Cancer in the Upper Aerodigestive Tract (UADT) is still among the leading cancer types worldwide, with both incidence rate and mortality rate constantly rising. Treatment of these diseases is by Ear-Nose-Throat (ENT) surgeons, operating with incomplete knowledge of the tumor geometry, under non-ergonomic conditions and with limited precision on fragile cancerous tissue. AIRCARE will bring clinical practice in diagnosis and surgical treatment to the next level, by introducing advanced AI and robotic technology into the clinical workflow. For diagnosis, AIRCARE will enable real-time on-the-spot AI-powered optical/electric biopsies, helping to optimize a patient-specific surgical approach. For surgery, AIRCARE will provide a more controlled and ergonomic setting. Novel robotic stabilizing and controlling tools will further allow manipulation of tissue and removal of cancer with unprecedented levels of precision. A newly developed intuitive 3D visualization will simplify the understanding of the complex surgical scene. Aside from increase of safety, quality and efficiency of the surgical procedure, also less experienced surgeons may become able to perform complex image guided treatments. Within this innovation action, our European partners spanning universities, research centers, industry and 3 hospitals, will join forces across disciplines to advance promising research prototypes into two advanced integrated systems: one for diagnosis, one for surgery, thus supporting clinicians from the detection and diagnosis of UADT diseases until their surgical treatment. Within the framework of the project, the superiority of AIRCARE technology will be demonstrated in real operational environments through three clinical studies. By doing so, we aim to demonstrate the benefits of AI and robotics to healthcare professionals and UADT patients and put the seeds to translate this technology into the next standard of care for improved clinical outcomes.

Traditionally, a robot is a machine controlled by a central unit and used to perform specific tasks automatically, often in a structured environment. MAPWORMS aims at challenging this traditional concept by proposing robots inspired by simplified forms of Marine Annelida, able to performtasks in response to environmental stimuli and to adapt to the environment with a shape-morphing strategy. Smart shape-memory hydrogels, able to respond to different stimuli (ion species, chemicals, light, pH, etc.), represent the building blocks in this new generation of morphing robots. By combining smart reactive hydrogels with nonreactive elements, actuation units able to transduce stiffness variation into geometrical changes will be developed. In the proposed endeavour, biology is the inspiration for simplifying principles to deal with a complex world, material science is the foundation for giving the body its proper role in shaping behaviour, mathematical modelling is the way to describe biological mechanisms to provide hints and laws for the artificial counterpart. Robotics and engineering aim at providing tools to quantitatively and functionally study biology, to bring innovative materials from chemistry labs to working systems, and to provide general purpose actuators and adapting machines. With a team of 6 partners (including 2 SMEs) in 4 years, MAPWORMS intends to: 1) study adaptation and plasticity of the body plan in Marine Annelida and shed light on the specialization process that allowed forms appeared early in the evolution of the Phylum to adapt to different environments; 2) develop a mathematical model of Annelida plasticity and adaptation to the environment through burrowing, protrusion of parts of their bodies, and morphological changes; 3) develop smart soft materials embodying responsivity, shape morphing and self-healing capabilities, and based on DNA components; 4) develop bio-inspired modular shape morphing robots across the scale.

Histopathology is a century-old standard for the diagnosis of cancer and other diseases, and for the choice of personalized treatments. Despite its paramount importance for clinical practice, this method is still limited to the analysis of thin slices, presenting a 2D view of the intrinsically 3D structure of biological tissue. Current histopathology practice poses the risk of severely undersampling relevant tissue features: indeed, a growing amount of data demonstrates that traditional 2D analysis produces inconsistent and unreliable results that may have important implications in treatment choice and other clinical decisions. Despite the compelling evidence of the clinical benefits of volumetric tissue analysis, clinical practice is still anchored to 2D imaging. A transition towards 3D inspection would be a quantum leap in the histopathology field but has been prevented hitherto because of technical limitations. Indeed, light-sheet fluorescence microscopy (LSFM) has been hailed in the last decades as a game changer in the field. However, LSFM-based solutions have profound limitations in terms of throughput, reliability and scalability that prevent their use outside specialised research labs. In 3DPATH, we want to leverage several key innovations in LSFM and data analysis technology – developed in previous research projects – to develop a 3D tissue scanner suitable for clinical use. The success of this project will revolutionize histopathology leading to more accurate diagnosis, improving quality of care for patients all over the world, and bringing Europe at the forefront of diagnostic technologies.

The ROBIOPSY project aims at evolving the robotic device for prostate cancer (PC) biopsy demonstrated during the ERC-PoC PROST into a product prototype that will be ready for clinical trials. The focus of the project will be two-fold: the engineerization of the PROST prototype, and the accurate analysis of the business case of prostate cancer diagnosis and its potential extension to focal therapy. We will correct the shortcomings of the pre-clinical tests, meet the strict medical certification regulations, and address the Health Economics implications of our solution. ROBIOPSY will achieve better performance than current competitors because it solves the two main causes of PC diagnostic error: uncertain target identification, and inaccurate needle positioning, as demonstrated in the pre-clinical tests. A novel image fusion method will permit to significantly reduce the target uncertainty, while the robotic device will zero the positioning error.The ROBIOPSY prototype will consist of a single cart holding the robotic needle positioner, and housing all the electronic components. The electronics will be divided into two subsystems: interface and data processing, and safety critical controls. This will reduce the operational risks and will simplify the medical certification. A multi-centric study is ongoing to collect biopsy images to train the Machine Learning algorithms for prostate segmentation and lesion identification. In parallel to the technical development, we will analyze in depth the business case of prostate biopsy in selected European Countries, we will analyze the time/cost reduction due to the new device and will establish the economic foundation of focal therapy, to be ready for the expected evolution of PC treatments.

Retina indications are the leading cause of visual impairment in industrialized countries and posing a big unmet socio-economic challenge. Performing surgical actions directly at the retina - one of the most delicate and sensitive areas of the human body - with ultra-thin microsurgical instruments and with a limited view makes retina surgery a very challenging discipline with surgeons working at the limit of what is possible, requiring years of training and experience to reach proficiency. The GEYEDANCE project is directly addressing this need by translating methods from Artificial Intelligence to the area of surgical robotics, together to be used for an advanced user support for reducing the mental and physical load of the surgeon. Work in the project is building on two existing main blocks - the CE certified robot platform PSS from project partner Preceyes, and a prototype for a Common-Path OCT system with extended measurement depth from partner ACMIT. For the AI-components to be developed, two European leading groups in this domain - ALTAIR/University of Verona and ARTORG/University of Bern - are part of the consortium. Seamless involvement of key stakeholders during the complete development phase is indispensable for a meaningful outcome, and thus a prominent board of world-wide leading eye surgeons, led by partner University of Ferrara, will provide user insight and evaluate the resulting advanced robotic solution. Development and validation of the GEYEDANCE system is strongly supported by industrial partners Carl Zeiss AG and Carl Zeiss Meditec AG. In-line with the concept of the Innovation Actions instrument, the project aims to generate tangible and close-to-certification" technology reaching a TRL of 7 (or even higher), being evaluated in the framework of a first clinical trial. All together, the planned AI-based guidance system GEYEDANCE will help the consortium to further consolidate their leading position worldwide, will help retinal surgeons to optimize their task, and finally will help the patient by contributing to a better surgical outcome.