Visual acuity prediction on real-life patient data using a machine learning based multistage system.

In ophthalmology, intravitreal operative medication therapy (IVOM) is a widespread treatment for diseases related to the age-related macular degeneration (AMD), the diabetic macular edema, as well as the retinal vein occlusion. However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. For the disease AMD, we found out a significant deterioration of the visual acuity over time. Within our proposed multistage system, we subsequently classify the VA progression into the three groups of therapy "winners", "stabilizers", and "losers" (WSL classification scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98%, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame, whereas our prediction is currently restricted to IVOM/no therapy. We achieve a final prediction accuracy of 69% in macro average F1-score, while being in the same range as the ophthalmologists with 57.8 and 50 ± 10.7 % F1-score.

A large-scale neurocomputational model of spatial cognition integrating memory with vision.

We introduce a large-scale neurocomputational model of spatial cognition called 'Spacecog', which integrates recent findings from mechanistic models of visual and spatial perception. As a high-level cognitive ability, spatial cognition requires the processing of behaviourally relevant features in complex environments and, importantly, the updating of this information during processes of eye and body movement. The Spacecog model achieves this by interfacing spatial memory and imagery with mechanisms of object localisation, saccade execution, and attention through coordinate transformations in parietal areas of the brain. We evaluate the model in a realistic virtual environment where our neurocognitive model steers an agent to perform complex visuospatial tasks. Our modelling approach opens up new possibilities in the assessment of neuropsychological data and human spatial cognition.

A neuro-computational model of visual attention with multiple attentional control sets.

In numerous activities, humans need to attend to multiple sources of visual information at the same time. Although several recent studies support the evidence of this ability, the mechanism of multi-item attentional processing is still a matter of debate and has not been investigated much by previous computational models. Here, we present a neuro-computational model aiming to address specifically the question of how subjects attend to two items that deviate defined by feature and location. We simulate the experiment of Adamo et al. (2010) which required subjects to use two different attentional control sets, each a combination of color and location. The structure of our model is composed of two components "attention" and "decision-making". The important aspect of our model is its dynamic equations that allow us to simulate the time course of processes at a neural level that occur during different stages until a decision is made. We analyze in detail the conditions under which our model matches the behavioral and EEG data from human subjects. Consistent with experimental findings, our model supports the hypothesis of attending to two control settings concurrently. In particular, our model proposes that initially, feature-based attention operates in parallel across the scene, and only in ongoing processing, a selection by the location takes place.

A mechanistic cortical microcircuit of attention for amplification, normalization and suppression.

Computational models of visual attention have replicated a large number of data from visual attention experiments. However, typically each computational model has been shown to account for only a few data sets. We developed a novel model of attention, particularly focused on explaining single cell recordings in multiple brain areas, to better understand the underlying computational circuits of attention involved in spatial- and feature-based biased competition, modulation of the contrast response function, modulation of the neuronal tuning curve, and modulation of surround suppression. In contrast to previous models, we use a two layer structure inspired by the layered cortical architecture which implements amplification, divisive normalization and suppression as well as spatial pooling.

Comparison of GPU- and CPU-implementations of mean-firing rate neural networks on parallel hardware.

Modern parallel hardware such as multi-core processors (CPUs) and graphics processing units (GPUs) have a high computational power which can be greatly beneficial to the simulation of large-scale neural networks. Over the past years, a number of efforts have focused on developing parallel algorithms and simulators best suited for the simulation of spiking neural models. In this article, we aim at investigating the advantages and drawbacks of the CPU and GPU parallelization of mean-firing rate neurons, widely used in systems-level computational neuroscience. By comparing OpenMP, CUDA and OpenCL implementations towards a serial CPU implementation, we show that GPUs are better suited than CPUs for the simulation of very large networks, but that smaller networks would benefit more from an OpenMP implementation. As this performance strongly depends on data organization, we analyze the impact of various factors such as data structure, memory alignment and floating precision. We then discuss the suitability of the different hardware depending on the networks' size and connectivity, as random or sparse connectivities in mean-firing rate networks tend to break parallel performance on GPUs due to the violation of coalescence.

Split of spatial attention as predicted by a systems-level model of visual attention.

Can we attend to multiple distinct spatial locations at the same time? According to a recent psychophysical study [J. Dubois et al. (2009)Journal of Vision, 9, 3.1-11] such a split of spatial attention might be limited to short periods of time. Following N. P. Bichot et al. [(1999)Perception & Psychophysics, 61, 403-423] subjects had to report the identity of multiple letters that were briefly presented at different locations, while two of these locations (targets) were relevant for a concurrent shape comparison task. In addition to the design used by Bichot et al. stimulus onset asynchrony between shape onset and letters was systematically varied. In general, the performance of subjects was superior at target locations. Furthermore, for short stimulus onset asynchronies, performance was simultaneously increasing at both target locations. For longer stimulus onset asynchronies, however, performance deteriorated at one of the target locations while increasing at the other target location. It was hypothesized that this dynamic deployment of attention might be caused by competitive processes in saccade-related structures such as the frontal eye field. Here we simulated the task of Dubois et al. using a systems-level model of attention. Our results are consistent with recent findings in the frontal eye field obtained during covert visual search, and they support the view of a transient deployment of spatial attention to multiple stimuli in the early epoch of target selection.