We present a method for automated spike sorting for recordings with high-density, large-scale multielectrode arrays. Exploiting the dense sampling of single neurons by multiple electrodes, an efficient, low-dimensional representation of detected spikes consisting of estimated spatial spike locations and dominant spike shape features is exploited for fast and reliable clustering into single units. Millions of events can be sorted in minutes, and the method is parallelized and scales better than quadratically with the number of detected spikes. Performance is demonstrated using recordings with a 4,096-channel array and validated using anatomical imaging, optogenetic stimulation, and model-based quality control. A comparison with semi-automated, shape-based spike sorting exposes significant limitations of conventional methods. Our approach demonstrates that it is feasible to reliably isolate the activity of up to thousands of neurons and that dense, multi-channel probes substantially aid reliable spike sorting.

Social interactions are made of complex behavioural actions that might be found in all mammalians, including humans and rodents. Recently, mouse models are increasingly being used in preclinical research to understand the biological basis of social-related pathologies or abnormalities. However, reliable and flexible automatic systems able to precisely quantify social behavioural interactions of multiple mice are still missing. Here, we present a system built on two components. A module able to accurately track the position of multiple interacting mice from videos, regardless of their fur colour or light settings, and a module that automatically characterise social and non-social behaviours. The behavioural analysis is obtained by deriving a new set of specialised spatio-temporal features from the tracker output. These features are further employed by a learning-by-example classifier, which predicts for each frame and for each mouse in the cage one of the behaviours learnt from the examples given by the experimenters. The system is validated on an extensive set of experimental trials involving multiple mice in an open arena. In a first evaluation we compare the classifier output with the independent evaluation of two human graders, obtaining comparable results. Then, we show the applicability of our technique to multiple mice settings, using up to four interacting mice. The system is also compared with a solution recently proposed in the literature that, similarly to us, addresses the problem with a learning-by-examples approach. Finally, we further validated our automatic system to differentiate between C57B/6J (a commonly used reference inbred strain) and BTBR T+tf/J (a mouse model for autism spectrum disorders). Overall, these data demonstrate the validity and effectiveness of this new machine learning system in the detection of social and non-social behaviours in multiple (>2) interacting mice, and its versatility to deal with different experimental settings and scenarios.

This paper presents a simple and effective generalization method for magnetic resonance imaging (MRI) segmentation when data is collected from multiple MRI scanning sites and as a consequence is affected by (site-)domain shifts. We propose to integrate a traditional encoder-decoder network with a regularization network. This added network includes an auxiliary loss term which is responsible for the reduction of the domain shift problem and for the resulting improved generalization. The proposed method was evaluated on multiple sclerosis lesion segmentation from MRI data. We tested the proposed model on an in-house clinical dataset including 117 patients from 56 different scanning sites. In the experiments, our method showed better generalization performance than other baseline networks.

An important task in connectomics studies is the classification of connectivity graphs coming from healthy and pathological subjects. In this paper, we propose a mathematical framework based on Riemannian geometry and kernel methods that can be applied to connectivity matrices for the classification task. We tested our approach using different real datasets of functional and structural connectivity, evaluating different metrics to describe the similarity between graphs. The empirical results obtained clearly show the superior performance of our approach compared with baseline methods, demonstrating the advantages of our manifold framework and its potential for other applications.