Refine
Year of publication
- 2020 (25) (remove)
Document Type
- conference proceeding (presentation, abstract) (25) (remove)
Is part of the Bibliography
- no (25)
Keywords
- Altersgerechte Assistenzsysteme (1)
- Ambulanter Hilfs- und Pflegedienst (1)
- Antennengruppe (1)
- Applied Learning (1)
- Artificial Intelligence (1)
- Assistenzsystem (1)
- Barrett's Carcinoma (1)
- Diagnose (1)
- Digitale Technik (1)
- Digitalisierung (1)
Institute
- Fakultät Informatik und Mathematik (9)
- Fakultät Angewandte Sozial- und Gesundheitswissenschaften (8)
- Fakultät Maschinenbau (5)
- Fakultät Elektro- und Informationstechnik (3)
- Labor Empirische Sozialforschung (3)
- Regensburg Center of Health Sciences and Technology - RCHST (3)
- Combustion Engines and Emissions Control Laboratory (CEEC) (2)
- Institut für Sozialforschung und Technikfolgenabschätzung (IST) (2)
- Labor Biomechanik (LBM) (2)
- Labor Logopädie (LP) (2)
Begutachtungsstatus
- peer-reviewed (7)
Eye tracking is a powerful technique that helps reveal how people process visual information. This paper discusses a novel metric for indicating expertise in visual information processing. Named the Gaze Relational Index (GRI), this metric is defined as the ratio of mean fixation duration to fixation count. Data from two eye-tracking studies of professional vision and visual expertise in using 3D dynamic medical visualizations are presented as cases to illustrate the suitability and additional benefits of the GRI. Calculated values of the GRI were higher for novices than for experts, and higher in non-representative, semi-familiar / unfamiliar task conditions than in domain-representative familiar tasks. These differences in GRI suggest that, compared to novices, experts engaged in more knowledge-driven, top-down processing that was characterized by quick, exploratory visual search. We discuss future research aiming to replicate the GRI in professional domains with complex visual stimuli and to identify the moderating role of cognitive ability on GRI estimates.
Introduction
We present a clinical case showing the real-time detection, characterization and delineation of an early Barrett’s cancer using AI.
Patients and methods
A 70-year old patient with a long-segment Barrett’s esophagus (C5M7) was assessed with an AI algorithm.
Results
The AI system detected a 10 mm focal lesion and AI characterization predicted cancer with a probability of >90%. After ESD resection, histopathology showed mucosal adenocarcinoma (T1a (m), R0) confirming AI diagnosis.
Conclusion
We demonstrate the real-time AI detection, characterization and delineation of a small and early mucosal Barrett’s cancer.