Clinical Evaluation of Deep Learning and Atlas-Based Auto-Contouring of Bladder and Rectum for Prostate Radiation Therapy

PurposeAuto-contouring may reduce workload, interobserver variation, and time associated with manual contouring of organs at risk. Manual contouring remains the standard due in part to uncertainty around the time and workload savings after accounting for the review and editing of auto-contours. This preliminary study compares a standard manual contouring workflow with 2 auto-contouring workflows (atlas and deep learning) for contouring the bladder and rectum in patients with prostate cancer.Methods and MaterialsThree contouring workflows were defined based on the initial contour-generation method including manual (MAN), atlas-based auto-contour (ATLAS), and deep-learning auto-contour (DEEP). For each workflow, initial contour generation was retrospectively performed on 15 patients with prostate cancer. Then, radiation oncologists (ROs) edited each contour while blinded to the manner in which the initial contour was generated. Workflows were compared by time (both in initial contour generation and in RO editing), contour similarity, and dosimetric evaluation.ResultsMean durations for initial contour generation were 10.9 min, 1.4 min, and 1.2 min for MAN, DEEP, and ATLAS, respectively. Initial DEEP contours were more geometrically similar to initial MAN contours. Mean durations of the RO editing steps for MAN, DEEP, and ATLAS contours were 4.1 min, 4.7 min, and 10.2 min, respectively. The geometric extent of RO edits was consistently larger for ATLAS contours compared with MAN and DEEP. No differences in clinically relevant dose-volume metrics were observed between workflows.ConclusionAuto-contouring software affords time savings for initial contour generation; however, it is important to also quantify workload changes at the RO editing step. Using deep-learning auto-contouring for bladder and rectum contour generation reduced contouring time without negatively affecting RO editing times, contour geometry, or clinically relevant dose–volume metrics. This work contributes to growing evidence that deep-learning methods are a clinically viable solution for organ-at-risk contouring in radiation therapy.     

Association of Multiple Plasma Biomarker Concentrations with Progression of Prevalent Diabetic Kidney Disease: Findings from the Chronic Renal Insufficiency Cohort (CRIC) Study

Open in a separate window     

American Cancer Society nutrition and physical activity guideline for cancer survivors

The overall 5-year relative survival rate for all cancers combined is now 68%, and there are over 16.9 million survivors in the United States. Evidence from laboratory and observational studies suggests that factors such as diet, physical activity, and obesity may affect risk for recurrence and overall survival after a cancer diagnosis. The purpose of this American Cancer Society guideline is to provide evidence-based, cancer-specific recommendations for anthropometric parameters, physical activity, diet, and alcohol intake for reducing recurrence and cancer-specific and overall mortality. The audiences for this guideline are health care providers caring for cancer survivors as well as cancer survivors and their families. The guideline is intended to serve as a resource for informing American Cancer Society programs, health policy, and the media. Sources of evidence that form the basis of this guideline are systematic literature reviews, meta-analyses, pooled analyses of cohort studies, and large randomized clinical trials published since 2012. Recommendations for nutrition and physical activity during cancer treatment, informed by current practice, large cancer care organizations, and reviews of other expert bodies, are also presented. To provide additional context for the guidelines, the authors also include information on the relationship between health-related behaviors and comorbidities, long-term sequelae and patient-reported outcomes, and health disparities, with attention to enabling survivors' ability to adhere to recommendations. Approaches to meet survivors' needs are addressed as well as clinical care coordination and resources for nutrition and physical activity counseling after a cancer diagnosis.     

The importance of how research participants think they are perceived: results from an electronic monitoring study of antiretroviral therapy in Uganda

Novel monitoring technologies in HIV research, such as electronic adherence monitors (EAMs), have changed the nature of researcher-participant interactions. Yet little is known about how EAMs and the resulting interaction between researchers and participants affect research participation and the data gathered. We interviewed participants and research assistants (RAs) in an observational cohort study involving EAMs for HIV antiretroviral therapy (ART) in Uganda. We qualitatively explored interviewees’ views about ethical issues surrounding EAMs and assessed data with conventional and directed content analysis. Participants valued their relationships with RAs and were preoccupied with RAs’ perceptions of them. Participants were pleased when the EAM revealed regular adherence, and annoyed when it revealed non-adherence that contradicted self-reported pill-taking behavior. For many, the desire to maintain a good impression incentivized adherence. But some sought to creatively conceal non-adherence, or refused to use the EAM to avoid revealing non-adherence to RAs. These findings show that participants’ perceptions of the study staff's perceptions of them affected the experience of being monitored, study participation, and ultimately the data gathered in the study. Investigators in monitoring-based research should be aware that social interactions between participants and study staff could affect both the practical and ethical conduct of that research.