RAW Deep Brain Stmulation Recordings
收藏资源简介：
The dataset contains 4650 DBS recordings acquired during 46 DBS surgeries for Parkinson's Disease. Metadata describing recordings (patient's id, surgery_id, hemisphere_id, electrode name, recording depth and length, and finally the class) are in the feather format that can be loaded using the Python pandas library. The class has a value 1 for recordings registered within the Subthalamic Nucleus (STN) and 0 otherwise. Raw samples are stored in a npz file format that can be read using the Python numpy library. The dataset contains examples of use in pdf and Python notebook format. This dataset accompanies the paper K.A. Ciecierski, T. Mandat; Classification of DBS microelectrode recordings using a residual neural network with attention in the temporal domain; Neural Networks; 2023; ISSN 0893-6080; https://doi.org/10.1016/j.neunet.2023.11.021. Please cite the above reference if you wish to use this data.
本数据集包含4650例脑深部电刺激（Deep Brain Stimulation, DBS）记录，这些记录采集自46例帕金森病患者的脑深部电刺激手术。描述该类记录的元数据（含患者ID、手术ID、脑半球ID、电极名称、记录深度与时长，最终为分类标签）以Feather格式存储，可通过Python的Pandas库加载。分类标签取值为1时，表示记录采集自丘脑底核（Subthalamic Nucleus, STN），取值为0则表示非该区域。原始样本以NPZ文件格式存储，可通过Python的NumPy库读取。本数据集还提供了PDF格式与Python笔记本格式的使用示例。本数据集配套的学术论文为：K.A. Ciecierski、T. Mandat所著的《基于时域注意力残差神经网络的脑深部电刺激微电极记录分类》，发表于《Neural Networks》期刊，2023年，ISSN 0893-6080，DOI：10.1016/j.neunet.2023.11.021。若您使用本数据集，请引用上述参考文献。
