Recent advances in brain clearing and imaging have made it possible to image entire mammalian brains at sub-micron resolution. These images offer the potential to assemble brain-wide atlases of projection neuron morphology, but manual neuron reconstruction remains a bottleneck. In this paper we present a probabilistic method which combines a hidden Markov state process that encodes neuron geometric properties with a random field appearance model of the flourescence process. Our method utilizes dynamic programming to efficiently compute the global maximizers of what we call the "most probable" neuron path. We applied our algorithm to the output of image segmentation models where false negatives severed neuronal processes, and showed that it can follow axons in the presence of noise or nearby neurons. Our method has the potential to be integrated into a semi or fully automated reconstruction pipeline. Additionally, it creates a framework for conditioning the probability to fixed start and endpoints through which users can intervene with hard constraints to, for example, rule out certain reconstructions, or assign axons to particular cell bodies.
翻译:大脑清理和成像的最新进步使得能够以亚微分分辨率来映射整个哺乳动物大脑。这些图像提供了收集整个脑部神经形态图集的潜力,但人工神经重建仍然是一个瓶颈。在本文中,我们提出了一个概率方法,将隐蔽的Markov状态进程与面粉过程的随机外观模型编码神经几何特性。我们的方法利用动态程序来有效地计算“最可能”神经路径的全球最大化。我们用算法来计算图像分割模型的输出,这些图解模型的输出是虚假的负神经神经过程,并显示它可以在噪音或附近神经神经元出现时跟随轴。我们的方法有可能被纳入半或完全自动化的重建管道。此外,我们的方法创造了一个框架,以调节固定起始和终点的可能性,用户可以通过这个框架来进行干预,例如,排除某些重建,或向特定的细胞体分配轴。