Refining epileptogenic high-frequency oscillations using deep learning: a reverse engineering approach

• Published in: Brain communications Vol. 4; no. 1; p. fcab267
• Main Authors: Zhang, Yipeng, Lu, Qiujing, Monsoor, Tonmoy, Hussain, Shaun A., Qiao, Joe X., Salamon, Noriko, Fallah, Aria, Sim, Myung Shin, Asano, Eishi, Sankar, Raman, Staba, Richard J., Engel, Jerome, Speier, William, Roychowdhury, Vwani, Nariai, Hiroki
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 2022
• Subjects: Original; HFO; physiological HFO; machine learning; pathological HFO; artificial intelligence
• ISSN: 2632-1297; 2632-1297
• DOI: 10.1093/braincomms/fcab267

Abstract
Intracranially recorded interictal high-frequency oscillations have been proposed as a promising spatial biomarker of the epileptogenic zone. However, its visual verification is time-consuming and exhibits poor inter-rater reliability. Furthermore, no method is currently available to distinguish high-frequency oscillations generated from the epileptogenic zone (epileptogenic high-frequency oscillations) from those generated from other areas (non-epileptogenic high-frequency oscillations). To address these issues, we constructed a deep learning-based algorithm using chronic intracranial EEG data via subdural grids from 19 children with medication-resistant neocortical epilepsy to: (i) replicate human expert annotation of artefacts and high-frequency oscillations with or without spikes, and (ii) discover epileptogenic high-frequency oscillations by designing a novel weakly supervised model. The ‘purification power’ of deep learning is then used to automatically relabel the high-frequency oscillations to distill epileptogenic high-frequency oscillations. Using 12 958 annotated high-frequency oscillation events from 19 patients, the model achieved 96.3% accuracy on artefact detection (F1 score = 96.8%) and 86.5% accuracy on classifying high-frequency oscillations with or without spikes (F1 score = 80.8%) using patient-wise cross-validation. Based on the algorithm trained from 84 602 high-frequency oscillation events from nine patients who achieved seizure-freedom after resection, the majority of such discovered epileptogenic high-frequency oscillations were found to be ones with spikes (78.6%, P < 0.001). While the resection ratio of detected high-frequency oscillations (number of resected events/number of detected events) did not correlate significantly with post-operative seizure freedom (the area under the curve = 0.76, P = 0.06), the resection ratio of epileptogenic high-frequency oscillations positively correlated with post-operative seizure freedom (the area under the curve = 0.87, P = 0.01). We discovered that epileptogenic high-frequency oscillations had a higher signal intensity associated with ripple (80–250 Hz) and fast ripple (250–500 Hz) bands at the high-frequency oscillation onset and with a lower frequency band throughout the event time window (the inverted T-shaped), compared to non-epileptogenic high-frequency oscillations. We then designed perturbations on the input of the trained model for non-epileptogenic high-frequency oscillations to determine the model’s decision-making logic. The model confidence significantly increased towards epileptogenic high-frequency oscillations by the artificial introduction of the inverted T-shaped signal template (mean probability increase: 0.285, P < 0.001), and by the artificial insertion of spike-like signals into the time domain (mean probability increase: 0.452, P < 0.001). With this deep learning-based framework, we reliably replicated high-frequency oscillation classification tasks by human experts. Using a reverse engineering technique, we distinguished epileptogenic high-frequency oscillations from others and identified its salient features that aligned with current knowledge.
See Hoogteijling and Zijlmans (https://doi.org/10.1093/braincomms/fcab307) for a scientific commentary on this article.
High-frequency oscillations (HFOs) comprise a promising neurophysiological biomarker of epilepsy, but identifying epileptogenic HFOs (eHFOs) among others is challenging. Zhang et al. report that a deep learning algorithm can reliably replicate classification tasks by human experts and can discover eHFOs by designing a novel weakly supervised model using clinical outcomes.
Graphical Abstract
Graphical Abstract