Search

Background: Over 20 million people in the United States identified as Asian American, Native Hawaiian, or Pacific Islander (AANHPI) in 2022. Despite the diversity of immigration histories, lived experiences, and health needs within the AANHPI community, prior studies in cervical cancer have considered this group in aggregate., Objective(s): We sought to analyze disparities in cervical cancer stage at presentation in the United States, focusing on disaggregated AANHPI groups., Study Design: Data from the United States National Cancer Database from 2004 to 2020 of 122,926 patients newly diagnosed with cervical cancer was retrospectively analyzed. AANHPI patients were disaggregated by country of origin. Logistic regression, adjusted for clinical and sociodemographic factors, was used to calculate adjusted odds ratios. Higher adjusted odds ratios indicate an increased likelihood of metastatic versus non-metastatic disease at diagnosis., Results: Out of 122,926 patients with cervical cancer, 5,142 (4.2%) identified as AANHPI. Compared to non-Hispanic White (NHW) patients, pooled AANHPI patients presented at lower stages of cancer (NHW: 58.7% diagnosed local/regional, AANHPI: 85.6% at local/regional, χ2 P<0.001). The largest AANHPI subgroups included Filipino Americans (n=1051, 20.4% of AANHPI), Chinese Americans (n=995, 19.4%), Asian Indian/Pakistani Americans (n=711, 13.8%), Vietnamese Americans (n=627, 12.2%), and Korean Americans (n=550, 10.7%) respectively. AANHPI disaggregation revealed that Pacific Islander American patients had higher odds of presenting with metastatic disease (aOR 1.58, 95% CI 1.21-2.06, p = 0.001) relative to non-Hispanic White patients. Conversely, Chinese American (aOR 0.47, 95% CI 0.37-0.59, p < 0.001), Vietnamese American (aOR 0.54, 95% CI 0.41-0.70, p < 0.001), Hmong American (aOR 0.46, 95% CI 0.22-0.97, p = 0.040), and Indian/Pakistani American (aOR 0.76, 95% CI 0.61-0.94, p = 0.013) patients were less likely to present with metastatic disease. Compared to the largest AANHPI group (Chinese American), nine other subgroups were more likely to present with metastatic disease. The largest differences were observed in Pacific Islander American (aOR 3.44, 95% CI 2.41-4.91, p < 0.001), Thai American (aOR 2.79, 95% CI 1.41-5.53, p = 0.003), Kampuchean American (aOR 2.39, 95% CI 1.29-4.42, p = 0.006), Native Hawaiian American (aOR 2.23, 95% CI 1.37-3.63, p = 0.001), and Laotian American (aOR 2.02, 95% CI 1.13-3.61, p = 0.017). In contrast, Vietnamese American (aOR 1.20, 95% CI 0.85-1.71, p = 0.303) and Hmong American (aOR 1.09, 95% CI 0.50-2.37, p = 0.828) patients did not show a statistically significant difference in presenting with metastatic disease compared to Chinese American patients., Conclusion(s): Aggregated evaluation of the Asian American, Native Hawaiian, or Pacific Islander monolith masks disparities in outcomes for distinct populations at risk for equity gaps. This disaggregation study shows that marginalized groups within the larger AANHPI population - including Pacific Islander American and Thai American patients - may face different exposures and larger structural barriers to cancer screening and early-stage diagnosis. A future focus on community based disaggregated research and tailored interventions is necessary to close these gaps., (Copyright © 2024 Elsevier Inc. All rights reserved.)

Objectives: The adoption of transoral robotic surgery and shifting epidemiology in oropharyngeal squamous cell cancer have stimulated debate over upfront and adjuvant treatment. Institutional variation in practice patterns can be obscured in patient-level analyses. We aimed to characterize institutional patterns of care as well as identify potential associations between patterns of care and survival., Methods: This was a retrospective cohort study of patients identified from 2004-2015 in the National Cancer Database. We analyzed 42,803 cases of oropharyngeal squamous cell cancer Stage cT1-2N0-2bM0 (AJCC 7th edition) treated with curative intent surgery and/or radiotherapy. We defined facility-4-year periods to account for changing institutional practice patterns. The 42,803 patients were treated within 2578 facility-4-year periods. We assessed institutional practice patterns, including the ratio of upfront surgery to definitive radiotherapy, case volumes, use of adjuvant therapies (radiotherapy or chemoradiotherapy), and margin positivity rates. Survival associations with institutional practice patterns were estimated with Cox regression., Results: The ratio of upfront surgery to definitive radiotherapy ranged from 80-to-1 to 1-to-23. The institution-level median rate of adjuvant radiotherapy was 69% (IQR 50%-100%), adjuvant chemoradiotherapy was 44% (IQR 0%-67%), and margin-positive resection was 33% (IQR 0%-50%). On patient-level MVA, worse overall survival was not significantly associated with institutional case volume, adjuvant radiotherapy, or adjuvant chemoradiotherapy utilization., Conclusions: High rates of multimodal therapy and positive margins underscore the importance of multidisciplinary care and highlight variable patterns of care across institutions. Further work is warranted to explore indicators of high-quality care and to optimize adjuvant therapy in the HPV era., Competing Interests: J.E.B. served on advisory boards for Galera Therapeutics and Castle Biosciences. The remaining authors declare no conflicts of interest., (Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.)

Background: Multimodality positron emission tomography/computed tomography (PET/CT) imaging combines the anatomical information of CT with the functional information of PET. In the diagnosis and treatment of many cancers, such as non-small cell lung cancer (NSCLC), PET/CT imaging allows more accurate delineation of tumor or involved lymph nodes for radiation planning., Purpose: In this paper, we propose a hybrid regional network method of automatically segmenting lung tumors from PET/CT images., Methods: The hybrid regional network architecture synthesizes the functional and anatomical information from the two image modalities, whereas the mask regional convolutional neural network (R-CNN) and scoring fine-tune the regional location and quality of the output segmentation. This model consists of five major subnetworks, that is, a dual feature representation network (DFRN), a regional proposal network (RPN), a specific tumor-wise R-CNN, a mask-Net, and a score head. Given a PET/CT image as inputs, the DFRN extracts feature maps from the PET and CT images. Then, the RPN and R-CNN work together to localize lung tumors and reduce the image size and feature map size by removing irrelevant regions. The mask-Net is used to segment tumor within a volume-of-interest (VOI) with a score head evaluating the segmentation performed by the mask-Net. Finally, the segmented tumor within the VOI was mapped back to the volumetric coordinate system based on the location information derived via the RPN and R-CNN. We trained, validated, and tested the proposed neural network using 100 PET/CT images of patients with NSCLC. A fivefold cross-validation study was performed. The segmentation was evaluated with two indicators: (1) multiple metrics, including the Dice similarity coefficient, Jacard, 95th percentile Hausdorff distance, mean surface distance (MSD), residual mean square distance, and center-of-mass distance; (2) Bland-Altman analysis and volumetric Pearson correlation analysis., Results: In fivefold cross-validation, this method achieved Dice and MSD of 0.84 ± 0.15 and 1.38 ± 2.2 mm, respectively. A new PET/CT can be segmented in 1 s by this model. External validation on The Cancer Imaging Archive dataset (63 PET/CT images) indicates that the proposed model has superior performance compared to other methods., Conclusion: The proposed method shows great promise to automatically delineate NSCLC tumors on PET/CT images, thereby allowing for a more streamlined clinical workflow that is faster and reduces physician effort., (© 2022 American Association of Physicists in Medicine.)

Background: The optimal management of patients with stage IV soft tissue sarcoma of the extremity (STSE) with distant metastases at diagnosis is unclear due to limited evidence and heterogeneity of current practice patterns. National guidelines have recommended surgical management of the primary site (SP) with or without radiotherapy (R), chemotherapy (C), and metastasectomy (M)., Methods: In the National Cancer Database (NCDB), patients with initially metastatic STSE who received definitive SP from 2004 to 2014 were identified. Survival distributions were estimated and compared using the Kaplan-Meier method and log-rank tests, and covariates were compared using Chi-square tests or analysis of variance (ANOVA). Propensity score analysis using inverse probability of treatment weighting was used., Results: Overall, 1124 patients were included, with a median age of 55 years (range 18-90). Utilization of SP+M increased over time from 18.8% in 2004-2006, to 33.3% in 2007-2009, to 47.9% in 2010-2014 (p = 0.024). The addition of M to SP was associated with superior 5-year overall survival (OS) at 30.8% (SP+M+/-C+/-R) compared with 18.2% for those treated with non-surgical adjuvant therapies (SP+/-C+/-R) and 12.6% for SP alone (p < 0.0001). Positive surgical margins were noted in 24.1% of patients and was associated with worse OS (hazard ratio 1.44, p < 0.001) on multivariable analysis., Conclusions: This is the first known study utilizing a large database to explore practice patterns and outcomes for patients with metastatic STSE receiving definitive SP. Utilization of metastasectomy increased in the study period and was associated with longer survival compared with SP alone. These hypothesis-generating data warrant additional study., (© 2021. Society of Surgical Oncology.)

Purpose: The delineation of organs at risk (OARs) is fundamental to cone-beam CT (CBCT)-based adaptive radiotherapy treatment planning, but is time consuming, labor intensive, and subject to interoperator variability. We investigated a deep learning-based rapid multiorgan delineation method for use in CBCT-guided adaptive pancreatic radiotherapy., Methods: To improve the accuracy of OAR delineation, two innovative solutions have been proposed in this study. First, instead of directly segmenting organs on CBCT images, a pretrained cycle-consistent generative adversarial network (cycleGAN) was applied to generating synthetic CT images given CBCT images. Second, an advanced deep learning model called mask-scoring regional convolutional neural network (MS R-CNN) was applied on those synthetic CT to detect the positions and shapes of multiple organs simultaneously for final segmentation. The OAR contours delineated by the proposed method were validated and compared with expert-drawn contours for geometric agreement using the Dice similarity coefficient (DSC), 95th percentile Hausdorff distance (HD95), mean surface distance (MSD), and residual mean square distance (RMS)., Results: Across eight abdominal OARs including duodenum, large bowel, small bowel, left and right kidneys, liver, spinal cord, and stomach, the geometric comparisons between automated and expert contours are as follows: 0.92 (0.89-0.97) mean DSC, 2.90 mm (1.63-4.19 mm) mean HD95, 0.89 mm (0.61-1.36 mm) mean MSD, and 1.43 mm (0.90-2.10 mm) mean RMS. Compared to the competing methods, our proposed method had significant improvements (p < 0.05) in all the metrics for all the eight organs. Once the model was trained, the contours of eight OARs can be obtained on the order of seconds., Conclusions: We demonstrated the feasibility of a synthetic CT-aided deep learning framework for automated delineation of multiple OARs on CBCT. The proposed method could be implemented in the setting of pancreatic adaptive radiotherapy to rapidly contour OARs with high accuracy., (© 2021 American Association of Physicists in Medicine.)

A 13-year-old healthy girl presented with dizziness and palpitations, found to have a left atrial mass. An 8-cm tumor was removed en bloc. Pathology confirmed grade 3 leiomyosarcoma with multifocal positive margins. She received adjuvant ifosfamide and doxorubicin, followed by concurrent proton radiotherapy and ifosfamide. Radiotherapy included 66 Gy (RBE) in 33 fractions to the operative bed. Prospectively graded toxicities included Grade 2 esophagitis and Grade 1 anorexia, dermatitis, and fatigue. She completed six cycles of ifosfamide. Two years post operation, she had no evidence of disease, intermittent palpitations with normal cardiac function, and no other cardiopulmonary or esophageal symptoms., (© 2021 Wiley Periodicals LLC.)

The COVID-19 pandemic altered the workplace for medical education. As restrictions ease, the opportunities provided by virtual rotations remain. Radiation oncology rotations based on virtual participation with patients (consultations, follow-ups, and brachytherapy), contouring and reviewing external beam plans, didactics, and unstructured office hours have been well received at multiple institutions. Virtual rotations decrease barriers to access including lack of a radiation oncology department at one's home institute and the high cost of travel and housing. Furthermore, rotations can be adapted to preclinical students and those with prior radiation oncology rotation experience. However, the virtual format creates and exacerbates several challenges including technical difficulties with electronic medical record or treatment planning software, lack of the spontaneous interactions common to in-person rotations, and unexpected delays in the clinic. We recommend early scheduled time with information technology services to troubleshoot any potential issues, scheduled office hours with faculty and videoconferencing with nonphysician team members to mitigate omission of in-person introductions, and provision of complete contact information for all staff scheduled to meet with students to facilitate communication when unexpected clinic issues arise. Although we are all excited for quarantine restrictions to safely be lifted, we support the continued development of virtual away rotations as a flexible, more affordable option to increase exposure to the field., (Copyright © 2021 American Society for Radiation Oncology. Published by Elsevier Inc. All rights reserved.)

Feature dimensionality reduction plays an important role in radiomic studies with a large number of features. However, conventional radiomic approaches may suffer from noise, and feature dimensionality reduction techniques are not equipped to utilize latent supervision information of patient data under study, such as differences in patients, to learn discriminative low dimensional representations. To achieve robustness to noise and feature dimensionality reduction with improved discriminative power, we develop a robust collaborative clustering method to simultaneously cluster patients and radiomic features into distinct groups respectively under adaptive sparse regularization. Our method is built upon matrix tri-factorization enhanced by adaptive sparsity regularization for simultaneous feature dimensionality reduction and denoising. Particularly, latent grouping information of patients with distinct radiomic features is learned and utilized as supervision information to guide the feature dimensionality reduction, and noise in radiomic features is adaptively isolated in a Bayesian framework under a general assumption of Laplacian distributions of transform-domain coefficients. Experiments on synthetic data have demonstrated the effectiveness of the proposed approach in data clustering, and evaluation results on an FDG-PET/CT dataset of rectal cancer patients have demonstrated that the proposed method outperforms alternative methods in terms of both patient stratification and prediction of patient clinical outcomes.

Radiomic approaches have achieved promising performance in prediction of clinical outcomes of cancer patients. Particularly, feature dimensionality reduction plays an important role in radiomic studies. However, conventional feature dimensionality reduction techniques are not equipped to suppress data noise or utilize latent supervision information of patient data under study ( e.g. difference in patients) for learning discriminative low dimensional representations. To achieve feature dimensionality reduction with improved discriminative power and robustness to noisy radiomic features, we develop an adaptive sparsity regularization based collaborative clustering method to simultaneously cluster patients and radiomic features into distinct groups respectively. Our method is built on adaptive sparsity regularized matrix tri-factorization for simultaneous feature denoising and dimension reduction so that the noise is adaptively isolated from the features, and grouping information of patients with distinctive features provides latent supervision information to guide feature dimension reduction. The sparsity regularization is grounded on distribution modeling of transform-domain coefficients in a Bayesian framework. Experiments on synthetic data have demonstrated the effectiveness of the proposed approach in data clustering, and empirical results on an FDG-PET/CT dataset of rectal cancer patients have demonstrated that the proposed method outperforms alternative methods in terms of both patient stratification and prediction of patient clinical outcomes.

Most machine learning approaches in radiomics studies ignore the underlying difference of radiomic features computed from heterogeneous groups of patients, and intrinsic correlations of the features are not fully exploited yet. In order to better predict clinical outcomes of cancer patients, we adopt an unsupervised machine learning method to simultaneously stratify cancer patients into distinct risk groups based on their radiomic features and learn low-dimensional representations of the radiomic features for robust prediction of their clinical outcomes. Based on nonnegative matrix tri-factorization techniques, the proposed method applies collaborative clustering to radiomic features of cancer patients to obtain clusters of both the patients and their radiomic features so that patients with distinct imaging patterns are stratified into different risk groups and highly correlated radiomic features are grouped in the same radiomic feature clusters. Experiments on a FDG-PET/CT dataset of rectal cancer patients have demonstrated that the proposed method facilitates better stratification of patients with distinct survival patterns and learning of more effective low-dimensional feature representations that ultimately leads to accurate prediction of patient survival, outperforming conventional methods under comparison.

Recent radiomic studies have witnessed promising performance of deep learning techniques in learning radiomic features and fusing multimodal imaging data. Most existing deep learning based radiomic studies build predictive models in a setting of pattern classification, not appropriate for survival analysis studies where some data samples have incomplete observations. To improve existing survival analysis techniques whose performance is hinged on imaging features, we propose a deep learning method to build survival regression models by optimizing imaging features with deep convolutional neural networks (CNNs) in a proportional hazards model. To make the CNNs applicable to tumors with varied sizes, a spatial pyramid pooling strategy is adopted. Our method has been validated based on a simulated imaging dataset and a FDG-PET/CT dataset of rectal cancer patients treated for locally advanced rectal cancer. Compared with survival prediction models built upon hand-crafted radiomic features using Cox proportional hazards model and random survival forests, our method achieved competitive prediction performance.

Purpose: Convolutional neural networks (CNN) have greatly improved medical image segmentation. A robust model requires training data can represent the entire dataset. One of the differing characteristics comes from variability in patient positioning (prone or supine) for radiotherapy. In this study, we investigated the effect of position orientation on segmentation using CNN., Methods: Data of 100 patients (50 in supine and 50 in prone) with rectal cancer were collected for this study. We designed three sets of experiments for comparison: (a) segmentation using the model trained with data from the same orientation; (b) segmentation using the model trained with data from the opposite orientation; (c) segmentation using the model trained with data from both orientations. We performed fivefold cross-validation. The performance was evaluated on segmentation of the clinical target volume (CTV), bladder, and femurs with Dice similarity coefficient (DSC) and Hausdorff distance (HD)., Results: Compared with models trained on cases positioned in the same orientation, the models trained with cases positioned in the opposite orientation performed significantly worse (P < 0.05) on CTV and bladder segmentation, but had comparable accuracy for femurs (P > 0.05). The average DSC values were 0.74 vs 0.84, 0.85 vs 0.88, and 0.91 vs 0.91 for CTV, bladder, and femurs, respectively. The corresponding HD values (mm) were 16.6 vs 14.6, 8.4 vs 8.1, and 6.3 vs 6.3, respectively. The models trained with data from both orientations have comparable accuracy (P > 0.05), with average DSC of 0.84, 0.88, and 0.91 and HD of 14.4, 8.1, and 6.3, respectively., Conclusions: Orientation affects the accuracy for CTV and bladder, but has negligible effect on the femurs. The model trained from data combining both orientations performs as well as a model trained with data from the same orientation for all the organs. These observations can offer guidance on the choice of training data for accurate segmentation., (© 2018 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.)

Convolutional neural networks (CNNs) have become the state-of-the-art method for medical segmentation. However, repeated pooling and striding operations reduce the feature resolution, causing loss of detailed information. Additionally, tumors of different patients are of different sizes. Thus, small tumors may be ignored while big tumors may exceed the receptive fields of convolutions. The purpose of this study is to further improve the segmentation accuracy using a novel CNN (named CAC-SPP) with cascaded atrous convolution (CAC) and a spatial pyramid pooling (SPP) module. This work is the first attempt at applying SPP for segmentation in radiotherapy. We improved the network based on ResNet-101 yielding accuracy gains from a greatly increased depth. We added CAC to extract a high-resolution feature map while maintaining large receptive fields. We also adopted a parallel SPP module with different atrous rates to capture the multi-scale features. The performance was compared with the widely adopted U-Net and ResNet-101 with independent segmentation of rectal tumors for two image sets, separately: (1) 70 T2-weighted MR images and (2) 100 planning CT images. The results show that the proposed CAC-SPP outperformed the U-Net and ResNet-101 for both image sets. The Dice similarity coefficient values of CAC-SPP were 0.78  ±  0.08 and 0.85  ±  0.03, respectively, which were higher than those of U-Net (0.70  ±  0.11 and 0.82  ±  0.04) and ResNet-101 (0.76  ±  0.10 and 0.84  ±  0.03). The segmentation speed of CAC-SPP was comparable with ResNet-101, but about 36% faster than U-Net. In conclusion, the proposed CAC-SPP, which could extract high-resolution features with large receptive fields and capture multi-scale context yields, improves the accuracy of segmentation performance for rectal tumors.

Purpose: To pool data across multiple institutions internationally and report on the cumulative experience of brainstem stereotactic radiosurgery (SRS)., Methods and Materials: Data on patients with brainstem metastases treated with SRS were collected through the International Gamma Knife Research Foundation. Clinical, radiographic, and dosimetric characteristics were compared for factors prognostic for local control (LC) and overall survival (OS) using univariate and multivariate analyses., Results: Of 547 patients with 596 brainstem metastases treated with SRS, treatment of 7.4% of tumors resulted in severe SRS-induced toxicity (grade ≥3, increased odds with increasing tumor volume, margin dose, and whole-brain irradiation). Local control at 12 months after SRS was 81.8% and was improved with increasing margin dose and maximum dose. Overall survival at 12 months after SRS was 32.7% and impacted by age, gender, number of metastases, tumor histology, and performance score., Conclusions: Our study provides additional evidence that SRS has become an option for patients with brainstem metastases, with an excellent benefit-to-risk ratio in the hands of experienced clinicians. Prior whole-brain irradiation increases the risk of severe toxicity in brainstem metastasis patients undergoing SRS., (Copyright © 2016 Elsevier Inc. All rights reserved.)