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.     

Impact of stereotactic body radiation therapy on geriatric assessment and management for older patients with head and neck cancer using G8

PurposeManagement of head and neck cancers (HNC) in older adults is a common but challenging clinical scenario. We assess the impact of Stereotactic Body Radiation Therapy (SBRT) on survival utilizing the Geriatric-8 (G8) questionnaire.Materials and methods171 HNC patients, deemed medically unfit for definitive treatment, were treated with SBRT ± systemic therapy. G8 questionnaires were collected at baseline, at 4–6 weeks, and at 2–3 months post-treatment. Patients were stratified according to their baseline G8 score: <11 as ‘vulnerable’, 11–14 as ‘intermediate’, and >14 as ‘fit’. Overall survival (OS) was assessed through univariate Kaplan Meier analysis. Repeated measures ANOVA was used to determine if baseline characteristics affected G8 score changes.ResultsMedian follow-up was seventeen months. 60% of patients presented with recurrent HNC, 30% with untreated HNC primaries, and 10% with metastatic non-HNC primaries. Median age was 75 years. Median Charlson Comorbidity Index score was 2. 51% of patients were ‘vulnerable’, 37% were ‘intermediate’, and 12% were ‘fit' at baseline, with median survival of 13.2, 24.3, and 41.0 months, respectively (p = .004). Patients who saw a decrease in their follow-up G8 score (n = 69) had significantly lower survival than patients who had stable or increased follow-up G8 scores (n = 102), with median survival of 8.6 vs 36.0 months (p < .001).ConclusionThe G8 questionnaire may be a useful tool in upfront treatment decision-making to predict prognosis and prevent older patients from receiving inappropriate anti-cancer treatment. Decline in follow-up G8 scores may also predict worse survival and aid in goals of care following treatment.     

Bi-allelic pathogenic variations in DNAJB11 cause Ivemark II syndrome,a renal-hepatic-pancreatic dysplasia

1. Download : Download high-res image (267KB)
2. Download : Download full-size image

     

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