Search

In clinical scenarios, there is an increasing interest in complex computational experiments, as for example the training of Deep Learning models. Reproducibility is an essential property of such experiments, especially if the result contributes to a patient’s treatment. This paper introduces Curious Containers, a software framework for computational reproducibility that treats data, software and runtime environment as decentralized network resources. All experiment resources are described in a single file, using a new format that is compatible with a subset of the Common Workflow Language. Docker is used to deploy the experiment software in a container image, including arbitrary data transmission programs to connect with existing storage solutions. The framework supports Deep Learning applications, that have a high demand in storage and processing capabilities. Large datasets can be mounted inside containers via network filesystems like SSHFS based on the filesystem in user-space technology. The Nvidia-Container-Toolkit enables GPU usage. Curious Containers has been tested in two biomedical scenarios. The first use case is a Deep Learning application for tumor classification in images that requires a large dataset and a GPU. In this context, a prototypical integration of the framework with the existing Data Version Control system for exploratory Deep Learning modeling has been developed. The second use case extends an existing container image, including a scientific workflow for detection and comparison of human protein in mass spectrography data. The container image was originally developed for an archiving platform and could be extended to be compatible with both Curious Containers and cwltool, the Common Workflow Language reference implementation. The presented solution allows for consistent description and execution of computational experiments, while trying to be both flexible and interoperable with existing software and standards. Support for Deep Learning experiments is gaining importance as such systems are increasingly validated as medical decision support systems.

Automatic electrocardiogram (ECG) analysis has been one of the very early use cases for computer assisted diagnosis (CAD). Most ECG devices provide some level of automatic ECG analysis. In the recent years, Deep Learning (DL) is increasingly used for this task, with the first models that claim to perform better than human physicians. In this manuscript, a pilot study is conducted to evaluate the added value of such a DL model to existing built-in analysis with respect to clinical relevance. 29 12-lead ECGs have been analyzed with a published DL model and results are compared to build-in analysis and clinical diagnosis. We could not reproduce the results of the test data exactly, presumably due to a different runtime environment. However, the errors were in the order of rounding errors and did not affect the final classification. The excellent performance in detection of left bundle branch block and atrial fibrillation that was reported in the publication could be reproduced. The DL method and the built-in method performed similarly good for the chosen cases regarding clinical relevance. While benefit of the DL method for research can be attested and usage in training can be envisioned, evaluation of added value in clinical practice would require a more comprehensive study with further and more complex cases.

A standard format for neurophysiology data is urgently needed to improve clinical care and promote research data exchange. Previous neurophysiology format standardization projects have provided valuable insights into how to accomplish the project. In medical imaging, the Digital Imaging and Communication in Medicine (DICOM) standard is widely adopted. DICOM offers a unique environment to accomplish neurophysiology format standardization because neurophysiology data can be easily integrated with existing DICOM-supported elements such as video, ECG, and images and also because it provides easy integration into hospital Picture Archiving and Communication Systems (PACS) long-term storage systems. Through the support of the International Federation of Clinical Neurophysiology (IFCN) and partners in industry, DICOM Working Group 32 (WG-32) has created an initial set of standards for routine electroencephalography (EEG), polysomnography (PSG), electromyography (EMG), and electrooculography (EOG). Longer and more complex neurophysiology data types such as high-definition EEG, long-term monitoring EEG, intracranial EEG, magnetoencephalography, advanced EMG, and evoked potentials will be added later. In order to provide for efficient data compression, a DICOM neurophysiology codec design competition will be held by the IFCN and this is currently being planned. We look forward to a future when a common DICOM neurophysiology data format makes data sharing and storage much simpler and more efficient.

Sleep is a fundamental biological process crucial for survival and health of (not only) humans. But many circumstances like physiological and mental disorders, environment and lifestyle may affect healthy sleep. To date, 88 different sleep disorders are internationally recognized. They cover a broad field of medical areas. Analysis of human sleep is typically based on multidimensional biosignal recordings, so called polysomnographies (PSG). Therefore research often includes digital signal processing. Clinical sleep research is an inherent multidisciplinary field. Inter-institutional and interdisciplinary collaborations are required to address the complexity of sleep regulation and disturbance. But to date, collaborative sleep research is poorly supported by IT systems. In particular, the management and processing of PSGs is challenging. A large variety of PSG devices, data formats, measurement procedures and quality variations impedes consistent biosignal data processing. In this manuscript we introduce a virtual research platform supporting inter-institutional data sharing and processing. The infrastructure is based on XNAT—a free and open source neuroimaging research platform, a loosely coupled service oriented architecture and scalable virtualization in the back end. The system is capable of local pseudonymization of biosignal data, mapping to a standardized set of parameters and automatic quality assessment. Terms and quality measures are derived from the “Manual for the Scoring of Sleep and Associated Events” of the American Academy of Sleep Medicine (AASM), the de facto standard for diagnostic biosignal analysis in sleep medicine.

Convolutional Neural Networks (CNN) are used for automatic cancer detection in pathological images. These data-driven experiments are difficult to reproduce, because the CNNs may require CUDA-enabled Nvidia GPUs for acceleration and training is often performed on a large dataset stored on a researcher's computer, inaccessible to others. We introduce the RED file format for reproducible experiment description, where executable programs are packaged and referenced as Docker container images. Data inputs and outputs are described as network resources using standard transmission and authentication protocols instead of local file paths. Following the FAIR guiding principles, the RED format is based on and compatible with the established Common Workflow Language specification. RED files are interpreted by the accompanying Curious Containers (CC) software. Arbitrarily large datasets are mounted inside containers via FUSE network filesystems like SSHFS. SSHFS is compared to NFS and a local SSD in artificial benchmarks and in the context of a CNN training scenario, where SSHFS introduces a performance decrease by a factor of 1.8. We are convinced that RED can greatly improve the reproducibility of deep learning workloads and data-driven experiments. This is in particular important in clinical scenarios where the result of an analysis may contribute to a patient's treatment.

Network physiology describes the human body as a complex network of interacting organ systems. It has been applied successfully to determine topological changes in different sleep stages. However, the number of network links can quickly grow above the number of parameters that are typically analyzed with standard statistical methods. Artificial Neural Networks (ANNs) are a promising approach as they are successful in large parameter spaces, such as in digital imaging. On the other hand, ANN models do not provide an intrinsic approach to interpret their predictions, and they typically require large training data sets. Both aspects are critical in biomedical research. Medical decisions need to be explainable, and large data sets of quality assured patient and control data are rare. In this paper, different models for the classification of insomnia-a common sleep disorder-have been trained with 59 patients and age and gender matched controls, based on their physiological networks. Feature relevance evaluation is employed for all methods. For ANNs, the extrinsic interpretation method DeepLift is applied. The results are not identical across methods, but certain network links have been rated as relevant by all or most of the models. While ANNs show less classification accuracy (0.89) than advanced tree-based models (0.92 and 0.93), DeepLift provides an in-depth ANN interpretation with feature relevance scores for individual data samples. The analysis revealed modifications in the pulmonar, ocular, and cerebral subnetworks that have not been described before but are consistent with known findings on the physiological impact of insomnia.

Applications for data analysis of biomedical data are complex programs and often consist of multiple components. Re-usage of existing solutions from external code repositories or program libraries is common in algorithm development. To ease reproducibility as well as transfer of algorithms and required components into distributed infrastructures Linux containers are increasingly used in those environments, that are at least partly connected to the internet. However concerns about the untrusted application remain and are of high interest when medical data is processed. Additionally, the portability of the containers needs to be ensured by using only security technologies, that do not require additional kernel modules. In this paper we describe measures and a solution to secure the execution of an example biomedical application for normalization of multidimensional biosignal recordings. This application, the required runtime environment and the security mechanisms are installed in a Docker-based container. A fine-grained restricted environment (sandbox) for the execution of the application and the prevention of unwanted behaviour is created inside the container. The sandbox is based on the filtering of system calls, as they are required to interact with the operating system to access potentially restricted resources e.g. the filesystem or network. Due to the low-level character of system calls, the creation of an adequate rule set for the sandbox is challenging. Therefore the presented solution includes a monitoring component to collect required data for defining the rules for the application sandbox. Performance evaluation of the application execution shows no significant impact of the resulting sandbox, while detailed monitoring may increase runtime up to over 420%.

Grid computing, the collaboration of distributed resources across institutional borders, is an emerging technology to meet the rising demand on computing power and storage capacity in fields such as high-energy physics, climate modeling, or more recently, life sciences. A secure, reliable, and highly efficient data transport plays an integral role in such grid environments and even more so in medical grids. Unfortunately, many grid middleware distributions, such as the well-known Globus Toolkit, lack the integration of the world-wide medical image communication standard Digital Imaging and Communication in Medicine (DICOM). Currently, the DICOM protocol first needs to be converted to the file transfer protocol (FTP) that is offered by the grid middleware. This effectively reduces most of the advantages and security an integrated network of DICOM devices offers. In this paper, a solution is proposed that adapts the DICOM protocol to the Globus grid security infrastructure and utilizes routers to transparently route traffic to and from DICOM systems. Thus, all legacy DICOM devices can be seamlessly integrated into the grid without modifications. A prototype of the grid routers with the most important DICOM functionality has been developed and successfully tested in the MediGRID test bed, the German grid project for life sciences.

Clinical Sleep Research is an inherent multidisciplinary field, as many health issues may affect a person's sleep conditions and sleep disorders may cause several health problems. Many patients with chronic sleep disorders suffer from different further medical conditions -- called multimorbidity. Due to the high variety of the reasons and the courses of sleep disorders, individual cases are difficult to compare. Therefore there is a high demand for sleep researchers to collaborate with each other to reach necessary participant numbers and multidisciplinary expertise. To date, inter-institutional sleep research is poorly supported by IT systems. In particular the heterogeneity and the quality variations within the acquired bio signal data -- caused by different bio signal recorders or different measurement procedures -- are impeding common bio signal data processing. In this manuscript we introduce a virtual research platform supporting inter-institutional data sharing and processing. The infrastructure is based on XNAT -- a free and open-source neuroimaging research platform -- a loosely coupled service oriented architecture and scalable virtualization in the backend. The system is capable of local pseudonymization of bio signal data, mapping to a standardized set of parameters and automatic quality assessment. Terms and quality measures are derived from the "Manual for the Scoring of Sleep and Associated Events" of the American Academy of Sleep Medicine, the de-facto standard for diagnostic bio signal analysis in sleep medicine.

Neurosciencific research is increasingly based on image analysis methods. Large sets of imaging data are processed using complex image analysis tools. While today magnetic resonance imaging (MRI) is widely used for both functional and anatomical analysis of the human brain, new imaging modalities are beginning to prove their capabilities for neurological research. Among them, optical coherence tomography (OCT) allows for noninvasive visualization of anatomical structures on a micrometer scale. Becoming a standard diagnostic tool in ophthalmology, it is of rising interest for neurological research. Crucial to all data analysis methods is the quality of the input data. The platform presented in this paper is designed for automatic quality assessment of retinal OCTs. It extends the image management platform XNAT by services to calculate and store quality measures. It is also extensible regarding new quality measure algorithms, allowing the developer to upload Matlab code, compile it for the infrastructure's hardware architecture and test it in the system. The image processing tools to calculate the quality measures are provided as a cloud-based service employing OpenStack as underlying IT infrastructure. The prototype implementation encompassing security and performance aspects are presented.

Sleep medicine and sleep research often include comprehensive analysis of multidimensional biosignal recordings during the whole bedtime phase, so called polysomnographies. In order to build an environment for support on the development of new analysis tools and clinical research in the field of sleep research, a production grid infrastructure is employed. Clinical data and polysomnographies from over 300 persons have been integrated as a reference database, and different algorithms for automated analysis of electrocardiograms (ECGs) are implemented. The database can be queried and matching data can be analyzed individually and as a collection. Workflow integration of the analysis and portlet based user interfaces provide a high level of abstraction, hiding the complexity of the underlying grid system and employing basic fault tolerance. The system is laid out for future extension to allow medical decision support based on the developed methods.

Personal Health Systems are developed for individualized diagnosis, prevention and treatment depending on the actual health-state of the regarding person with a minimum of interference of his or her daily life. They imply the continuous or at least frequent monitoring of the person's health status, subsequent evaluation and possible action initialization, may it be feedback to the patient, a message to the attending physician or the readjustment of a therapeutical device. In this paper, we propose personal health systems that combine new sensor and information technologies. They allow for extensive undisturbing biosignal acquisition at the person's home and comprehensive data processing and analysis using a grid infrastructure. The grid can be considered as a virtual space where people can share their personal health data with attending medical professionals and where an individual and adaptive set of processing and analysis tools is available in a uniform, easy-to-access and cost-efficient way. The current state of public IT networks and grid infrastructures may not allow real-time applications, while complex near-term postprocessing and decision support can be accomplished. The presented systems are dedicated to sleep related breathing disorders, but the underlying concept may also be suitable for other use-cases.

This chapter describes security and privacy issues within the scope of biomedical Grid Computing. Grid Computing is of rising interest for life sciences (Konagaya, 2006) and has been used since many years in sciences like high energy physics. Anyhow, medical applications on the grid require a special focus on data security and data protection issues. Based on general security and privacy rules, the authors describe the current state of the art of grid security. Then they describe which additional security measures have to be established in different biomedical grid scenarios. Legal aspects have to be taken into account as well as the current possibilities and flaws of grid security technology. Describing the enhanced security concept in MediGRID (MediGRID, 2005) they outline how medical Grid Computing could fulfill privacy regulations used in more demanding environments.

The Charite Grid Portal combines portal components from different groups and projects to provide domain researchers a gateway to Grid-based biomedical applications. Trusted users can securely access and employ Grid resources and services. In this paper, five portal components are presented: (1) The credential management administrates the user-credentials and authenticates them to the Grid. (2) The brain imaging data analysis (FSL) submits workflows to the Grid as part of Medical Image processing. (3) The integrated web services of Generic Workflow Execution Service (GWES) manage workflows executed by users in the Grid. (4) The data management component provides secure and efficient data management in a Grid environment, and enables high-speed data transports between user and Grid. (5) The lung sound analysis application provides twofold-pseudonymization before data-transferred to the Grid. The implementation as standardized portlets allows easy integration of specific components into different Grid portals such as the VO specific MediGRID and PneumoGrid portals.

Advanced visualization technologies are gaining major importance to interpret, present and manipulate high dimensional biomedical data. Since new health technologies are constantly increasing in complexity, adequate information processing is required for diagnostics, therapy planning and treatment. The combination of advanced visualization resources and biomedical grid infrastructures is a promising approach to build dynamic and scalable problem solving environments for such tasks. Visualization then becomes the main issue in system-user interaction, and is therefore a crucial factor in the usefulness of the complete system for the domain researchers. In this paper, two remote visualization approaches to utilize the capabilities of such an environment are presented and evaluated. Evaluation criteria are performance, usability, adaptivity and functionality. Both, an open source and a commercial solution are considered. While the proprietary software shows better performance, the open source solution offers the advantage for seamless grid integration.

Longterm biosignal recordings, such as overnight sleep recordings (so-called polysomnographies, PSG), often vary in signal quality and signal shape. Movement artifacts occur frequently. This may impede successful application of automated processing algorithms designed for well-defined short-term recordings. To test existing algorithms on suitability for PSG analysis, and develop robust analysis tools, an environment that offers efficient application of biosignal methods on comprehensive and representative reference data is required. In this article, a Grid based biosignal processing platform is presented, that provides a large set of clinical PSG reference data collected within the SIESTA project. To date, different processing and evaluation methods with focus on polysomnographic electrocardiogram (PSG-ECG) based analysis are implemented. First results for heart rate analysis of PSG-ECG are given, including the introduction of a performance quality measure for non-annotated PSG-ECG. Different publicly available heart beat detection algorithms have been tested. As an example, the wqrs algorithm, provided by the PhysioNet shows a sensitivity of over 99% and a positive predictive value of over 94% on the PhysioNet's PSG reference data. Processed on the SIESTA data, it only detects around 60% of the heart beats, resulting in a low average performance quality of 0.28. Evaluation of further algorithms has led to the development of an improved, robust algorithm with a high average performance quality of 0.98.

Analysis of diffusion weighted magnetic resonance images serves increasingly for non-invasive tracking of nerve fibers in the human brain, both in clinical diagnosis and basic research. Diffusion-tensor imaging (DTI) enables in-vivo research on the internal structure of the central nervous system, an estimation of the interconnection of functional areas and diagnosis of brain tumors and de-myelinating diseases. But modeling the local diffusion parameters is computationally expensive and on standard desktop computers runtimes of up to days are common. A workflow based grid implementation of the algorithm with slice-based parallelization has shown significant speedup. However, in production use, the implementation frequently delayed and even failed, discouraging the medical collaborators to take up the management of the data processing themselves. Therefore a comprehensive analysis of possible sources for errors and delays as well as their real impact in the respective infrastructure is vital to enable clinical researchers to fully exploit the benefits of the Healthgrid application. In this manuscript, we tested different implementations of the DTI analysis with respect to robustness and runtime. Based on the results, concrete application improvements as well as general suggestions for the layout and maintenance of Healthgrids are concluded.

The analysis of biosignals, such as the electroencephalogram EEG or the electrocardiogram (ECG), is essential for diagnosis in many medical areas, in particular sleep medicine and sleep research. A standard method in this field is the polysomnography, a multidimensional biosignal recording during the whole bedtime phase. Within the SIESTA project, a European multicenter study, comprehensive clinical and polysommnographic records from over 300 persons has been collected. To make the data available for researchers as reference for clinical research and development of new analysis tools, the SIESTA database is implemented into a grid infrastructure. To date, the complete data is stored into the grid and different algorithms for automated ECG analysis are implemented. The database can be queried and the matching data can be analysed on record level and collection level. The application is modelled as a workflow and integrated into the grid using a workflow manager. A graphical user interface is implemented as a grid portlet. It allows the initialization of new computation tasks as well as the monitoring and result-retrieval from already launched analyses.

Many scenarios in medical research are predestined for grid computing. Large amounts of data in complex medical image, biosignal and genome processing demand large computing power and data storage. Integration of distributed, heterogeneous data, e.g. correlation between phenotype and genotype data are playing an essential part in life sciences. Sharing of specialized software, data and processing results for collaborative work are further tasks which would strongly benefit from the use of grid infrastructures. However, two major barriers are identified in existing grid environments that prevent extensive use within the life sciences community: Extended security requirements and appropriate usability. To meet these requirements, the MediGRID project is enhancing the basic D-Grid infrastructure along with the implementation of prototype applications from different fields of biomedical research. In this paper, we focus on the developments for ease-of-use under consideration of different aspects of security. They encompass not only security within the grid infrastructure, but also the boundary conditions of network security oil the site of the research institutions. For medical grids, we propose a strictly web portal-based access to grid resources for end-users, with user-guiding, application specific. graphical interfaces. Different levels Of authorization are implemented, from fully authorized users to guests without certificate authentication in order to allow hands-on experience for potential grid users.

Medical grid networks typically deal with extremely sensitive information and therefore require a special diligence in terms of security and reliability. This holds especially true in Medical Imaging, which is why the medical community long established DICOM (Digital Imaging and Communication in Medicine), a world-wide imaging and communication standard for secure and reliable data interchange. Most healthgrid projects today use DICOM with a combination of GridFTP and the Reliable-File-Transfer (RFT) webservice. Due to the multiple protocols and services involved, this solution is not ideally suited in terms of reliability or fault-tolerance. The proposed solution in this paper replaces the GridFTP combination by an end- to-end Grid-enhanced DICOM implementation and models the GridDICOM transfers as complex, Petri-Nets-based workflows. Based on these workflows, a respective workflow engine can autonomously and reliably control transfers including complex fault recovery and optimized routing strategies. A first prototype of the service, the components, and the respective workflows have been developed and successfully tested in MediGRID, the German grid network for life-sciences.