三维图像栈中神经末梢点的自动检测

作为神经元追踪算法的种子点,神经元的末梢点的检测非常关键。此前的研究提出了一种基于发散射线模型(rayshooting model)的检测方法,通过分析神经元图像中候选末梢点附近邻域的灰度强度分布来检测神经元的末梢点。然而,在此模型中,射线的长度以及z方向切片的数量都是固定值,所以在处理一些神经元直径尺寸变化较大的图像时,算法的准确性很受影响。因此,提出了一种可以根据神经元局部直径大小来改变射线长度以及相邻切片数量的自适应发散射线模型,神经元的局部直径由一种结合了Rayburst sampling算法及MSFM(multistencils fast marching)算法的方法测得。实验结果表明,与之前的方法相比,检测精度提高了约10%。

Automatic neuron terminal point detection in 3D image stack

3D neuron terminal points could be very good seed points in neuron tracing algorithms.Previously,a ray-shooting model to detect neuron terminal point was proposed by analyzing the intensity distribution characteristics of the neighborhoods around the terminal point candidates.However,the length of the shooting rays and the number of z-slices that should be considered in this model are fixed,its accuracy would be seriously affected when handling datasets where the diameter of the neuron varies much.Thus,an adaptive ray-shooting model is proposed by changing the length of the shooting rays and the number of adjacent slices according to the local diameter of the neuron obtained by the MSFM (multistencils fast marching) method and Rayburst sampling algorithm.Compared with the previous work,the experimental results show that the proposed method could improve the detection accuracy by about 10％.