Oliver Dürr

• Phd
• Professor (Associate) at ZHAW Zurich University of Applied Sciences

Study design: Retrospective, mono-centric cohort research study. Objectives: The purpose of this study is to validate a novel artificial intelligence (AI)-based algorithm against human-generated ground truth for radiographic parameters of adolescent idiopathic scoliosis (AIS). Methods: An AI-algorithm was developed that is capable of detecting...

In many medical applications, interpretable models with high prediction performance are sought. Often, those models are required to handle semistructured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression that fulfill these requirements. DTMs allow the data analyst to specify (deep...

Contemporary empirical applications frequently require flexible regression models for complex response types and large tabular or non-tabular, including image or text, data. Classical regression models either break down under the computational load of processing such data or require additional manual feature extraction to make these problems tracta...

BACKGROUND CONTEXT The manual measurement of coronal parameters is known to be time-consuming and dependent on the physician's experience. Spinal measurements of patients who suffer from adolescent idiopathic scoliosis (AIS) are particularly prone to errors in the measurement of Cobb angles due to the subjective localization of end vertebrae of the...

For many medical applications, interpretable models with a high prediction performance are sought. Often, those models are required to handle semi-structured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression which fulfill these requirements. DTMs allow the data analyst to specify...

The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control. However, high fluctuations and increasing electrification cause huge forecast variability, not reflected in traditional point estimates. Probabilistic load forecasts take future uncertain...

Variational inference (VI) is a technique to approximate difficult to compute posteriors by optimization. In contrast to MCMC, VI scales to many observations. In the case of complex posteriors, however, state-of-the-art VI approaches often yield unsatisfactory posterior approximations. This paper presents Bernstein flow variational inference (BF-VI...

Outcomes with a natural order commonly occur in prediction problems and often the available input data are a mixture of complex data like images and tabular predictors. Deep Learning (DL) models are state-of-the-art for image classification tasks but frequently treat ordinal outcomes as unordered and lack interpretability. In contrast, classical or...

The main challenge in Bayesian models is to determine the posterior for the model parameters. Already, in models with only one or few parameters, the analytical posterior can only be determined in special settings. In Bayesian neural networks, variational inference is widely used to approximate difficult-to-compute posteriors by variational distrib...

Outcomes with a natural order, such as quality of life scores or movie ratings, commonly occur in prediction tasks. The available input data are often a mixture of complex inputs like images and tabular predictors. Deep Learning (DL) methods have shown outstanding performances on perceptual tasks. Yet, most DL applications treat ordered outcomes as...

At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the models uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provi...

Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BD...

At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we prov...

We present a deep transformation model for probabilistic regression. Deep learning is known for outstandingly accurate predictions on complex data but in regression tasks, it is predominantly used to just predict a single number. This ignores the non-deterministic character of most tasks. Especially if crucial decisions are based on the predictions...

Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep...

Rheumatoid arthritis is an autoimmune disease that causes chronic inflammation of synovial joints, often resulting in irreversible structural damage. The activity of the disease is evaluated by clinical examinations, laboratory tests, and patient self-assessment. The long-term course of the disease is assessed with radiographs of hands and feet. Th...

Deep learning (DL) methods have gained considerable attention since 2014. In this chapter we briefly review the state of the art in DL and then give several examples of applications from diverse areas of application. We will focus on convolutional neural networks (CNNs), which have since the seminal work of Krizhevsky et al. (ImageNet classificatio...

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters k, and for each \(1 \le k \le k_\mathrm {max}\), a distribution over the individual cluster assignment for each data point. The ne...

Deep neural networks have become a veritable alternative to classic speaker recognition and clustering methods in recent years. However, while the speech signal clearly is a time series, and despite the body of literature on the benefits of prosodic (suprasegmental) features, identifying voices has usually not been approached with sequence learning...

Deep convolutional neural networks show outstanding performance in image-based phenotype classification given that all existing phenotypes are presented during the training of the network. However, in real-world high-content screening (HCS) experiments, it is often impossible to know all phenotypes in advance. Moreover, novel phenotype discovery it...

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters $k$, and for each $1 \leq k \leq k_\mathrm{max}$, a distribution over the individual cluster assignment for each data point. The n...

Deep Learning has boosted artificial intelligence over the past 5 years and is seen now as one of the major technological innovation areas, predicted to replace lots of repetitive, but complex tasks of human labor within the next decade. It is also expected to be ‘game changing’ for research activities in pharma and life sciences, where large sets...

Deep learning, especially in the form of convolutional neural networks (CNNs), has triggered substantial improvements in computer vision and related fields in recent years. This progress is attributed to the shift from designing features and subsequent individual sub-systems towards learning features and recognition systems end to end from nearly u...

Poster Presented at the third edition of the ”Swiss Image-Based Screening Conference”, SIBS 2015 30th Sep – 1st Oct 2015 in Basel

We aimed to identify gene expression signatures associated with angiogenesis and hypoxia pathways with predictive value for treatment response to bevacizumab/erlotinib (BE) of non-squamous advanced NSCLC patients. Whole genome gene expression profiling was performed on 42 biopsy samples (from SAKK 19/05 trial) using Affymetrix exon arrays, and asso...

In this paper we describe a fast and accurate pipeline for real-time face recognition that is based on a convolutional neural network (CNN) and requires only moderate computational resources. After training the CNN on a desktop PC we employed a Raspberry Pi, model B, for the classification procedure. Here, we reached a performance of approximately...

http://alt.qcri.org/semeval2014/cdrom/pdf/SemEval062.pdf In this paper, we describe how we cre- ated a meta-classifier to detect the mes- sage-level sentiment of tweets. We par- ticipated in SemEval-2014 Task 9B by combining the results of several exist- ing classifiers using a random forest. The results of 5 other teams from the competition as we...

Background: Tumor-associated stromal cells have an important role in tumor growth, disease progression and drug resistance. Gene expression analysis (GEA) of various cancers identified molecular subtypes and predictive models for clinically relevant outcomes. This information however, is often derived from heterogeneous clinical samples (tumor and...

In this paper, we analyze the quality of several commercial tools for sentiment detection. All tools are tested on nearly 30,000 short texts from various sources, such as tweets, news, reviews etc. In addition to the quality analysis (measured by various metrics), we also investigate the effect of increasing text length on the performance. Finally,...

Google Trends and other IT fever charts rate Data Science among the most rapidly emerging and promising fields that expand around computer science. Although Data Science draws on content from established fields like artificial intelligence, statistics, databases, visualization and many more, industry is demanding for trained data scientists that no...

We present a new layout algorithm for complex networks that combines a multi-scale approach for community detection with a standard force-directed design. Since community detection is computationally cheap, we can exploit the multi-scale approach to generate network configurations with close-to-minimal energy very fast. As a further asset, we can u...

Recent technological advances in high-content screening instrumentation have increased its ease of use and throughput, expanding the application of high-content screening to the early stages of drug discovery. However, high-content screens produce complex data sets, presenting a challenge for both extraction and interpretation of meaningful informa...

Fast ion conduction is known to occur in many solid materials, allowing us to perform fundamental studies of diffusion processes in a variety of structures. After briefly discussing classes of solid ionic conductors with increasing complexity in their structural and transport behaviour, we shall focus on polymer electrolytes. A lattice model is des...

Stochastic semi-microscopic models for glassy and polymer ion conductors provide a framework for understanding a variety of experimental transport properties in these materials. In the case of glasses we discuss effects of counter ions and propose a mechanism for constant dielectric loss in terms of a dipolar lattice gas. The behavior of glasses is...

There is a growing need to precisely quantify the selectivity of large compound sets in high throughput screening, directing investment in lead optimization towards compounds with a high chance of success. High-content, high-density screening technologies such as multiparametric ultra-HTS provide a basis for highly precise screening with unpreceden...

Monte Carlo simulations are used to study ion and polymer chain dynamic properties in a simplified lattice model with only one species of mobile ions. The ions interact attractively with specific beads in the host chains, while polymer beads repel each other. Cross linking of chains by the ions reduces chain mobilities which in turn suppresses ioni...

This work is devoted to transport processes in dense polymer systems, with emphasis on ion transport in polymer electrolytes. In polymeric systems, orders of magnitude lie between the time scales of relevant microscopic processes and the time scales on which long--range transport takes place. A direct integration of the microscopic equations of mot...

A semi-microscopic description of ionic transport in polyethylene oxide (PEO)-type electrolytes is presented, which is based on discrete stochastic moves of individual molecular units. Diffusion coefficients for ions and for the center of mass motion of chains are calculated by Monte Carlo simulation as a function of various model parameters, with...

Recent experimental observations of anisotropic conductivity in stretched polymer electrolytes films of the polyethylene oxide family are discussed. The main experimental observations, enhancement of the ionic diffusion and conductivity in the stretch direction and decrease in these transport coefficients in the normal direction are interpreted in...

Tracer-diffusion of small molecules through dense systems of chain polymers is studied within an athermal lattice model, where hard core interactions are taken into account by means of the site exclusion principle. An approximate mapping of this problem onto dynamic percolation theory is proposed. This method is shown to yield quantitative results...

Kramers relaxation times $\tau_{K}$ and relaxation times $\tau_{R}$ and $\tau_{G}$ for the end-to-end distances and for center of mass diffusion are calculated for dense systems of athermal lattice chains. $\tau_{K}$ is defined from the response of the radius of gyration to a Kramers potential which approximately describes the effect of a stationar...

Ion-conducting glasses and polymer systems show several characteristic peculiarities in their composition-dependent diffusion properties and in their dynamic response. First we give a brief review of the current understanding of the ion dynamics in network glasses in terms of stochastic theories. Secondly, a model for PEO(polyethylene-oxide)-based...

Diffusion of ions through a fluctuating polymeric host is studied both by Monte Carlo simulation of the complete system dynamics and by dynamic bond percolation (DBP) theory. Comparison of both methods suggests a multiscale-like approach for calculating the diffusion coefficients of the ions

Structural disorder is an inherent property of solid materials, which can support a macroscopic ionic current. Many transport phenomena in these solid ionic conductors appear to be related to concepts from percolation theory. We demonstrate this for three classes of materials, namely (i) dispersed ionic conductors, which show conductance properties...

Thema dieser Arbeit waren Monte-Carlo-Simulationen zu polymeren Ionenleitern. Dabei lag der Schwerpunkt auf der Entwicklung einer Methode zur Berechnung dynamischer Größen eines Gittermodells von in PEO gelöstem Salz bei konstantem Druck. Damit erhält man zum einen Zugang zu dem experimentell wichtigen (NpT)-Ensemble, zum anderen kann so der Einflu...