Efficient Sequential Bayesian Inference Method for Real-time Detection and Sorting of Overlapped Neural Spikes
Efficient Sequential Bayesian Inference Method for Real-time Detection and Sorting of Overlapped Neural Spikes
复制标题
用于重叠神经尖峰实时检测和排序的高效顺序贝叶斯推理方法
DOI：
10.1016/j.jneumeth.2013.06.009
复制
发表时间：
2013
影响因子：
3
通讯作者：
Kunihiko Mabuchi
中科院分区：
文献类型：
--
作者：
Tatsuya Haga;Osamu Fukayama;Yuzo Takayama;Takayuki Hoshino;Kunihiko Mabuchi
细胞外记录的神经尖峰波形的重叠导致原始尖峰波形变得隐藏和合并，混淆了这些尖峰的实时检测和排序。为解决这个问题而提出的方法包括使用多电极或限制重叠的复杂性。在本文中，我们提出了一个快速的顺序方法的鲁棒性检测和排序的任意重叠的尖峰记录与任意类型的电极。在我们的方法中，可能的尖峰列车的概率，包括那些重叠的，通过序贯贝叶斯推断的基础上的尖峰列车生成和细胞外电压记录的概率模型进行评估。为了降低穷举评估中固有的高计算成本，具有低概率的候选被认为是不可能的候选，并且在每个采样时间被废除以限制下一次评估中的候选数量。此外，来自几个后续采样时间的数据被考虑并用于计算“前瞻概率”，由于更快速地排除候选者而导致计算效率提高。这些充分减少了计算时间，以实现实时计算而不损害性能。我们评估了我们的方法使用模拟的神经信号和实际的神经信号记录在多电极阵列上培养的原代皮层神经元的性能。我们的结果表明，我们的计算方法可以应用于实时的延迟小于10毫秒。估计精度高于传统的尖峰排序方法，特别是对于具有多个重叠尖峰的信号。
Overlapping of extracellularly recorded neural spike waveforms causes the original spike waveforms to become hidden and merged, confounding the real-time detection and sorting of these spikes. Methods proposed for solving this problem include using a multi-trode or placing a restriction on the complexity of overlaps. In this paper, we propose a rapid sequential method for the robust detection and sorting of arbitrarily overlapped spikes recorded with arbitrary types of electrodes. In our method, the probabilities of possible spike trains, including those that are overlapping, are evaluated by sequential Bayesian inference based on probabilistic models of spike-train generation and extracellular voltage recording. To reduce the high computational cost inherent in an exhaustive evaluation, candidates with low probabilities are considered as impossible candidates and are abolished at each sampling time to limit the number of candidates in the next evaluation. In addition, the data from a few subsequent sampling times are considered and used to calculate the “look-ahead probability”, resulting in improved calculation efficiency due to a more rapid elimination of candidates. These sufficiently reduce computational time to enable real-time calculation without impairing performance. We assessed the performance of our method using simulated neural signals and actual neural signals recorded in primary cortical neurons cultured on a multi-electrode array. Our results demonstrated that our computational method could be applied in real-time with a delay of less than 10 ms. The estimation accuracy was higher than that of a conventional spike sorting method, particularly for signals with multiple overlapping spikes.