A unified framework for simultaneous assessment of accuracy, between-, and within-reader variability of image segmentations.

Medical imaging is utilized in a wide range of clinical applications. To enable a detailed quantitative analysis, medical images must often be segmented to label (delineate) structures of interest; for example, a tumor. Frequently, manual segmentation is utilized in clinical practice (e.g., in radiation oncology) to define such structures of interest. However, it can be quite time consuming and subject to substantial between-, and within-reader variability. A more reproducible, less variable, and more time efficient segmentation approach is likely to improve medical treatment. This potential has spurred the development of segmentation algorithms which harness computational power. Segmentation algorithms' widespread use is limited due to difficulty in quantifying their performance relative to manual segmentation, which itself is subject to variation. This paper presents a statistical model which simultaneously estimates segmentation method accuracy, and between- and within-reader variability. The model is simultaneously fit for multiple segmentation methods within a unified Bayesian framework. The Bayesian model is compared to other methods used in literature via a simulation study, and application to head and neck cancer PET/CT data. The modeling framework is flexible and can be employed in numerous comparison applications. Several alternate applications are discussed in the paper.

Exploring the Parents' Attitudes and Perceptions About School Breakfast to Understand Why Participation Is Low in a Rural Midwest State.

OBJECTIVE: To explore parental attitudes and perceptions about the school breakfast program in a state with low school breakfast participation. DESIGN: A cross-sectional study design that used an online survey completed by parents supplemented with district data from a state department of education. The survey included quantitative and qualitative components. SETTING: A rural Midwestern state with low school breakfast participation. PARTICIPANTS: Parents and caregivers of children in grades 1-12 were recruited through schools to complete a survey (n = 7,209). MAIN OUTCOME MEASURES: Participation in a school breakfast program. ANALYSIS: A generalized estimating equation model was used to analyze the data and account for the possible correlation among students from the same school district. Open-end survey items were coded. RESULTS: Parents identified several structural and logistic barriers in response to open-ended survey items. Factors associated with breakfast participation include perceived benefits, stigma related to those for whom breakfast is intended, and the importance of breakfast. CONCLUSIONS AND IMPLICATIONS: Interventions should be designed to test whether changing parent perceptions and decreasing stigma will lead to increased breakfast participation. Policy, systems, and environment changes addressing the structural and logistic barriers also may have the potential to increase participation.

Estimating the Probability of Traditional Copying, Conditional on Answer-Copying Statistics.

Statistics for detecting copying on multiple-choice tests produce p values measuring the probability of a value at least as large as that observed, under the null hypothesis of no copying. The posterior probability of copying is arguably more relevant than the p value, but cannot be derived from Bayes' theorem unless the population probability of copying and probability distribution of the answer-copying statistic under copying are known. In this article, the authors develop an estimator for the posterior probability of copying that is based on estimable quantities and can be used with any answer-copying statistic. The performance of the estimator is evaluated via simulation, and the authors demonstrate how to apply the formula using actual data. Potential uses, generalizability to other types of cheating, and limitations of the approach are discussed.