SBI – Department of Systems Biology and Bioinformatics
Faculty of Computer Science and Electrical Engineering
University of Rostock
Ulmenstrasse 69 | 18057 Rostock
+49 381 498-7571
In the evaluation of imaging procedures (X-ray, CT, MRI), many assistance systems already exist to visually prepare the images for diagnosis. Software tools support physicians by segmenting and annotating regions of interest in medical images and diagnosing diseases. In recent years in particular, the analysis of medical image data using artificial intelligence has made great strides.
In order to increase acceptance among physicians, diagnoses should be made comprehensible. However, the greatest advantage of frequently used neural networks is at the same time a great disadvantage: Due to their complexity, they allow classifications to be made for difficult questions, but the underlying decision-making process can hardly be traced. However, the comprehensibility can be increased by novel methods through so-called "Explainable" or "Reasonable" AI. Here, especially for image data, a modified version of the image is usually output, in which specific areas are marked that are of high importance for the network for a certain diagnosis/classification.
At SBI, existing algorithms of "Explainable" AI are applied to medical diagnostic tools, and new methods are developed specifically for this use case.
Finding groups of airway tree structures in CT images
A European standardization framework for data integration and data-driven in silico models for personalised medicine.
The project addresses the generation and establishment of programmed pacemaker cells for an in vitro drug testing possibility to perform predictive tests. This may lead to an improved treatment of cardiac arrhythmias or an accurate identification of potential drug molecules at an early stage of development. Important benefits will arise in verifying the safety of a wide variety of medicines while reducing animal testing.
RNA Sequencing (RNA-Seq) has become a widely used tool to study quantitative and qualitative aspects of the transcriptome. The variety of RNA-Seq protocols, experimental study designs and the characteristic properties of the organisms under investigation greatly affect downstream and comparative analyses. We provide easy access to comprehensive analysis of RNA-Seq experiments as a service. To do so, we leverage on the Galaxy framework, and organise dedicated workshops, training programs, and screencasts to make Life Scientists familiar with computational approaches to biological problems.
Computational Models for Clinical Applications in Personalized Medicine—Guidelines and Recommendations for Data Integration and Model Validation
Catherine Bjerre Collin, Tom Gebhardt, Martin Golebiewski, Tugce Karaderi, Maximilian Hillemanns, Faiz Muhammad Khan, Ali Salehzadeh-Yazdi, Marc Kirschner, Sylvia Krobitsch, EU-STANDSPM consortium, Lars Kuepfer
The future development of personalized medicine depends on a vast exchange of data from different sources, as well as harmonized integrative analysis of large-scale clinical health and sample data. Computational-modelling approaches play a key role in the analysis of the underlying molecular processes and pathways that characterize human biology, but they also lead to a more profound understanding of the mechanisms and factors that drive diseases; hence, they allow personalized treatment strategies that are guided by central clinical questions. However, despite the growing popularity of computational-modelling approaches in different stakeholder communities, there are still many hurdles to overcome for their clinical routine implementation in the future. Especially the integration of heterogeneous data from multiple sources and types are challenging tasks that require clear guidelines that also have to comply with high ethical and legal standards. Here, we discuss the most relevant computational models for personalized medicine in detail that can be considered as best-practice guidelines for application in clinical care. We define specific challenges and provide applicable guidelines and recommendations for study design, data acquisition, and operation as well as for model validation and clinical translation and other research areas.
accepted in MDPI Journal of Personalized Medicine
Comparison of Deep Learning Approaches for Cardiomyocyte Evaluation
Arrhythmias are severe cardiac diseases and lethal if untreated. To serve as an in vitro drug testing option for anti-arrhythmic agents, cardiomyocytes and especially pacemaker cells are being generated in vitro from induced pluripotent stem cells (iPSCs). These generated cardiomyocytes resemble fetal cardiac tissue rather than adult cardiomyocytes. An automated tool for evaluations of cardiomyocytes would help the establishment of new generation protocols. In this work, a novel approach for this task is presented and evaluated.
Different convolutional neural networks (CNNs) including transfer models and native 2D and 3D models were trained on fluorescence images of cardiomyocytes, which were rated based on their sarcomerisation and the orientation of sarcomeres (directionality) beforehand. The CNNs were trained to perform classifications on sarcomerisation and directionality ratings and cell source, as cardiomyocytes from five different sources were used in this work. In this thesis, it could be shown that cellular fluorescence images can be analysed with CNNs. This classifier can be used to make trustworthy predictions on the quality of a cardiomyocyte which will hopefully benefit the generation of cardiomyocytes from iPSCs. This classifier is currently being
Education and Work Experience
Department of Systems Biology and Bioinformatics, Universität Rostock, Germany
2017 - 2020
Medical Engineering Sciences, University of Lübeck, Germany
2013 - 2017
Medical Engineering Sciences, University of Lübeck, Germany