CLEAN-MI: A Scalable and Efficient Pipeline for Constructing High-Quality Neurodata in Motor Imagery Paradigm

2025-06-13

AI Summary

To address key bottlenecks in motor imagery (MI) brain–computer interfaces—including low signal-to-noise ratio (SNR), heterogeneous electrode configurations, and substantial inter-subject variability across subjects and recording devices—this paper proposes the first end-to-end neural data cleaning pipeline for EEG. The pipeline integrates bandpass filtering, template-driven channel remapping, statistical-guided subject selection, and maximum mean discrepancy (MMD)-based adversarial marginal distribution alignment to achieve automated standardization and quality enhancement of multi-source EEG data. Evaluated on multiple public MI datasets, the method significantly improves SNR and class separability, yielding an average 5.2% gain in downstream classification accuracy and tripling data reuse efficiency. This work establishes a high-quality, standardized data foundation essential for developing robust and generalizable foundation models for MI-BCI systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

The construction of large-scale, high-quality datasets is a fundamental prerequisite for developing robust and generalizable foundation models in motor imagery (MI)-based brain-computer interfaces (BCIs). However, EEG signals collected from different subjects and devices are often plagued by low signal-to-noise ratio, heterogeneity in electrode configurations, and substantial inter-subject variability, posing significant challenges for effective model training. In this paper, we propose CLEAN-MI, a scalable and systematic data construction pipeline for constructing large-scale, efficient, and accurate neurodata in the MI paradigm. CLEAN-MI integrates frequency band filtering, channel template selection, subject screening, and marginal distribution alignment to systematically filter out irrelevant or low-quality data and standardize multi-source EEG datasets. We demonstrate the effectiveness of CLEAN-MI on multiple public MI datasets, achieving consistent improvements in data quality and classification performance.

Problem

• Addresses low signal-to-noise ratio in EEG signals
• Standardizes multi-source heterogeneous EEG datasets
• Improves data quality for motor imagery BCIs

Innovation

• Frequency band filtering for noise reduction
• Channel template selection for standardization
• Marginal distribution alignment for consistency