Digital Commons Network^™

Uncertainty-Guided Test-Time Optimization For Personalizing Segmentation Models In Longitudinal Medical Imaging, Jaehee Chun, Austin Castelo, Mckell Woodland, Caleb O'Connor, Mais Al Taie, Aashish Gupta, Shanli Ding, Jeddy Bennett, Anirban Maitra, Matthew A Firpo, Kimberly Kirkwood, Eugene J Koay, Kristy K Brock

Faculty, Staff and Student Publications

Background: Accurate and consistent image segmentation across longitudinal scans is essential in many clinical applications, including surveillance, treatment monitoring, and adaptive interventions. While personalized model adaptation using patient-specific prior scans has shown promise, current approaches typically rely on fixed training durations and lack mechanisms to determine optimal stopping points on a per-patient basis, particularly in the absence of validation labels.

Purpose: We propose an uncertainty-guided test-time optimization (TTO) framework that dynamically adjusts the personalization duration for each patient using a validation-free stopping criterion based on predictive uncertainty.

Methods: Our framework personalizes a generalized segmentation model using patient-specific prior imaging and …

Ideational Behavior And Occupational Identity Achievement: A Study Of Emerging Adult College Students Preceding Entry Into The Fouth Industrial Revolution Workforce, Carrington M. Faulk, Michael F. Kosloski, Philip Reed

Marketing Faculty Publications

As emerging adults transition into the Fourth Industrial Revolution (4IR) workforce, it is essential to understand the factors that predict successful occupational identity achievement, as automation will impact human occupational identity crises. This descriptive cross-sectional study employed a correlational design to determine the degree to which ideational behavior predicts occupational identity achievement prior to entry into the 4IR workforce. Using a sample of 166 emerging adult college students from a Mid-Atlantic, diverse, four-year university, data were collected using Runco's Ideational Behavior Scale (RIBS) and Melgosa's Occupational Identity Achievement subscale (OIA). Results showed that ideational behavior significantly predicted occupational identity achievement …

Advertising With Haart: Introducing Human-Ai Asymmetric Relationship Theory, Veronica L. Thomas, Heather Shoenberger, Andrés Gvirtz, Sean Sands, Lotte Willemsen

Marketing Faculty Publications

Generative artificial intelligence (GenAI)is rapidly reconfiguring advertising from message delivery and optimization to relationship-like exchanges between consumers and brands. While existing work has explained these interactions through social response accounts and interpersonal relationship theories, this lens risks overlooking a defining structural mismatch: AI agents convincingly enact relational characteristics but cannot experience relational benefits, costs, or commitment. Perceived mutuality can be high even when the underlying relational capacity for reciprocity is absent. We introduce human–AI asymmetric relationship theory (HAART), which conceptualizes AI-mediated relationships as relationally expressive yet structurally one-sided. HAART advances three tenets: (1) inherent AI agent characteristics limit relational reciprocity; …

Artificial Intelligence And Consumer Well-Being: A Cross Domain Systemic Review, Setar Lytle, Mahesh Gopinath

Marketing Faculty Publications

Artificial intelligence (AI) is increasingly embedded in everyday consumption, yet evidence on its longer-term implications for consumer eudaimonic well-being remains dispersed across disciplines and application contexts. This review integrates that literature to clarify the domains, theoretical explanations, and conditions through which AI shapes consumer well-being. Following PRISMA and SPAR-4-SLR procedures, we reviewed research published from January 2010 to January 2026. From 6058 records, 480 studies across psychology, business, and human-technology interaction met the inclusion criteria. The evidence is organised through psychological, social, and technological perspectives and identifies six interconnected domains: mental health, cognitive development, physical health, personal growth, autonomy and …

Grading Melanocytic Dysplasia: Updated Histopathologic Criteria, Christopher R Shea, Victor G Prieto, Catherine M Shachaf, Scott R Florell

Faculty, Staff and Student Publications

Dr. Martin C. Mihm, Jr.'s innovative work on the dysplastic nevus achieved a milestone in his chapter in the World Health Organisation Classification of Skin Tumours (WHO-C). WHO-C presents a dichotomous classification (high-grade versus low-grade dysplastic nevi) and a quantitative metric to assess melanocytic nuclear enlargement. The Duke classification is a related approach that provides mostly quantitative histopathologic criteria for dysplastic nevi and gives due weight to architectural features as well as cytology. This paper proposes and illustrates updated criteria for scoring and grading melanocytic dysplasia, incorporating some of the definitions and categories of WHO-C, while refining the quantitative and …

Exploring Mathematics Texts In A Further Education College, Rajdulari Pettitt

School of Law, Humanities and Social Sciences Theses

Learning mathematics is a challenge for many learners in Further Education. It is also a requirement since Government policy stipulates that Further Education (FE) learners in England, who have achieved a General Certificate of Secondary Education (GCSE) Mathematics grade 3 or lower, are required to continue studying this subject alongside their vocational courses. As a core subject, mathematics includes numbers, shapes, patterns and statistics with progression generally from concrete to abstract form; mathematics texts include specific vocabulary such as probability trees and procedures such as calculations using decimals. Engagement with mathematics has been shown to be related to motivation, confidence …

‘The Limits Of The Landscape: A Critical Examination Of Outdoor Learning, Self-Regulation, And Semh Within Neoliberal Schooling’, Nicola Clayton

School of Law, Humanities and Social Sciences Theses

This doctoral thesis critically examines a specialised outdoor learning intervention for primary pupils with significant Social, Emotional, and Mental Health (SEMH) needs who are at risk of exclusion. It assesses the intervention’s implementation and its efficacy in supporting these pupils' capacity for self-regulation and stress management.The study is situated amidst escalating global child mental health concerns and recent English educational policy shifts that mandate schools to actively foster pupil well-being. Exploring outdoor education as a widely cited approach for promoting positive mental health, this research engages with established social theories, particularly those of Bernstein and Bourdieu, to critique the wider …

Navigating The Digital Shift In Mozambique: Teacher Agency And Digital Learning In Schools, Clive Ruraca

School of Law, Humanities and Social Sciences Theses

The educational technology industry frequently promotes the idea of a significant paradigm shift, proposing that technology can supplant traditional, transmission-based pedagogies such as ‘tell and practice’ approaches. In theory, this perspective positions digital tools as catalysts for systemic educational reform, capable of replacing rote learning with dynamic, technology-supported models (Voogt et al., 2013; Wang et al., 2024; Casilli & Posada, 2019). Employing an interpretative, empirical methodology, involving questionnaires and interviews with secondary school teachers. Data from this study are used to explore teachers’ experiences with digital learning tools through the lens of Activity Theory. This study examines the digital shift …