A deep learning-based brain-computer interface electrode position optimization method and system

By combining independent component analysis and deep learning models, personalized optimal electrode positions are generated, solving the problems of subjectivity and adaptability in electrode combinations during neurosurgery and improving the reliability and real-time performance of neuroelectric signal monitoring.

CN122290957APending Publication Date: 2026-06-26TONGJI HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
TONGJI HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI TECH
Filing Date
2026-03-26
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Current technologies in neurosurgery rely on the surgeon's subjective experience or fixed electrode combinations for signal analysis, resulting in a lack of standardized analysis results. This makes it difficult to adapt to changes in physiological state during surgery, reducing the reliability and real-time performance of nerve electrical signals.

Method used

By acquiring historical patients' magnetic resonance images and intraoperative multi-channel neuroelectrical signals, combined with independent component analysis and deep learning models, personalized optimal electrode positions are generated, enabling objective evaluation and adaptive selection of electrodes.

Benefits of technology

It significantly enhances the adaptability and accuracy of neurophysiological monitoring, providing objective and reliable intraoperative surgical decision support.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122290957A_ABST
    Figure CN122290957A_ABST
Patent Text Reader

Abstract

This invention relates to the fields of neuroengineering and medical device technology, specifically to a method and system for optimizing the electrode placement of a brain-computer interface based on deep learning. The method includes: acquiring historical patient MRI images, surgical tasks, and intraoperative multi-channel neural electrical signals, and recording the three-dimensional spatial coordinates of each electrode; performing independent component analysis on the multi-channel neural electrical signals after preprocessing to evaluate the quality of each electrode and generate an electrode subset with spatial location information; training a deep learning model using MRI images and surgical tasks as training data and the electrode subset as labels; inputting the target patient's MRI images and surgical tasks into the model, and outputting the optimal electrode placement. This invention integrates multimodal data, accurately evaluates electrodes through independent component analysis, and automatically generates personalized optimal electrode placement using deep learning. This overcomes the shortcomings of traditional methods that rely on subjective experience or fixed combinations, significantly enhancing the adaptability and accuracy of intraoperative monitoring.
Need to check novelty before this filing date? Find Prior Art