Multi Resolution LSTM For Long Term Prediction In Neural Activity Video

TL;DR

This paper introduces a multi-resolution LSTM framework with adversarial training for long-term prediction of neural activity waves in videos, aiming to enable real-time seizure intervention.

Contribution

It proposes a novel multi-resolution LSTM architecture with encoder-decoder structures and adversarial training to improve long-term neural activity prediction.

Findings

Multi-resolution LSTM outperforms single-resolution models.

Adversarial training reduces prediction blurring.

3D CNN enhances long-term prediction accuracy.

Abstract

Epileptic seizures are caused by abnormal, overly syn- chronized, electrical activity in the brain. The abnor- mal electrical activity manifests as waves, propagating across the brain. Accurate prediction of the propagation velocity and direction of these waves could enable real- time responsive brain stimulation to suppress or prevent the seizures entirely. However, this problem is very chal- lenging because the algorithm must be able to predict the neural signals in a sufficiently long time horizon to allow enough time for medical intervention. We consider how to accomplish long term prediction using a LSTM network. To alleviate the vanishing gradient problem, we propose two encoder-decoder-predictor structures, both using multi-resolution representation. The novel LSTM structure with multi-resolution layers could significantly outperform the single-resolution benchmark with similar number of parameters. To overcome the blurring effect associated with video prediction in the pixel domain using standard mean square error (MSE) loss, we use energy- based adversarial training to improve the long-term pre- diction. We demonstrate and analyze how a discriminative model with an encoder-decoder structure using 3D CNN model improves long term prediction.