Steffen Oeltze-Jafra

Otto-von-Guericke-Universität Magdeburg | OvGU · Clinic for Neurology

Expert interpretation of anatomical images of the human brain is the central part of neuro-radiology. Several machine learning-based techniques have been proposed to assist in the analysis process. However, the ML models typically need to be trained to perform a specific task, e.g., brain tumour segmentation or classification. Not only do the corre...

Motion artefacts in magnetic resonance images can critically affect diagnosis and the quan-tification of image degradation due to their presence is required. Usually, image quality assessment is carried out by experts such as radiographers, radiologists and researchers. However, subjective evaluation requires time and is strongly dependent on the e...

Motion artefacts in magnetic resonance brain images are a crucial issue. The assessment of MR image quality is fundamental before proceeding with the clinical diagnosis. If the motion artefacts alter a correct delineation of structure and substructures of the brain, lesions, tumours and so on, the patients need to be re-scanned. Otherwise, neuro-ra...

Many deep learning-based techniques have been proposed in recent years to reconstruct undersampled MRI – showing their potential for shortening the acquisition time. Before using them in actual practice, they are usually evaluated by comparing their results against the available ground-truth – which is not available during real applications. This r...

Deep learning methods are typically trained in a supervised with annotated data for analysing medical images with the motivation of detecting pathologies. In the absence of manually annotated training data, unsupervised anomaly detection can be one of the possible solutions. This work proposes StRegA, an unsupervised anomaly detection pipeline base...

The lack of reproducibility of research results is a serious problem – known as “the reproducibility crisis”. The German National Research Data Infrastructure (NFDI) initiative implemented by the German Research Foundation (DFG) aims to help overcoming this crisis by developing sustainable solutions for research data management (RDM). NFDI comprise...

The development and validation of Clinical Decision Support Models (CDSM) based on Bayesian networks (BN) is commonly done in a collaborative work between medical researchers providing the domain expertise and computer scientists developing the decision support model. Although modern tools provide facilities for data-driven model generation, domain...

Expert interpretation of anatomical images of the human brain is the central part of neuro-radiology. Several machine learning-based techniques have been proposed to assist in the analysis process. However, the ML models typically need to be trained to perform a specific task, e.g., brain tumour segmentation or classification. Not only do the corre...

Background: The Locus Coeruleus (LC) may play an important role in the pathogenesis of Alzheimer's disease (AD). Neuromelanin-sensitive Magnetic Resonance Imaging (MRI) permits the visualization of the LC in vivo. Previously, we proposed an automatic, deep learning-based approach to segmenting the LC in a cohort of 82 healthy young and older adult...

Purpose Development and performance measurement of a fully automated pipeline that localizes and segments the locus coeruleus in so-called neuromelanin-sensitive magnetic resonance imaging data for the derivation of quantitative biomarkers of neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease. Methods We propose a pipel...

Purpose Quantitative assessment of prospective motion correction (PMC) capability at 7T MRI for compliant healthy subjects to improve high-resolution images in the absence of intentional motion. Methods Twenty-one healthy subjects were imaged at 7 T. They were asked not to move, to consider only unintentional motion. An in-bore optical tracking sy...

Here, we present an extension to our previously published structural ultrahigh resolution T 1 -weighted magnetic resonance imaging (MRI) dataset with an isotropic resolution of 250 µm, consisting of multiple additional ultrahigh resolution contrasts. Included are up to 150 µm Time-of-Flight angiography, an updated 250 µm structural T 1 -weighted re...

Here, we present an extension to our previously published structural ultrahigh resolution T1- weighted magnetic resonance imaging (MRI) dataset with an isotropic resolution of 250 µm, consisting of multiple additional ultrahigh resolution contrasts. Included are up to 150 µm Time-of-Flight angiography, an updated 250 µm structural T1-weighted recon...

Here, we present an extension to our previously published structural ultrahigh resolution T1- weighted magnetic resonance imaging (MRI) dataset with an isotropic resolution of 250 µm, consisting of multiple additional ultrahigh resolution contrasts. Included are up to 150 µm Time-of-Flight angiography, an updated 250 µm structural T1-weighted recon...

While commonly used approach for disease localization, we propose an approach to detect anomalies by differentiating them from reliable models of anatomies without pathologies. The method is based on a Variational Auto Encoder to learn the anomaly free distribution of the anatomy and a novel image subtraction approach to obtain pixel-precise segmen...

One of the common problems in MRI is the slow acquisition speed, which can be solved using undersampling. But this might result in image artefacts. Several deep learning based techniques have been proposed to mitigate this problem. Most of these methods work only in the image space. Fine anatomical structures obscured by artefacts in the image can...

Diffusion-weighted magnetic resonance imaging (DW-MRI) can be used to characterise the microstructure of the nervous tissue, e.g. to delineate brain white matter connections in a non-invasive manner via fibre tracking. Magnetic Resonance Imaging (MRI) in high spatial resolution would play an important role in visualising such fibre tracts in a supe...

The identification of interesting patterns and relationships is essential to exploratory data analysis. This becomes increasingly difficult in high dimensional datasets. While dimensionality reduction techniques can be utilized to reduce the analysis space, these may unintentionally bury key dimensions within a larger grouping and obfuscate meaning...

The Dual Analysis framework is a powerful enabling technology for the exploration of high dimensional quantitative data by treating data dimensions as first-class objects that can be explored in tandem with data values. In this article, we extend the Dual Analysis framework through the joint treatment of quantitative (numerical) and qualitative (...

The locus coeruleus (LC) is a small nucleus in the brain stem. It is gaining increasing interest of the neuroscientific community due to its potentially important role in the pathogenesis of several neurodegenerative diseases such as Alzheimer's disease. In this study, an existing LC segmentation approach has been improved by adding a preceding LC...

Increasing complexity and volume of research data pose increasing challenges for scientists to manage their data efficiently. At the same time, availability and reuse of research data are becoming more and more important in modern science. The German government has established an initiative to develop research data management (RDM) and to increase...

In MRI, motion artefacts are among the most common types of artefacts. They can degrade images and render them unusable for accurate diagnosis. Traditional methods , such as prospective or retrospective motion correction, have been proposed to avoid or alleviate motion artefacts. Recently, several other methods based on deep learning approaches hav...

In MRI, motion artefacts are among the most common types of artefacts. They can degrade images and render them unusable for accurate diagnosis. Traditional methods, such as prospective or retrospective motion correction, have been proposed to avoid or alleviate motion artefacts. Recently, several other methods based on deep learning approaches have...

The disease and treatment of patients with head and neck cancer can lead to multiple late and long-term sequelae. Especially pain, psychosocial problems, and voice issues can have a high impact on patients’ health-related quality of life. The aim was to show the feasibility of implementing an electronic Patient-Reported Outcome Measure (PROM) in pa...

Despite continuing efforts in solving the problem of motion artifacts in MRI, subject motion remains one of the major sources of image degradation, in research applications and more importantly, in clinical routine acquisitions. It is fundamental to differentiate between images with an acceptable level of motion corruption and those that cannot be...

Following the DOI, you can download the entire dataset: https://doi.org/10.24352/UB.OVGU-2020-145 Here, we present an extension to our previously published structural ultrahigh isotropic resolution T1-weighted magnetic resonance imaging (MRI) dataset, consisting of multiple additional high quality contrasts. Included are up to 150 μm Time-of-Fligh...

Removing motion artifacts in MR images remains a challenging task. In this work, we employed 2 convolutional neural networks, a conditional generative adversarial network (c-GAN), also known as pix2pix, as well as a network based on the residual network (ResNet) architecture, to remove synthetic motion artifacts for phantom images and T1-w brain im...

In this study, contrast prediction is used as an auxiliary tool to regularize underdetermined image reconstructions. This novel regularization strategy enables to share information across individual reconstructions and outperforms state of the art regularizations for high acceleration factors.

Clinical Decision Support Systems (CDSS) provide assistance to physicians in clinical decision-making. Based on patient-specific evidence items triggering the inferencing process, such as examination findings, and expert-modeled or machine-learned clinical knowledge, these systems provide recommendations in finding the right diagnosis or the optima...

Objectives Probabilistic modeling of a patient's situation with the goal of providing calculated therapy recommendations can improve the decision making of interdisciplinary teams. Relevant information entities and direct causal dependencies, as well as uncertainty, must be formally described. Possible therapy options, tailored to the patient, can...

The locus coeruleus (LC) is a small brain structure in the brainstem that may play an important role in the pathogenesis of Alzheimer’s Disease (AD) and Parkinson’s Disease (PD). The majority of studies to date have relied on using manual segmentation methods to segment the LC, which is time consuming and leads to substantial interindividual variab...

Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, and are a marker of cerebral small vessel disease. Most studies use time-consuming and subjective visual scoring to assess these structures. Recently, automated methods to quantify enlarged perivascular spaces have been proposed. Most of these methods have been evaluate...

Denosing of MR data during image reconstruction in complex domain prior to channel combination gives better results compared to denoising magnitude images after reconstruction. In this study we compare 'BM4D' with two settings and the pre-trained neural network 'DnCNN'. The reconstruction pipeline is shared on Github.

Here, we present a reconstruction pipeline written in MATLAB® to reconstruct raw MRI data. Image reconstruction at the scanner’s console is to some extend a black box and no offline out-of-the-box image reconstruction pipeline is publicly available. While e.g. Gadgetron1 and BART2 exists, they do offer a set of tools to reconstruct data rather than...

Enlarged perivascular spaces (PVS) are structural brain changes visible in MRI, and are a marker of cerebral small vessel disease. Most studies use time-consuming and subjective visual scoring to assess these structures. Recently, automated methods to quantify enlarged perivascular spaces have been proposed. Most of these methods have been evaluate...

Considerable evidence suggests a close relationship between vascular and degenerative pathology in the human hippocampus. Due to the intrinsic fragility of its vascular network, the hippocampus appears less able to cope with hypoperfusion and anoxia than other cortical areas. Although hippocampal blood supply is generally provided by the collateral...

Finding an individualized therapy decision for a cancer patient remains a challenge for interdisciplinary teams. The large amount of treatment options, their possible combinations, and the respective medical knowledge must be digested to finally decide for the most promising treatment. In this work, we propose a concept for the imitation of patient...

The poster deals with the generation of Bayesian Networks as a tool for clinical decision support in oncology. It introduces the ways of manual and automatic (based on machine learning) model generation as well as a custom hybrid approach that we are currently developing.

A therapy decision support system (TDSS) based on Bayesian networks (BN) has the potential to support multidisciplinary teams in making patient-specific therapy decisions; mathematically substantiated, transparent and reproducible. BNs are used to model, simulate and study abstractions of real-life situations. At the project "Digital Patient-and Pr...

Model-based decision support systems promise to be a valuable addition to oncological treatments and the implementation of personalized therapies. For the integration and sharing of decision models, the involved systems must be able to communicate with each other. In this paper, we propose a modularized architecture of dedicated systems for the int...

We present a Cerebral Aneurysm Vortex Classification (CAVOCLA) that allows to classify blood flow in cerebral aneurysms. Medical studies assume a strong relation between the progression and rupture of aneurysms and flow patterns. To understand how flow patterns impact the vessel morphology, they are manually classified according to predefined class...

Decision support systems based on probabilistic patient models will contribute to personalized oncological treatments. To be fully used and integrated into the physicians' workflow, the systems must interlink well with hospital information systems. Different technical and contentual requirements render this a demanding task. We set up a list of req...

Simulations and measurements of blood and airflow inside the human circulatory and respiratory system play an increasingly important role in personalized medicine for prevention, diagnosis and treatment of diseases. This survey focuses on three main application areas. (1) Computational fluid dynamics (CFD) simulations of blood flow in cerebral aneu...

PurposeOvercoming the flaws of current data management conditions in head and neck oncology could enable integrated information systems specifically tailored to the needs of medical experts in a tumor board meeting. Clinical dashboards are a promising method to assist various aspects of the decision-making process in such cognitively demanding scen...

Life and health sciences are key application areas for immersive analytics. This spans a broad range including medicine (e.g., investigations in tumour boards), pharmacology (e.g., research of adverse drug reactions), biology (e.g., immersive virtual cells) and ecology (e.g., analytics of animal behaviour). We present a brief overview of general ap...

Head and neck cancer treatment leads to impairment of multiple health and social functions in patients’ lives. These impairments need to be considered in order to find the best suitable aftercare. For their recording, the physicians of the Clinic of Otolaryngology, Head and Neck Surgery at the University of Leipzig conduct a voluntary, questionnair...

Die Tumornachsorge bei Patienten mit Kopf-Hals-Tumoren stellt den Untersucher vor spezifische Herausforderungen. Neben dem Ziel einer optimalen Lokalbefundkontrolle, steht die Erfassung von funktionellen Defiziten, wie unter anderem Beeinträchtigungen der Stimme, der Schluckfunktion und der psychosozialen Funktion im Vordergrund. Aus diesem Grund w...

During the diagnostic process a lot of information is generated. All this information is assessed when making a final diagnosis and planning the therapy. While some patient information is stable, e.g., gender, others may become outdated, e.g., tumor size derived from CT data. Quantifying this information up-to-dateness and deriving consequences are...

Diagnostic delay describes the time it takes for a team of physicians to diagnose a patient and decide on a individual therapy. It is a challenging task to quantify the consequences of diagnostic delay and implement them in a clinical decision support system. When information entities tend to become outdated, their impact on calculations and infere...

Germination, the process whereby a dry, quiescent seed springs to life, has been a focus of plant biologist for many years, yet the early events following water uptake, during which metabolism of the embryo is restarted, remain enigmatic. Here, the nature of the cues required for this restarting in oilseed rape (Brassica napus) seed has been invest...

tumor board. A central role in finding the best therapy options for patients with solid tumors plays the Tumor-, lymph Node, and Metastasis staging (TNM staging). Correctness of TNM staging has a significant impact on the therapy choice and hence, on the patient’s post-therapeutic quality of life or even survival. If inconsistencies in the TNM stag...

In clinical practice, hand drawn sketches are employed to express concepts and are an efficient method for the discussion of complex issues. We present computer graphic methods to improve and support the creation and annotation of complex sketches, resulting in a more clear, expressive and understandable result. For this, we consider the medical ar...

A therapy decision support system (TDSS) based on Bayesian networks (BN) has the potential to support multidisciplinary teams in making patient-specific therapy decisions; mathematically substantiated, transparent and reproducible. BNs are used to model, simulate and study abstractions of real-life situations. At the project “Digital Patient- and P...

Diagnostic delay involves the peril of information becoming outdated. It is a challenging task to quantify the up-to-dateness of clinical information and the consequences of diagnostic delay with the goal of considering them in clinical decision support. We propose an approach to integrating the up-to-dateness of clinical information in a model-bas...

In complex cancer cases, Bayesian networks can support clinical experts in finding the best patient-specific therapeutic decisions. However, the development of decision networks requires teamwork of at least one domain expert and one knowledge engineer making the process expensive, time-consuming, and prone to misunderstandings. We present a novel...

We present a semi-immersive 3D User Interface to sketch complex vascular structures and vessel pathologies by drawing centerlines in 3D. Our framework comprises on-the-fly reconstruction of the corresponding vessel surface and subsequent local surface compression and expansion. Additionally, we allow the enrichment with an illustrative, plausible b...

Epidemiology characterizes the influence of causes to disease and health conditions of defined populations. Cohort studies are population-based studies involving usually large numbers of randomly selected individuals and comprising numerous attributes, ranging from self-reported interview data to results from various medical examinations, e.g., blo...

Computational fluid dynamic (CFD) simulations of blood flow provide new insights into the hemodynamics of vascular pathologies such as cerebral aneurysms. Understanding the relations between hemodynamics and aneurysm initiation, progression, and risk of rupture is crucial in diagnosis and treatment. Recent studies link the existence of vortices in...

Epidemiology characterizes the influence of causes to disease and health conditions of defined populations. Cohort studies are population-based studies involving usually large numbers of randomly selected individuals and comprising numerous attributes, ranging from self-reported interview data to results from various medical examinations, e.g., blo...

Epidemiological population studies impose information about a set of subjects (a cohort) to characterize disease-specific risk factors. Cohort studies comprise heterogenous variables describing the medical condition as well as demographic and lifestyle factors and, more recently, medical image data. We propose an Interactive Visual Analysis (IVA) a...

Annotations of relevant structures and regions are crucial in diagnostics, treatment planning, medical team meet-ings as well as in medical education. They serve to focus discussions, present results of collaborative decision making, record and forward diagnostic support orientation in complex or unfamiliar views on the data, and study anatomy. Di...

Biological multi-channel microscopy data are often characterized by a high local entropy and phenotypically identical structures covering only a few pixels and forming disjoint regions spread over, e.g., a cell or a tissue section. Toponome data as an example, comprise a fluorescence image (channel) per protein affinity reagent, and capture the loc...

Understanding the hemodynamics of blood flow in vascular pathologies such as intracranial aneurysms is essential for both their diagnosis and treatment. Computational Fluid Dynamics (CFD) simulations of blood flow based on patient-individual data are performed to better understand aneurysm initiation and progression and more recently, for predictin...

Medical cohort studies enable the study of medical hypotheses with many samples. Often, these studies acquire a large amount of heterogeneous data from many subjects. Usually, researchers study a specific data subset to confirm or reject specific hypotheses. A new approach enables the interactive visual exploration and analysis of such data, helpin...