The robust delineation of the cochlea and its inner structures combined with the detection of the electrode of a cochlear implant within these structures is essential for envisaging a safer, more individualized, routine image-guided cochlear implant therapy. We present Nautilus—a web-based research platform for automated pre- and post-implantation cochlear analysis. Nautilus delineates cochlear structures from pre-operative clinical CT images by combining deep learning and Bayesian inference approaches. It enables the extraction of electrode locations from a post-operative CT image using convolutional neural networks and geometrical inference. By fusing pre- and post-operative images, Nautilus is able to provide a set of personalized pre- and post-operative metrics that can serve the exploration of clinically relevant questions in cochlear implantation therapy. In addition, Nautilus embeds a self-assessment module providing a confidence rating on the outputs of its pipeline. We present a detailed accuracy and robustness analyses of the tool on a carefully designed dataset. The results of these analyses provide legitimate grounds for envisaging the implementation of image-guided cochlear implant practices into routine clinical workflows.

Abstract-Unprecedented knowledge levels in life sciences along with technological advances in micro-and nanotechnologies and microfluidics have recently conditioned the advent of Lab-on-Chip (LoC) devices for In-Vitro Medical Testing (IVMT). Combined with smart-mobile technologies, LoCs are pervasively giving rise to opportunities to better diagnose disease, predict and monitor personalised treatment efficacy, or provide healthcare decision-making support at the Pointof-Care (PoC). Although made increasingly available to the consumer market, the adoption of LoC-based PoC In-Vitro Medical Testing (IVMT) systems is still in its infancy. This attrition partly pertains to the intricacy of designing and developing complex systems, destined to be used sporadically, in a fast-pace evolving technological paradigm. System evolvability is therefore key in the design process and constitutes the main motivation for this work. We introduce a smart-mobile and LoC-based system architecture designed for evolvability. By propagating LoC programmability, instrumentation, and control tools to the highlevel abstraction smart-mobile software layer, our architecture facilitates the realisation of new use-cases and the accommodation for incremental LoC-technology developments. We demonstrate these features with an implementation allowing the interfacing of LoCs embedding current-or impedancebased biosensors such as Silicon Nanowire Field Effect Transistors (SiNW-FETs) or electrochemical transducers. Structural modifications of these LoCs or changes in their specific operation may be addressed by the sole reengineering of the mobilesoftware layer, minimising system upgrade development and validation costs and efforts.

An ageing population leading to more chronic disease is straining healthcare systems. This paper makes two core contributions to healthcare systems design research: Firstly, a systemic techno-behavioural approach is presented to support intervention design with value-effective health outcomes. The systemic techno-behavioural perspective takes into consideration the interaction between three angles: The current healthcare system in place, the technological opportunities for addressing an issue and a broader and deeper understanding of the behaviour of those involved. The purpose of considering these three angels is to create interventions that are more robust. This will help inform healthcare systems design researchers and other stakeholders. Secondly, it is proposed that interventions should be grounded in behavioural theory, a collection of theories are presented to be incorporated in the design process of interventions. The systemic techno-behavioural approach is applied to dementia care highlighting the need to understand the dynamic relationship between the context of the current healthcare delivery system, technology, and behaviour to improve quality of care during the progression of the disease.

Current healthcare delivery challenges are multi-faceted, requiring multiple perspectives to be addressed using a systems approach. However, a significant amount of healthcare systems design research work is carried out within single disciplines or at best a few disciplines working together. There appears to be little deliberate attempt to draw together a wide range of disciplines committed to working together to overcome differences and tackle some of the complex challenges in healthcare delivery. In this paper, we report on the initial outcomes of such an international initiative that, in the form of a workshop held at the University of Cambridge, brought together researchers and practitioners from a wide range of disciplines to explore the foundations of a community for Healthcare Systems Design Research and Practice.