Search

Clustering white matter (WM) tracts from diffusion tensor imaging (DTI) is primarily important for quantitative analysis on pediatric brain development. A recently developed algorithm, density peaks (DP) clustering, demonstrates great robustness to the complex structural variations of WM tracts without any prior templates. Nevertheless, the calculation of densities, the core step of DP, is time consuming especially when the number of WM fibers is huge. In this paper, we propose a fast algorithm that accelerates the density computation about 50 times over the original one. We convert the global calculation for the density as well as critical parameter in the process into local computations, and develop a binary tree structure to orderly store the neighbors for these local computations. Hence, the density computation turns out to be a direct access of the structure, rendering significantly computational saving. Performing experiments on synthetic point data and the JHU-DTI data set and comparing results of our fast DP algorithm and existing clustering methods, we can validate the efficiency and effectiveness of our fast DP algorithm. Finally, we demonstrate the application of the proposed algorithm on the analysis of pediatric WM tract development. [ABSTRACT FROM AUTHOR]

Difficulties in motor development are frequent and impairing. However, the assessment of these motor learning skills is difficult and limits early stage rehabilitation. Electronic sensors and algorithms can help to measure motor difficulties more easily and objectively. We will present a systematic review detailing these methods and challenges in Autism Spectrum Disorders (ASD). Electronic tablets, give access to handwriting features that are not usually evaluated in classical assessments. We describe how such digital features (in static, dynamic, pressure, and tilt domains) allow diagnosing dysgraphia and how they evolve during children development. From a finer analysis, three different clusters of dysgraphia emerge, longitudinal studies will allow to underline different patterns of development that seemingly require tailored remediation strategies. However, those digital features are not used in the context of conventional pen and paper therapies. It is possible to engage children with typical development in handwriting exercises by asking them to teach a robot to write. We implemented a longterm case study (20 sessions, 500 minutes in total) observing a child with severe Developmental Co-ordination Disorder who did not progress anymore with a classic pen and paper approach by enriching this setup with various training activities using real-time feedback loops (on tilt, pressure, dynamic, pauses). We show how this new method tackles previous child's behaviour avoidances, boosting his motivation, and improving his motor and writing skills. This talk demonstrates how new motor digital features allow the implementation of innovative motor remediation interventions, which rely on fostering children's personal characteristics and adaptation skills. [ABSTRACT FROM AUTHOR]