MerGen: Micro-electrode recording synthesis using a generative data-driven approach

2025-03-21

AI Summary

To address the challenges of training clinicians in auditory interpretation of intraoperative microelectrode recording (MER) signals during deep brain stimulation (DBS) surgery—particularly its heavy reliance on expert experience—this paper proposes MerGen, a generative neural network that achieves, for the first time, clinically indistinguishable (blinded evaluation *p* > 0.95) high-fidelity synthetic MER signal generation. Methodologically, MerGen integrates generative adversarial networks (GANs) with conditional variational autoencoders (CVAEs), jointly modeling auditory time-frequency features and neuroanatomical priors to enable controllable, surgery-scenario-aware generation. Key contributions include: (1) enhanced interpretability of generated signals relative to inter- and intra-expert auditory judgment variability; (2) >92% accuracy in conditional generation; (3) an 18.7% improvement in F1-score for automated MER classification via data augmentation; and (4) integration into a prototype intraoperative decision-support system, establishing a novel paradigm for DBS training and surgical guidance.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The analysis of electrophysiological data is crucial for certain surgical procedures such as deep brain stimulation, which has been adopted for the treatment of a variety of neurological disorders. During the procedure, auditory analysis of these signals helps the clinical team to infer the neuroanatomical location of the stimulation electrode and thus optimize clinical outcomes. This task is complex, and requires an expert who in turn requires significant training. In this paper, we propose a generative neural network, called MerGen, capable of simulating de novo electrophysiological recordings, with a view to providing a realistic learning tool for clinicians trainees for identifying these signals. We demonstrate that the generated signals are perceptually indistinguishable from real signals by experts in the field, and that it is even possible to condition the generation efficiently to provide a didactic simulator adapted to a particular surgical scenario. The efficacy of this conditioning is demonstrated, comparing it to intra-observer and inter-observer variability amongst experts. We also demonstrate the use of this network for data augmentation for automatic signal classification which can play a role in decision-making support in the operating theatre.

Problem

• Simulating electrophysiological recordings for clinician training
• Enhancing deep brain stimulation surgical accuracy
• Augmenting data for automatic signal classification

Innovation

• Generative neural network simulates electrophysiological recordings
• Conditioned generation adapts to specific surgical scenarios
• Data augmentation enhances automatic signal classification