Browsing by Author "Hagen, Hans"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item From Research Topic to Industrial Practice: An Experience Report(The Eurographics Association, 2020) Gospodnetic, Petra; Rauhut, Markus; Hagen, Hans; Gillmann, Christina and Krone, Michael and Reina, Guido and Wischgoll, ThomasContinuous technological progress requires both research and industry to work together. It is a necessity which cannot and should not be avoided. However, due to different interests of the two, it is often accompanied by various challenges. The inability to foresee and overcome the challenges can greatly impact the quality of collaboration results and thus chances of such results being used further by the industry. In this paper, we provide background on the topic and emphasize frequently discussed points. Focus of the work are industry-academia collaborations in applied computer science research such as visualization. For that purpose, a set of requirements is recognized and provided for both industry and research community. Further, we provide an overview of challenges recognized over years of experience from working in industry-academia collaborations. Together, the challenges indicate the gap between the industry and research which is inherently transferred further onto results of collaborative research. Finally, we discuss various possibilities for both industry and research to reduce the gap.Item Rockwell Adhesion Test - Approach to Standard Modernization(The Eurographics Association, 2020) Hatic, Damjan; Cheng, Xiaoyin; Weibel, Thomas; Rauhut, Markus; Hagen, Hans; Byška, Jan and Jänicke, StefanAutomatization of industry processes and analyses has been successfully applied in many different areas using varying methods. The basis for these industrial analyses is defined by global or country specific standards and often development of automated solutions works towards streamlining processes currently done heuristically. Lately, image classification, as one of the automatization development areas, has turned to machine learning in search for solutions. Though approaches that involve neural networks often result in high accuracy predictions, their complexity makes feature hard to understand and ultimately reproduce. To this end, we introduce a pipeline for the design, implementation and evaluation of a hand-crafted feature set used for the parameterization of two thin film coating adhesion classification standards. The method mimics the current expert classification process, and is developed in collaboration with domain experts. Implementation of an automated classification process was used for verification and integration testing.Item Towards Closing the Gap of Medical Visualization Research and Clinical Daily Routine(The Eurographics Association, 2020) Maack, Robin Georg Claus; Saur, Dorothee; Hagen, Hans; Scheuermann, Gerik; Gillman, Christina; Gillmann, Christina and Krone, Michael and Reina, Guido and Wischgoll, ThomasMedical visualization papers are constantly published throughout the last years, but many never make their way into clinical daily routine. In this manuscript we aim to examine the gap between visualization research and clinical daily routine and suggest a mechanism that can lead towards closing this gap. We first identify the actors involved in developing new medical visualization approaches and their different views in this process. Then we develop a software development process unifying all actors and their needs. In addition, we collect further barriers in the medical software development process.Item Uncertainty-aware Brain Lesion Visualization(The Eurographics Association, 2020) Gillmann, Christina; Saur, Dorothee; Wischgoll, Thomas; Hoffmann, Karl-Titus; Hagen, Hans; Maciejewski, Ross; Scheuermann, Gerik; Kozlíková, Barbora and Krone, Michael and Smit, Noeska and Nieselt, Kay and Raidou, Renata GeorgiaA brain lesion is an area of tissue that has been damaged through injury or disease. Its analysis is an essential task for medical researchers to understand diseases and find proper treatments. In this context, visualization approaches became an important tool to locate, quantify, and analyze brain lesions. Unfortunately, image uncertainty highly effects the accuracy of the visualization output. These effects are not covered well in existing approaches, leading to miss-interpretation or a lack of trust in the analysis result. In this work, we present an uncertainty-aware visualization pipeline especially designed for brain lesions. Our method is based on an uncertainty measure for image data that forms the input of an uncertainty-aware segmentation approach. Here, medical doctors can determine the lesion in the patient's brain and the result can be visualized by an uncertainty-aware geometry rendering. We applied our approach to two patient datasets to review the lesions. Our results indicate increased knowledge discovery in brain lesion analysis that provides a quantification of trust in the generated results.