RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection

Abstract

Hippocampal sharp wave ripples (SPW-R) have been identified as key bio-markers of important brain functions such as memory consolidation and decision making. Understanding their underlying mechanisms in healthy and pathological brain function and behaviour rely on accurate SPW-R detection. In this multidisciplinary study, we propose a novel, self-improving artificial intelligence (AI) detection method in the form of deep Recurrent Neural Networks (RNN) with Long Short-Term memory (LSTM) layers that can learn features of SPW-R events from raw, labeled input data. The approach contrasts conventional routines that typically relies on hand-crafted, heuristic feature extraction and often laborious manual curation. The algorithm is trained using supervised learning on hand-curated data sets with SPW-R events obtained under controlled conditions. The input to the algorithm is the local field potential (LFP), the low-frequency part of extracellularly recorded electric potentials from the CA1 region of the hippocampus. Its output predictions can be interpreted as time-varying probabilities of SPW-R events for the duration of the inputs. A simple thresholding applied to the output probabilities is found to identify times of SPW-R events with high precision. The non-causal, or bidirectional variant of the proposed algorithm demonstrates consistently better accuracy compared to the causal, or unidirectional counterpart. Reference implementations of the algorithm, named ‘RippleNet’, are open source, freely available, and implemented using a common open-source framework for neural networks () and can be easily incorporated into existing data analysis workflows for processing experimental data.

Analysis of Diabetes Clinical Data Based on Recurrent Neural Networks

“…Conventional neural networks consist of an input layer, an implicit layer, and an output layer, and although there are connections between the layers, the nodes within the layers are not connected [ 14 ]. As a result, many real-world problems cannot be handled using conventional neural networks.…”

Cell-type-specific silence in thalamocortical circuits precedes hippocampal sharp-wave ripples

“…Those SWR waveforms that were not agreed upon across the subjects discarded. A recently developed recurrent neural-network based automated tool (Hagen et al, 2021) was tested on a subset of recordings used in Figures 1, 2, 3, 4 and 5 (n = 12 mice, 35 sessions, 4509 SWR). The ratio of events deemed SWR by both the recurrent network and visual inspection to those events only deemed SWR by the recurrent network was 0.92, indicating that results from visual inspection closely matched a more objective, automated method for SWR detection.…”

Deep learning based feature extraction for prediction and interpretation of sharp-wave ripples

“…Remarkably, the filter exhibited larger variability across sessions. Our CNN performed similar to a filter-based optimized algorithm (F1=0.66 ± 0.11) (Dutta et al, 2019), but significantly better than RippleNET, a recurrent network designed to detect SWR mostly during periods of immobility (F1=0.31 ± 0.21; p<0.00001 one-way ANOVA for comparisons with both CNN12 and CNN32) (Hagen et al, 2021). This supports similar operation of CNN as compared with the gold standard in conditions when optimized detection was possible.…”

“…Moreover, with the advent of ultra-dense recordings, the need for automatic identification is pressing. In spite of recent advances (Dutta et al, 2019; Hagen et al, 2021), current solutions still fall short in capturing the complexity of SWR events across hippocampal layers.…”