Privacy-preserving Early Detection of Epileptic Seizures in Videos

TL;DR

This paper introduces a privacy-preserving video-based framework for early detection of epileptic seizures using optical flow features and transformer-based knowledge distillation, achieving 83.9% accuracy on tonic-clonic seizures halfway through their progression.

Contribution

It presents a novel framework combining optical flow features and progressive knowledge distillation for privacy-preserving early seizure detection in videos.

Findings

Achieved 83.9% accuracy in detecting seizures halfway through their progression.

Utilized optical flow features to encode seizure motion while preserving patient privacy.

Demonstrated real-time detection capability on shortened video segments.

Abstract

In this work, we contribute towards the development of video-based epileptic seizure classification by introducing a novel framework (SETR-PKD), which could achieve privacy-preserved early detection of seizures in videos. Specifically, our framework has two significant components - (1) It is built upon optical flow features extracted from the video of a seizure, which encodes the seizure motion semiotics while preserving the privacy of the patient; (2) It utilizes a transformer based progressive knowledge distillation, where the knowledge is gradually distilled from networks trained on a longer portion of video samples to the ones which will operate on shorter portions. Thus, our proposed framework addresses the limitations of the current approaches which compromise the privacy of the patients by directly operating on the RGB video of a seizure as well as impede real-time detection of a seizure by utilizing the full video sample to make a prediction. Our SETR-PKD framework could detect tonic-clonic seizures (TCSs) in a privacy-preserving manner with an accuracy of 83.9% while they are only half-way into their progression. Our data and code is available at https://github.com/DevD1092/seizure-detection