Christina Gillmann

Fraunhofer Institute for Applied Information Technology | FIT · Data Science & Künstliche Intelligenz

The application of uncertainty-aware visualization techniques in Machine Learning (ML) predictions has proven to be invaluable in the realm of clinical data. This article delves into the prospect of transferring these lessons to sporting applications. By scrutinizing the insights derived from uncertainty-aware visualization in clinical data, our go...

The integration and management of heterogeneous data pose challenges across various applications, requiring scalable solutions to handle large volumes of data, maintain compatibility, and ensure security, privacy, and regulatory compliance. This position paper presents a federated data and service catalogue based on the Eclipse XFSC framework. It p...

Visual analytics (VA) is a paradigm for insight generation by using visual analysis techniques and automated reasoning by transforming data into hypotheses and visualization to extract new insights. The insights are fed back into the data to enhance it until the desired insight is found. Many applications use this principle to provide meaningful me...

Network visualization is one of the most widely used tools in digital humanities research. The idea of uncertain or “fuzzy” data is also a core notion in digital humanities research. Yet network visualizations in digital humanities do not always prominently represent uncertainty. In this article, we present a mathematical and logical model of uncer...

Interactive visualization empowers users to actively engage with data. This article introduces interactive visualization’s key features and its applications in data analysis, business, science, and journalism. It also highlights challenges, including scalability, complexity, and user engagement, and discusses how two applications address these issu...

Visualization approaches have been successfully applied to a variety of application fields. Continuously published novel visualization approaches reflect the need for and success of visualization approaches. However, when looking at visualization techniques that designers apply in real-world applications targeted at a larger user group (e.g., medic...

Visual Analytics (VA) is a paradigm for insight generation by using visual analysis techniques and automated reasoning by transforming data into hypotheses and visualization to extract new insights, feeding them back into the data. This enhances the data until the desired insight is found. Many applications use this principle to provide meaningful...

Visual Analytics (VA) is a paradigm for insight generation by using visual analysis techniques and automated reasoning by transforming data into hypotheses and visualization to extract new insights, feeding them back into the data. This enhances the data until the desired insight is found. Many applications use this principle to provide meaningful...

Visual analytics (VA) has become a standard tool to process and analyze data visually to generate novel insights. Unfortunately, each component can introduce uncertainty in the visual analytics process. These uncertainty events can originate from many effects and need to be differentiated. In this work, we propose a taxonomy of potential uncertaint...

Purpose: The interpretation of image data plays a critical role during acute brain stroke diagnosis, and promptly defining the requirement of a surgical intervention will drastically impact the patient's outcome. However, determining stroke lesions purely from images can be a daunting task. Many studies proposed automatic segmentation methods for...

Visualization researchers and visualization professionals seek appropriate abstractions of visualization requirements that permit considering visualization solutions independently from specific problems. Abstractions can help us design, analyze, organize, and evaluate the things we create. The literature has many task structures (taxonomies, typolo...

Perfusion CT is established to aid selection of patients with proximal intracranial vessel occlusion for thrombectomy in the extended time window. Selection is mostly based on simple thresholding of perfusion parameter maps, which, however, does not exploit the full information hidden in the high-dimensional perfusion data. We implemented a multipa...

We develop an interactive approach for analyzing multi-field tensor data from simulations in close collaboration with domain scientists. Our approach is based on extensive application analysis and built around a multi-field clustering addressing multiple user-defined quantities which were required by the domain scientists. Established techniques li...

Visualization researchers and visualization professionals seek appropriate abstractions of visualization requirements that permit considering visualization solutions independently from specific problems. Abstractions can help us design, analyze, organize, and evaluate the things we create. The literature has many task structures (taxonomies, typolo...

The interpretation of image data plays a critical role during acute brain stroke diagnosis, and promptly defining the requirement of a surgical intervention will drastically impact the patient's outcome. However, determining stroke lesions purely from images can be a daunting task. Many studies proposed automatic segmentation methods for brain stro...

In many applications, visual analytics (VA) has developed into a standard tool to ease data access and knowledge generation. VA describes a holistic cycle transforming data into hypothesis and visualization to generate insights that enhance the data. Unfortunately, many data sources used in the VA process are affected by uncertainty. In addition, t...

Brain lesions derived from stroke episodes can result in disabilities for a patient. Therefore, the segmentation of brain lesions is an important task in neurology. Recently this task has been mainly tackled by machine learning approaches that demonstrated to be very successful. One of these approaches is Graph Convolutional Networks (GCN), where t...

Machine learning has become a standard tool in computer vision. Nowadays, neural networks are one of the most prominent representatives in this class of algorithms that usually require training and evaluation to work as desired. There exist a variety of evaluation metrics to determine the quality of a trained neural network, which are usually thres...

The articles in this special section focus on visualization in manufacturing. While the overall idea of manufacturing might seem straightforward, the manufacturing processes themselves are extremely diverse, complex, and specialized depending on the area of application. Regardless of whether the raw materials are being transformed into simple objec...

Machine learning has become a standard tool in computer vision. Nowadays, neural networks are one of the most prominent representatives in this class of algorithms that usually require training and evaluation to work as desired. There exist a variety of evaluation metrics to determine the quality of a trained neural network, which are usually thres...

In many applications, Visual Analytics(VA) has developed into a standard tool to ease data access and knowledge generation. Unfortunately, many data sources, used in the VA process, are affected by uncertainty. In addition, the VA cycle itself can introduce uncertainty to the knowledge generation process. The classic VA cycle does not provide a mec...

Recently, machine learning is massively on the rise in medical applications providing the ability to predict diseases, plan treatment and monitor progress. Still, the use in a clinical context of this technology is rather rare, mostly due to the missing trust of clinicians. In this position paper, we aim to show how uncertainty is introduced in the...

The sigmoid activation is the standard output activation function in binary classification and segmentation with neural networks. Still, there exist a variety of other potential output activation functions, which may lead to improved results in medical image segmentation. In this work, we consider how the asymptotic behavior of different output act...

The medical domain has been an inspiring application area in visualization research for many years already, but many open challenges remain. The driving forces of medical visualization research have been strengthened by novel developments, for example, in deep learning, the advent of affordable VR technology, and the need to provide medical visuali...

A U-Net is a type of convolutional neural network that has been shown to output impressive results in medical imaging segmentation tasks. Still, neural networks in general form a black box that is hard to interpret, especially by noncomputer scientists. This work provides a visual system that allows users to examine U-Nets that were trained to pred...

Medical imaging (image acquisition, image transformation, and image visualization) is a standard tool for clinicians in order to make diagnoses, plan surgeries, or educate students. Each of these steps is affected by uncertainty, which can highly influence the decision‐making process of clinicians. Visualization can help in understanding and commun...

Due to the limitations of existing experimental methods for capturing stereochemical molecular data, there usually is an inherent level of uncertainty present in models describing the conformation of macromolecules. This uncertainty can originate from various sources and can have a significant effect on algorithms and decisions based upon such mode...

Due to the limitations of existing experimental methods for capturing stereochemical molecular data, there usually is an inherent level of uncertainty present in models describing the conformation of macromolecules. This uncertainty can originate from various sources and can have a significant effect on algorithms and decisions based upon such mode...

Medical imaging (image acquisition, image transformation, and image visualization) is a standard tool for clinicians in order to make diagnoses, plan surgeries, or educate students. Each of these steps is affected by uncertainty, which can highly influence the decision-making process of clinicians. Visualization can help in understanding and commun...

Eddy detection is a state of the art tool to examine transport behavior in oceans, as they form circular movements that are highly involved in transferring mass in an ocean. To achieve this, ocean simulations are run multiple times, and an eddy detection is performed in the final simulation results. Unfortunately, this process is affected by a vari...

Building floor plans are an important tool forarchitects to derive new designs or analyze given designs. Here, architects are interested in the analysis of existing designs. Unfortunately, building floor plans need to be analyzed by architects manually, which requires a lot of time. This paper builds on a close collaboration between computer scient...

Stroke lesions are a result of a sudden cerebrovas-cular disease that cause a lack of blood supply to the brain. Clinicians aim to localize and quantify brain lesions by utilizing multi-modal CT (Computed Tomography) imaging in order to provide a suitable treatment. In clinical daily routine, neurologists review one modality at a time and a correla...

A 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 e...

Reliable component design is one of structural mechanics' main objectives. Especially for lightweight constructions, hybrid parts made of a multi-material combination are used. The design process for these parts often becomes very challenging. The critical section of such hybrid parts is usually the interface layer that often builds the weakest zon...

Medical 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 de...

Exa-scale simulations can be hard to analyze because it is nearly impossible to store all computed time-steps and other parameters. The Cinema Database provides a storage-saving solution, that captures images of each simulation time-step from a variety of camera angles. Still, the resulting number of images can be overwhelming and it is hard to fin...

Digital methods are increasingly applied to store, structure and analyse vast amounts of musical data. In this context, visualization plays a crucial role, as it assists musicologists and non‐expert users in data analysis and in gaining new knowledge. This survey focuses on this unique link between musicology and visualization. We classify 129 rela...

Exa-scale simulations can be hard to analyze because it is nearly impossible to store all computed time-steps and other parameters. The Cinema Database provides a storage-saving solution, that captures images of each simulation time-step from a variety of camera angles. Still, the resulting number of images can be overwhelming and it is hard to fin...

Ramachandran Plots are an important tool for researchers in bio-chemistry to examine the stability of a molecule. In these plots,dihedral (torsion) angles of the protein’s backbone are visualized ona plane, where different areas are known to be stable configurations.Unfortunately, the underlying atom positions are affected by uncer-tainty, which is...

Image segmentation is an important subtask in biomedical research applications, such as estimating the position and shape of a tumor. Unfortunately, advanced image segmentation methods are not widely applied in research applications as they often miss features, such as uncertainty communication, and may lack an intuitive approach for the use of the...

Peripheral Artery Disease (PAD) is an often occurring problem caused by narrowed veins. With this type of disease, mostly the legs receive an insufficient supply of blood to sustain their functions. This can result in an amputation of extremities or strokes. In order to quantify the risks, doctors consult a classification table which is based on th...

Finding bottlenecks and eliminating them to increase the overall flow of a network often appears in real world applications, such as production planning, factory layout, flow related physical approaches, and even cyber security. In many cases, several edges can form a bottleneck (cascaded bottlenecks). This work presents a visual analytics methodol...

Figure 1: Uncertainty-aware pipeline used for an evaluation of the uncertainty principle. Using the original dataset (a), four different uncertainty measures (b) are being computed. The uncertainty measures and the original dataset are used to smooth the image with an uncertainty-aware gauss filter (c) to reduce noise. The smoothed image and the un...

Due to image reconstruction process of all image capturing methods, image data is inherently affected by uncertainty. This is caused by the underlying image reconstruction model, that is not capable to map all physical properties in its entirety. In order to be aware of these effects, image uncertainty needs to be quantified and propagated along th...

Cardiovascular diseases, mainly caused by lipids accumulating within the vessel wall creating plaque, are one of the leading causes of death in modern society. In advanced cases, surgery is required to avoid strokes or heart attacks. Therefore the aim of the presented approach is to assist in the entire surgery process, identify risks, discuss opti...

3D Thinning is an often required image processing task in order to perform shape analysis in various applications. For researchers in these domains, a fast, flexible and easy to access implementation is required. Open source solutions, as the Insights Segmentation and Registration Toolkit (ITK), are often used for image processing and visualization...

Although image processing becomes increasingly important in most applications such as medicine, image processing and visualization is usually not a part of the medical education and therefore not widely spread in clinical daily routine. Contrary to students from computer science, medical students are usually not familiar with computational models o...

The popularity of open source tools is constantly increasing, as they offer the possibility to quickly create and use visualizations of arbitrary data sources. As the positive effects of uncertainty communication to all kinds of visualizations were discussed over the past years in the academic world, this work examines the uncertainty-awareness of...

Figure 1: Intuitive error space exploration of medical image data embedded in the medical workflow. a) Iso-surface visualization of clustered error space embedded in the established slice-by-slice reviewing method utilized in clinical daily routine. b) User selections can be made to inspect interesting pixels. c) Error space of the user selected pi...

Visualizations are a powerful tool to solve various tasks in different applications. Although a huge variety of visualiza-tion techniques are constantly published, only a few of them end up being used in real world day-today operations. To identify the reasons for this observation, this work aims at summarizing the criteria, that promote a real wor...

Three-dimensional thinning is an important task in medical image processing when performing quantitative analysis on structures , such as bones and vessels. For researchers of this domain a fast, robust and easy to access implementation is required. The Insight Segmentation and Registration Toolkit (ITK) is often used in medical image processing an...

Keyhole surgeries become increasingly important in clinical daily routine as they help minimizing the damage of a patient’s healthy tissue. The planning of keyhole surgeries is based on medical imaging and an important factor that influences the surgeries’ success. Due to the image reconstruction process, medical image data contains uncertainty tha...

The wear behavior of cutting tools directly affects the quality of the machined part. The measurement and evaluation of wear is a time consuming and process and is subjective. Therefore, an image-based wear measure that can be computed automatically based on given image series of cutting tools and an objective way to review the resulting wear is pr...

3D Thinning is an often required image processing task in order to perform shape analysis in various applications. For researchers in these domains, a fast, flexible and easy to access implementation is required. Open source solutions, as the Insights Segmentation and Registration Toolkit (ITK), are often used for image processing and visualization...

EIT (Electrical Impedance Tomography) is a novel imaging method visualizing impedance changes in the thorax mainly influenced by breathing and heart beating. Unfortunately, this technique has a poor image resolution. To improve the quality of EIT images, computer scientists and medical researchers are working together on the image reconstruction pr...