In image-guided neurosurgery, co-registered preoperative anatomical, functional, and diffusion tensor imaging can be used to facilitate a maximally safe resection of brain tumors in eloquent areas of the brain. However, because the brain can deform significantly during surgery, particularly in the presence of tumor resection, non-rigid registration of the preoperative image data to the patient is required. This talk reports the results (using clinical data) of a comparison of the accuracy and performance among four open-source non-rigid registration methods for handling brain deformation in the presence of tumor resection, including a new adaptive method that automatically removes mesh elements in the area of the resected tumor, thereby automatically handling deformation in the presence of resection.

In this talk data from 30 glioma surgeries performed at two different hospitals, many of which involved the resection of significant tumor volumes. Three measures aid in assessing the accuracy of the registration methods: (i) visual assessment, (ii) a Hausdorff Distance-based metric, and (iii) a landmark-based approach using anatomical points identified by a neurosurgeon. Performance analysis showed that the adaptive method could be applied, on average, in less than two minutes, achieving desirable speed for use in a clinical setting and significantly better than other readily-available registration methods at modeling deformation in the presence of resection. Both the registration accuracy and performance proved sufficient to be of clinical value in the operating room.

Given time availability a brief description of related real-time Image-to-Mesh conversion technologies at developed CRTC to facility adaptive method will be presented.

Unobtrusive clinical monitoring with robots in AAL environments: the RADIO ecosystem
Technical advancements in ICT, including robotics, bring new opportunities to improve the quality of life of the elderly, their family and care-givers, and to mimimize the invonvenience and cost of clinical monitoring. Automatically detecting early symptoms of cognitive impairment, frailty and social exclusion would extend people's ability to safely and comportably live independently. 
The ecosystem proposed by the H2020 RADIO project (http://radio-project.eu/) aims to integrate multiple RADIO Home deployments, medical institutions, and informal care givers into an information management and sharing Ecosystem that is by design scalable, secure and privacy-preserving. RADIO Home is, effectively, a robot operating inside a Smart Home. In this environment, Smart Home and robot functionalities accommodate the user’s needs, while assuming interaction with the users as an opportunity for clinical monitoring. In this manner, clinical monitoring sensors do not need to be masked but become an obvious, yet discrete and accepted, part of the user’s daily life. Moreover, a robot has a dynamic presence in the user’s space, which can increase the feeling of safety by being in the right place at the right time. 
The talk will present the project outcomes so far, focusing on the clinical and unobtrusiveness requirements which guided the design of the RADIO architecture, and on the architectural and methodological work to ensure that multiple RADIO Homes and care-givers can be interconnected in a scalable, secure and privacy-preserving ecosystem. It will also present the outcomes of real-environment piloting performed in the premises of our clinical partners, to evaluate the usability of the system, its fitness for its medical purpose and the compliance with unobtrusiveness.