Fakultät Informatik und Mathematik
Refine
Year of publication
- 2020 (6) (remove)
Document Type
- conference proceeding (presentation, abstract) (6) (remove)
Language
- English (6)
Is part of the Bibliography
- no (6)
Keywords
- Artificial Intelligence (1)
- Barrett's Carcinoma (1)
- Diagnose (1)
- Künstliche Intelligenz (1)
- Speiseröhrenkrebs (1)
- human-robot interaction (1)
- spoken language processing (1)
- virtual agents (1)
Institute
Begutachtungsstatus
- peer-reviewed (6) (remove)
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.
This paper summarizes six presentations in a session of the track “Use of Simulation for Manufacturing Applications”. The research work deals with the following key issues of this track: Modelling of process problems in manufacturing; Solutions of planning problems in manufacturing; Simulation of processes in manufacturing. This publication shows that the contributions in this track address research questions that are of high importance for industrial practice as well as current research directions such as stochastic optimization or the efficient search of large solution spaces.
In industrial practice, a travelling crane on the ceiling of a factory hall transports products in process from one station to the next one in a production line. Due to space restrictions, there is no buffer between the stations. The production line at Fiedler Andritz, Regensburg in Germany, can be seen as an example of such a problem class. Such restrictions reduce the set of feasible schedules even more than the no-buffer restrictions discussed in the literature in the case of limited storage. Since this scheduling problem is integrated in the usual hierarchical planning, the tardiness is minimised. Due to the high number of jobs as well as the goal of a simple algorithm, scheduling is always done by priority rules at the company site. The standard approach of using the net processing time causes poor results. A simulation of the processing time is suggested. In addition, several very relevant priority rules from the literature are modified by this simulated processing and significantly better results are obtained. Keywords-Simulation of processing time; scheduling, flowshop; no-buffer (blocking); no-wait; priority rules; real world application; filter production