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.

Computational methods are nowadays ubiquitous in the field of bioinformatics and biomedicine. Besides established fields like molecular dynamics, genomics or neuroimaging, new emerging methods rely heavily on large scale computational resources. These new methods need to manage Tbytes or Pbytes of data with large-scale structural and functional relationships, TFlops or PFlops of computing power for simulating highly complex models, or many-task processes and workflows for processing and analyzing data. Today, many areas in Life Sciences are facing these challenges. This special issue contains papers showing existing solutions and latest developments in Life Sciences and Computing Sciences to collaboratively explore new ideas and approaches to successfully apply distributed IT-systems in translational research, clinical intervention, and decision-making.

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.

In this paper, we describe the grid integration of medical image processing applications as grid workflows. The workflow management system is able to execute all tasks related to grid communication, such as authorization, scheduling and monitoring. It remains to the developer to make the code accessible for the workflow manager, and to define, what to do with it. Coarse-grained parallelization of processing steps for runtime reduction can easily be realized. We describe the procedure how to port the code to the grid and show exemplarily the integration of segmentation and registration algorithms for transrectal ultrasound guided prostate biopsies.

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.