lateral pterygoid (MP, LP) muscles were manually segmented on 56 CT images. CT images were randomly divided into training (n = 27) and validation (n = 29) cohorts. Two methods were used for automatic delineation of masticatory muscles (MMs): Deep learning auto-segmentation (DLAS) and atlas-based auto-segmentation (ABAS). The automatic algorithms were evaluated using Dice similarity coefficient (DSC), recall, precision, Hausdorff distance (HD), HD95, and mean surface distance (MSD). A consolidated score was calculated by normalizing the metrics against interobserver variability and averaging over all patients. Differences in dose (∆Dose) to MMs for DLAS and ABAS segmentations were assessed. A paired t-test was used to compare the geometric and dosimetric difference between DLAS and ABAS methods. RESULTS: DLAS outperformed ABAS in delineating all MMs (p < 0.05). The DLAS mean DSC for M, T, MP, and LP ranged from 0.83 ± 0.03 to 0.89 ± 0.02, the ABAS mean DSC ranged from 0.79 ± 0.05 to 0.85 ± 0.04. The mean value for recall, HD, HD95, MSD also improved with DLAS for auto-segmentation. Interobserver variation revealed the highest variability in DSC and MSD for both T and MP, and the highest scores were achieved for T by both automatic algorithms. With few exceptions, the mean ∆D98%, ∆D95%, ∆D50%, and ∆D2% for all structures were below 10% for DLAS and ABAS and had no detectable statistical difference (P > 0.05). DLAS based contours had dose endpoints more closely matched with that of the manually segmented when compared with ABAS. CONCLUSIONS: DLAS auto-segmentation of masticatory muscles for the head and neck radiotherapy had improved segmentation accuracy compared with ABAS with no qualitative difference in dosimetric endpoints compared to manually segmented contours.