Purpose Soft tissue sarcomas (STS) represent a heterogeneous group of diseases, and selection of individualized treatments remains a challenge. The goal of this study was to determine whether radiomic features extracted from magnetic resonance (MR) images are independently associated with overall survival (OS) in STS. Methods and Materials This study analyzed 2 independent cohorts of adult patients with stage II-III STS treated at center 1 (N = 165) and center 2 (N = 61). Thirty radiomic features were extracted from pretreatment T1-weighted contrast-enhanced MR images. Prognostic models for OS were derived on the center 1 cohort and validated on the center 2 cohort. Clinical-only (C), radiomics-only (R), and clinical and radiomics (C+R) penalized Cox models were constructed. Model performance was assessed using Harrell's concordance index. Results In the R model, tumor volume (hazard ratio [HR], 1.5) and 4 texture features (HR, 1.1-1.5) were selected. In the C+R model, both age (HR, 1.4) and grade (HR, 1.7) were selected along with 5 radiomic features. The adjusted c-indices of the 3 models ranged from 0.68 (C) to 0.74 (C+R) in the derivation cohort and 0.68 (R) to 0.78 (C+R) in the validation cohort. The radiomic features were independently associated with OS in the validation cohort after accounting for age and grade (HR, 2.4; P = .009). Conclusions This study found that radiomic features extracted from MR images are independently associated with OS when accounting for age and tumor grade. The overall predictive performance of 3-year OS using a model based on clinical and radiomic features was replicated in an independent cohort. Optimal models using clinical and radiomic features could improve personalized selection of therapy in patients with STS.
Machine learning for image segmentation could provide expedited clinic workflow and better standardization of contour delineation. We evaluated a new model using deep decision forests of image features in order to contour pelvic anatomy on treatment planning CTs. 193 CT scans from one UK and two US institutions for patients undergoing radiotherapy treatment for prostate cancer from 2012–2016 were anonymized. A decision forest autosegmentation model was trained on a random selection of 94 images from Institution 1 and tested on 99 scans from Institution 1, 2, and 3. The accuracy of model contours was measured with the Dice similarity coefficient (DSC) and the median slice-wise Hausdorff distance (MSHD) using clinical contours as the ground truth reference. Two comparison studies were performed. The accuracy of the model was compared to four commercial software packages on twenty randomly-selected images. Additionally, inter-observer variability (IOV) of contours between three radiation oncology experts and the original contours was evaluated on ten randomly-selected images. The highest median values of DSC across all institutions were 0.94–0.97 for bladder (with interquartile range, or IQR, of 0.92–0.98) and 0.96–0.97 (IQR 0.94–0.97) for femurs. Good agreement was seen for prostate, with median DSC 0.75–0.76 (IQR 0.67–0.82), and rectum, with median DSC 0.71–0.82 (IQR 0.63–0.87). The lowest median scores were 0.49–0.70 for seminal vesicles (IQR 0.31–0.79). For the commercial software comparison, model-based segmentation produced higher DSC than atlas-based segmentation, with decision forests producing highest DSC for all organs of interest. For the interobserver study, variability in DSC between observers was similar to the agreement between the model and ground truth. Deep decision forests of radiomic features can generate contours of pelvic anatomy with reasonable agreement with physician contours. This method could be useful for automated treatment planning, and autosegmentation may improve efficiency and increase standardization in the clinic.
Objectives Throughout the United States numerous models of local programs, including student-run clinics, exist to address the issue of access to care. The role of these clinics in serving the local community and contributing to medical education has been documented only in limited detail, however. The purpose of this article is to describe the clinic models, patient demographics, and services provided by four student-run clinics in New Orleans. Methods This is a retrospective, multisite chart review study of adult patients examined at student-run clinics between January 1, 2010 and July 31, 2011. Results During a 19-month period, 859 patients collectively were seen at the clinics, for a total of 1455 visits. The most common reasons for seeking care were medication refills (21.6%) and musculoskeletal pain (12.0%). Counseling and health education were provided primarily for smoking cessation (9.0%), diabetes management (7.1%), and hypertension management (5.8%). Nearly one-fifth of patients were given a referral to primary care services. In the 2010–2011 academic year, 87.6% of preclinical medical students volunteered at ≥1 of these clinics and spent 4508 hours during 1478 shifts. Conclusions This article highlights the role of student-run clinics in the community, the safety-net healthcare system, and medical education. Future directions include the establishment of a new clinic, fundraising, and prospective studies to further assess the impact of student-run clinics.
PurposeStudies have shown that radiation dose to the heart may be associated with worse outcomes in patients receiving chemoradiation for lung cancer. As esophageal cancer radiation treatment can result in relatively high cardiac doses, we evaluated a single-institution database of patients treated for esophageal cancer for heart dose and outcomes.MethodsWe retrospectively reviewed 59 patients with stage IIA-IIIB esophageal cancer treated with neoadjuvant chemoradiation to 50.4 Gy followed by esophagectomy from 2007-2015. Patient demographics and outcome data, including pathological response, local recurrence, distant metastases, and overall survival, were obtained. Mean heart dose (MHD), heart V5, V40, and V50, were calculated. Differences in patient characteristics between the three radiation therapy modalities: three-dimensional (3D) conformal radiotherapy (3D-CRT), intensity modulated radiotherapy (IMRT), and proton beam radiation therapy (PBT) were tested using non-parametric Kruskal-Wallis (K-W) analysis of variance (ANOVA). Patient characteristics and heart dosimetric parameters were screened by univariate Cox regression for an association to overall survival, and univariate predictors (p < 0.05) were then selected as inputs into a multivariate Cox regression model using stepwise backward elimination. Kaplan-Meier risk-stratified survival curves were plotted for the best univariate or multivariate Cox model variables. An exploratory subgroup univariate Cox regression was conducted in each of the treatment modalities (proton, IMRT, 3D-CRT).ResultsThe median follow-up was 20 months. The median overall survival was 73 months. Eleven patients (20%) experienced a complete pathologic response (pCR). Only two patients (4%) experienced a local recurrence. On univariate analysis, predictors of survival were age, prior radiation, pathologic response in involved lymph nodes, and tumor length post-treatment. On a multivariate analysis, only pathologic nodal response (yN) remained significant (p = 0.007). There was no relationship between any heart dosimetric variables analyzed and any clinical outcomes.ConclusionsIn this retrospective review, radiation dose to the heart was not associated with inferior treatment outcomes in patients receiving trimodality therapy for esophageal cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.