End-to-end neural system identification with neural information flow.

Neural information flow (NIF) provides a novel approach for system identification in neuroscience. It models the neural computations in multiple brain regions and can be trained end-to-end via stochastic gradient descent from noninvasive data. NIF models represent neural information processing via a network of coupled tensors, each encoding the representation of the sensory input contained in a brain region. The elements of these tensors can be interpreted as cortical columns whose activity encodes the presence of a specific feature in a spatiotemporal location. Each tensor is coupled to the measured data specific to a brain region via low-rank observation models that can be decomposed into the spatial, temporal and feature receptive fields of a localized neuronal population. Both these observation models and the convolutional weights defining the information processing within regions are learned end-to-end by predicting the neural signal during sensory stimulation. We trained a NIF model on the activity of early visual areas using a large-scale fMRI dataset recorded in a single participant. We show that we can recover plausible visual representations and population receptive fields that are consistent with empirical findings.

Epidemiology of rotator cuff surgery in Italy: regional variation in access to health care. Results from a 14-year nationwide registry.

PURPOSE: Rotator cuff (RC) disease is frequent and represents a common source of shoulder pain. The aim of this study is to analyse geographical differences in RC surgeries from 2001 to 2014 in Italy, a country with universal and free health care for its population. METHODS: An analysis of the Italian National Hospital Discharge records from 2001 to 2014 was performed. These data are anonymous and include patient's age, sex, domicile, region of hospitalization, length of the hospitalization and type of reimbursement (public or private). National and regional population data were obtained from the National Institute for Statistics (ISTAT) for each year. RESULTS: During the 14-year study period, 390,001 RC repairs were performed in Italy, which represented a mean incidence of 62.1 RC procedures for every 100,000 Italian inhabitants. Nevertheless, the incidence was very different if every single regional population is considered individually. Lombardy resulted to have the highest number of surgeries during the 14-year study period, with 27.95% (108,954) of the total national procedures performed in the 2001-2014 time span. More than half the surgeries (52.00%) were performed in only 3 regions of the northern part of Italy. CONCLUSIONS: This study shows the existence of geographical disparities in access to RC surgery and patients' necessity to migrate among regions in order to obtain it. Southern regions of Italy are characterized by a lower number of surgeries compared to the northern part of Italy.

Generative adversarial networks for reconstructing natural images from brain activity.

We explore a method for reconstructing visual stimuli from brain activity. Using large databases of natural images we trained a deep convolutional generative adversarial network capable of generating gray scale photos, similar to stimuli presented during two functional magnetic resonance imaging experiments. Using a linear model we learned to predict the generative model's latent space from measured brain activity. The objective was to create an image similar to the presented stimulus image through the previously trained generator. Using this approach we were able to reconstruct structural and some semantic features of a proportion of the natural images sets. A behavioural test showed that subjects were capable of identifying a reconstruction of the original stimulus in 67.2% and 66.4% of the cases in a pairwise comparison for the two natural image datasets respectively. Our approach does not require end-to-end training of a large generative model on limited neuroimaging data. Rapid advances in generative modeling promise further improvements in reconstruction performance.