Background: We compared overall survival (OS) between radiation therapy (RT) and chemoradiotherapy (CRT) in patients with anaplastic thyroid carcinoma (ATC) using a large database. Methods: The National Cancer Data Base was queried for ATC patients diagnosed between 2004 and 2013 who received RT or CRT. Groups were balanced by propensity score matching (PSM) on nine relevant variables. OS was also examined in five paired subgroups given known patient heterogeneity. Results: Of 858 total patients, 575 received CRT and 283 received RT. CRT was associated with decreased risk of death (hazard ratio [HR] 0.66, P <.001), 1-year OS 25.5% vs 14.3%. A survival advantage to CRT was seen using PSM cohorts (HR 0.75, P =.006). Those receiving definitive surgery saw the greatest benefit to CRT over RT (HR 0.65, P =.009), 1-year OS 39.6% vs 20.4%. Conclusions: CRT is associated with decreased risk of death in ATC; the magnitude of CRT vs RT benefit varied by subgroup.

Background Pathologic extranodal extension (ENE) has traditionally guided the management of head and neck cancers. The prognostic value of radiographic ENE (rENE) in HPV-associated oropharyngeal squamous cell carcinoma (HPV+OPX) is uncertain. Methods HPV+OPX patient with adequate pre-treatment radiographic nodal evaluation, from a single institution were analyzed. rENE status was determined by neuroradiologists’ at time of diagnosis. Distant metastasis-free survival (DMFS), overall survival (OS), locoregional recurrence-free survival (LRFS) and were estimated using Kaplan-Meier methods. Cox proportional hazards models were fit to assess the impact of rENE on survival endpoints. Results 168 patients with OPX+SCC diagnosed between April 2008 and December 2014 were included for analysis with median follow-up of 3.3 years. Eighty-eight percent of patients received concurrent chemoradiotherapy. rENE was not prognostic; its presence in HPV+OPX patients did not significantly impact OS, LRFS, or DMFS. Conclusions In patients with HPV+OPX, rENE was not significantly associated with OS, LRFS, or DMFS.

Background: The prognostic relevance of human papillomavirus (HPV) status in non-oropharyngeal (OPX) squamous cell cancer (SCC) of the head and neck is controversial. We evaluated the impact of high-risk HPV status on overall survival (OS) in patients with non-OPX SCC using a large database approach. Methods: The National Cancer Data Base was queried to identify patients diagnosed from 2004–2014 with SCC of the OPX, hypopharynx (HPX), larynx, and oral cavity (OC) with known HPV status. Survival was estimated using Kaplan-Meier methods; distributions were compared with log-rank tests. Propensity score matching (PSM) and inverse probability of treatment weighing (IPTW) methods were utilized; cohorts were matched on age, sex, Charlson-Deyo score, clinical group stage, treatments received, and anatomic subsite. Propensity analyses were stratified by group stage. Results: 24,740 patients diagnosed from 2010–2013 were analyzed; 1,085 patients with HPX, 4804 with larynx, 4,018 with OC, and 14,833 with OPX SCC. The proportions of HPV positive cases by site were: 17.7% in HPX, 11% in larynx, 10.6% in OC, and 62.9% in OPX. HPV status was prognostic in multiple un-adjusted and propensity-adjusted non-OPX populations. HPV positivity was associated with superior OS in HPX SCC with hazard ratio (HR) of 0.61 (p<0.001, IPTW), in stage III-IVB laryngeal SCC (HR 0.79, p=0.019, IPTW), and in stage III-IVB OC SCC (HR 0.78, p=0.03, IPTW). Conclusions: Positive high-risk HPV status is associated with longer OS in multiple non-oropharynx head and neck populations – hypopharynx, locally-advanced larynx and oral cavity. If prospectively validated, these findings have implications for risk-stratification.

Objective: The purpose of this work is to develop and validate a learning-based method to derive electron density from routine anatomical MRI for potential MRI-based SBRT treatment planning. Methods: We proposed to integrate dense block into cycle generative adversarial network (GAN) to efec-tively capture the relationship between the CT and MRI for CT synthesis. A cohort of 21 patients with co-registered CT and MR pairs were used to evaluate our proposed method by the leave-one-out cross-validation. Mean absolute error, peaksignal-to-noise ratio and normalized cross-correlation were used to quantify the imaging diferences between the synthetic CT (sCT) and CT. The accuracy of Hounsfeld unit (HU) values in sCT for dose calculation was evaluated by comparing the dose distribution in sCT-based and CT-based treatment planning. Clinically relevant dose-volume histogram metrics were then extracted from the sCT-based and CT-based plans for quantitative comparison. results: The mean absolute error, peaksignal-to-noise ratio and normalized cross-correlation of the sCT were 72.87 ± 18.16 HU, 22.65 ± 3.63 dB and 0.92 ± 0.04, respectively. No signifcant diferences were observed in the majority of the planning target volume and organ at risk dose-volume histogram metrics ( p > 0.05). The average pass rate of analysis was over 99% with 1%/1 mm acceptance criteria on the coronal plane that intersects with isocenter. Conclusion: The image similarity and dosimetric agreement between sCT and original CT warrant further development of an MRI-only workfow for liver stereo-tactic body radiation therapy. advances in knowledge: This work is the frst deep-learning-based approach to generating abdominal sCT through dense-cycle-GAN. This method can successfully generate the small bony structures such as the rib bones and is able to predict the HU values for dose calculation with comparable accuracy to reference CT images.

Purpose: Transrectal ultrasound (TRUS) is a versatile and real-time imaging modality that is commonly used in image-guided prostate cancer interventions (e.g., biopsy and brachytherapy). Accurate segmentation of the prostate is key to biopsy needle placement, brachytherapy treatment planning, and motion management. Manual segmentation during these interventions is time-consuming and subject to inter- and intra-observer variation. To address these drawbacks, we aimed to develop a deep learning-based method which integrates deep supervision into a 3D patch-based V-Net for prostate segmentation. Methods and materials: We developed a multi-directional deep-learning-based method to automatically segment the prostate for ultrasound-guided radiation therapy. A 3D supervision mechanism is integrated into the V-Net stages to deal with the optimization difficulties when training a deep network with limited training data. We combine a binary cross entropy loss and a batch-based Dice loss into the stage-wise hybrid loss function for a deep supervision training. During the segmentation stage, the patches are extracted from the newly acquired ultrasound image as the input of the well-trained network and the well-trained network adaptively labels the prostate tissue. The final segmented prostate volume is reconstructed using patch fusion and further refined through a contour refinement processing. Results: 44 patients’ TRUS images were used to test our segmentation method. Our segmentation results were compared with the manually segmented contours (ground truth). The mean prostate volume Dice Similarity Coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), residual mean surface distance (RMSD) was 0.92±0.03, 3.94±1.55 mm, 0.60±0.23 mm, and 0.90±0.38 mm, respectively. Conclusion: We developed a novel deeply supervised deep learning-based approach with reliable contour refinement to automatically segment the TRUS prostate, demonstrated its clinical feasibility, and validated its accuracy compared to manual segmentation. The proposed technique could be a useful tool for diagnostic and therapeutic applications in prostate cancer.

Frontotemporal lobar degeneration with neuronal inclusions of the TAR DNA-binding protein 43 (FTLD-TDP) represents the most common pathological subtype of FTLD. We established the international FTLD-TDP whole-genome sequencing consortium to thoroughly characterize the known genetic causes of FTLD-TDP and identify novel genetic risk factors. Through the study of 1131 unrelated Caucasian patients, we estimated that C9orf72 repeat expansions and GRN loss-of-function mutations account for 25.5% and 13.9% of FTLD-TDP patients, respectively. Mutations in TBK1 (1.5%) and other known FTLD genes (1.4%) were rare, and the disease in 57.7% of FTLD-TDP patients was unexplained by the known FTLD genes. To unravel the contribution of common genetic factors to the FTLD-TDP etiology in these patients, we conducted a two-stage association study comprising the analysis of whole-genome sequencing data from 517 FTLD-TDP patients and 838 controls, followed by targeted genotyping of the most associated genomic loci in 119 additional FTLD-TDP patients and 1653 controls. We identified three genome-wide significant FTLD-TDP risk loci: one new locus at chromosome 7q36 within the DPP6 gene led by rs118113626 (p value = 4.82e − 08, OR = 2.12), and two known loci: UNC13A, led by rs1297319 (p value = 1.27e − 08, OR = 1.50) and HLA-DQA2 led by rs17219281 (p value = 3.22e − 08, OR = 1.98). While HLA represents a locus previously implicated in clinical FTLD and related neurodegenerative disorders, the association signal in our study is independent from previously reported associations. Through inspection of our whole-genome sequence data for genes with an excess of rare loss-of-function variants in FTLD-TDP patients (n ≥ 3) as compared to controls (n = 0), we further discovered a possible role for genes functioning within the TBK1-related immune pathway (e.g., DHX58, TRIM21, IRF7) in the genetic etiology of FTLD-TDP. Together, our study based on the largest cohort of unrelated FTLD-TDP patients assembled to date provides a comprehensive view of the genetic landscape of FTLD-TDP, nominates novel FTLD-TDP risk loci, and strongly implicates the immune pathway in FTLD-TDP pathogenesis.

Allele-specific copy number analysis of tumors (ASCAT) assesses copy number variations (CNV) while accounting for aberrant cell fraction and tumor ploidy. We evaluated if ASCAT-assessed CNV are associated with survival outcomes in 56 patients with WHO grade IV gliomas. Tumor data analyzed by Affymetrix OncoScan FFPE Assay yielded the log ratio (R) and B-allele frequency (BAF). Input into ASCAT quantified CNV using the segmentation function to measure copy number inflection points throughout the genome. Quantified CNV was reported as log R and BAF segment counts. Results were confirmed on The Cancer Genome Atlas (TCGA) glioblastoma dataset. 25 (44.6%) patients had MGMT hyper-methylated tumors, 6 (10.7%) were IDH1 mutated. Median follow-up was 36.4 months. Higher log R segment counts were associate with longer progression-free survival (PFS) [hazard ratio (HR) 0.32, p < 0.001], and overall survival (OS) [HR 0.45, p = 0.01], and was an independent predictor of PFS and OS on multivariable analysis. Higher BAF segment counts were linked to longer PFS (HR 0.49, p = 0.022) and OS (HR 0.49, p = 0.052). In the TCGA confirmation cohort, longer 12-month OS was seen in patients with higher BAF segment counts (62.3% vs. 51.9%, p = 0.0129) and higher log R (63.6% vs. 55.2%, p = 0.0696). Genomic CNV may be a novel prognostic biomarker for WHO grade IV glioma patient outcomes.

Purpose: Reliable automated segmentation of the prostate is indispensable for image-guided prostate interventions. However, the segmentation task is challenging due to inhomogeneous intensity distributions, variation in prostate anatomy, among other problems. Manual segmentation can be time-consuming and is subject to inter- and intraobserver variation. We developed an automated deep learning-based method to address this technical challenge. Methods: We propose a three-dimensional (3D) fully convolutional networks (FCN) with deep supervision and group dilated convolution to segment the prostate on magnetic resonance imaging (MRI). In this method, a deeply supervised mechanism was introduced into a 3D FCN to effectively alleviate the common exploding or vanishing gradients problems in training deep models, which forces the update process of the hidden layer filters to favor highly discriminative features. A group dilated convolution which aggregates multiscale contextual information for dense prediction was proposed to enlarge the effective receptive field of convolutional neural networks, which improve the prediction accuracy of prostate boundary. In addition, we introduced a combined loss function including cosine and cross entropy, which measures similarity and dissimilarity between segmented and manual contours, to further improve the segmentation accuracy. Prostate volumes manually segmented by experienced physicians were used as a gold standard against which our segmentation accuracy was measured. Results: The proposed method was evaluated on an internal dataset comprising 40 T2-weighted prostate MR volumes. Our method achieved a Dice similarity coefficient (DSC) of 0.86 ± 0.04, a mean surface distance (MSD) of 1.79 ± 0.46 mm, 95% Hausdorff distance (95%HD) of 7.98 ± 2.91 mm, and absolute relative volume difference (aRVD) of 15.65 ± 10.82. A public dataset (PROMISE12) including 50 T2-weighted prostate MR volumes was also employed to evaluate our approach. Our method yielded a DSC of 0.88 ± 0.05, MSD of 1.02 ± 0.35 mm, 95% HD of 9.50 ± 5.11 mm, and aRVD of 8.93 ± 7.56. Conclusion: We developed a novel deeply supervised deep learning-based approach with a group dilated convolution to automatically segment the MRI prostate, demonstrated its clinical feasibility, and validated its accuracy against manual segmentation. The proposed technique could be a useful tool for image-guided interventions in prostate cancer.

Introduction: Cone-beam CT (CBCT) image quality is important for its quantitative analysis in adaptive radiation therapy. However, due to severe artifacts, the CBCTs are primarily used for verifying patient setup only so far. We have developed a learning-based image quality improvement method which could provide CBCTs with image quality comparable to planning CTs (pCTs). The accuracy of dose calculations based on these CBCTs is unknown. In this study, we aim to investigate the dosimetric accuracy of our corrected CBCT (CCBCT) in brain stereotactic radiosurgery (SRS) and pelvic radiotherapy. Materials and Methods: We retrospectively investigated a total of 32 treatment plans from 22 patients, each of whom with both original treatment pCTs and CBCTs acquired during treatment setup. The CCBCT and original CBCT (OCBCT) were registered to the pCT for generating CCBCT-based and OCBCT-based treatment plans. The original pCT-based plans served as ground truth. Clinically-relevant dose volume histogram (DVH) metrics were extracted from the ground truth, OCBCT-based and CCBCT-based plans for comparison. Gamma analysis was also performed to compare the absorbed dose distributions between the pCT-based and OCBCT/CCBCT-based plans of each patient. Results: CCBCTs demonstrated better image contrast and more accurate HU ranges when compared side-by-side with OCBCTs. For pelvic radiotherapy plans, the mean dose error in DVH metrics for planning target volume (PTV), bladder and rectum was significantly reduced, from 1% to 0.3%, after CBCT correction. The gamma analysis showed the average pass rate increased from 94.5% before correction to 99.0% after correction. For brain SRS treatment plans, both original and corrected CBCT images were accurate enough for dose calculation, though CCBCT featured higher image quality. Conclusion: CCBCTs can provide a level of dose accuracy comparable to traditional pCTs for brain and prostate radiotherapy planning and the correction method proposed here can be useful in CBCT-guided adaptive radiotherapy.

Objective. Current segmentation practice for thoracic cancer RT considers the whole heart as a single organ despite increased risks of cardiac toxicities from irradiation of specific cardiac substructures. Segmenting up to 15 different cardiac substructures can be a very time-intensive process, especially due to their different volume sizes and anatomical variations amongst different patients. In this work, a new deep learning (DL)-based mutual enhancing strategy is introduced for accurate and automatic segmentation, especially of smaller substructures such as coronary arteries. Approach. Our proposed method consists of three subnetworks: retina U-net, classification module, and segmentation module. Retina U-net is used as a backbone network architecture that aims to learn deep features from the whole heart. Whole heart feature maps from retina U-net are then transferred to four different sets of classification modules to generate classification localization maps of coronary arteries, great vessels, chambers of the heart, and valves of the heart. Each classification module is in sync with its corresponding subsequent segmentation module in a bootstrapping manner, allowing them to share their encoding paths to generate a mutual enhancing strategy. We evaluated our method on three different datasets: institutional CT datasets (55 subjects) 2) publicly available Multi-Modality Whole Heart Segmentation (MM-WHS) challenge datasets (120 subjects), and Automated Cardiac Diagnosis Challenge (ACDC) datasets (100 subjects). For institutional datasets, we performed five-fold cross-validation on training data (45 subjects) and performed inference on separate hold-out data (10 subjects). For each subject, 15 cardiac substructures were manually contoured by a resident physician and evaluated by an attending radiation oncologist. For the MM-WHS dataset, we trained the network on 100 datasets and performed an inference on a separate hold-out dataset with 20 subjects, each with 7 cardiac substructures. For ACDC datasets, we performed five-fold cross-validation on 100 datasets, each with 3 cardiac substructures. We compared the proposed method against four different network architectures: 3D U-net, mask R-CNN, mask scoring R-CNN, and proposed network without classification module. Segmentation accuracies were statistically compared through dice similarity coefficient, Jaccard, 95% Hausdorff distance, mean surface distance, root mean square distance, center of mass distance, and volume difference. Main results. The proposed method generated cardiac substructure segmentations with significantly higher accuracy (P < 0.05) for small substructures, especially for coronary arteries such as left anterior descending artery (CA-LADA) and right coronary artery (CA-RCA) in comparison to four competing methods. For large substructures (i.e. chambers of the heart), our method yielded comparable results to mask scoring R-CNN method, resulting in significantly (P < 0.05) improved segmentation accuracy in comparison to 3D U-net and mask R-CNN. Significance. A new DL-based mutual enhancing strategy was introduced for automatic segmentation of cardiac substructures. Overall results of this work demonstrate the ability of the proposed method to improve segmentation accuracies of smaller substructures such as coronary arteries without largely compromising the segmentation accuracies of larger substructures. Fast and accurate segmentations of up to 15 substructures can possibly be used as a tool to rapidly generate substructure segmentations followed by physicians' reviews to improve clinical workflow.