使用深度学习进行神经元细胞类型分类
Neuronal Cell Type Classification using Deep Learning
AI总结：
本文提出一种可解释深度学习框架，基于电生理活动对小鼠和人类神经元进行细胞类型、宽泛类型及转基因品系分类，并通过领域自适应取得最先进性能。
摘要：
鉴于大脑所控制功能的多样性、所包含细胞的数量及其相应的多样性，它很可能是最复杂的器官。研究和识别神经元——大脑的基本组成单元——是一个关键里程碑，对于理解健康和疾病状态下的脑功能至关重要。机器学习的最新进展为神经元分类提供了先进能力。然而，这些方法仍然是黑箱，缺乏可解释性和推理能力。本文旨在提供一个稳健且可解释的深度学习框架，根据神经元的电生理活动对其进行分类。我们的分析基于 Allen Cell Types 数据库提供的数据，该数据库包含从小鼠和人类单细胞记录中获得的生物学特征普查。首先，我们对小鼠数据中的神经元细胞类型进行分类，以识别兴奋性和抑制性神经元。随后，利用来自小鼠数据的领域自适应，将人类神经元划分为其宽泛类型。最后，以可解释的方式使用深度神经网络，根据转基因小鼠品系将神经元分类为亚型。我们在兴奋性与抑制性神经元的树突类型分类以及转基因小鼠品系分类中展示了最先进的结果。该模型还具有内在可解释性，揭示了神经元类型与其电生理特性之间的相关性。
英文摘要：
The brain is likely the most complex organ, given the variety of functions it controls, the number of cells it comprises, and their corresponding diversity. Studying and identifying neurons, the brain's primary building blocks, is a crucial milestone and essential for understanding brain function in health and disease. Recent developments in machine learning have provided advanced abilities for classifying neurons. However, these methods remain black boxes with no explainability and reasoning. This paper aims to provide a robust and explainable deep-learning framework to classify neurons based on their electrophysiological activity. Our analysis is performed on data provided by the Allen Cell Types database containing a survey of biological features derived from single-cell recordings of mice and humans. First, we classify neuronal cell types of mice data to identify excitatory and inhibitory neurons. Then, neurons are categorized to their broad types in humans using domain adaptation from mice data. Lastly, neurons are classified into sub-types based on transgenic mouse lines using deep neural networks in an explainable fashion. We show state-of-the-art results in a dendrite-type classification of excitatory vs. inhibitory neurons and transgenic mouse lines classification. The model is also inherently interpretable, revealing the correlations between neuronal types and their electrophysiological properties.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
