基于改进U-Net网络的神经元分割算法

Neuron Segmentation Algorithm Based on Improved U-Net Network

针对目前电镜神经元图像分割的特征模糊性、复杂程度高以及边缘有损等缺陷,提出了一种将自注意力机制、叠加损失函数与U-Net网络相结合的网络模型,实现了对神经元图像的精确分割。首先,在原始图像的基础上通过几何变换实现数据集增广,有效地抑制了过拟合;其次,采用改进的自注意力机制对图像细节进行重点学习,提高模型分割的准确度;最后,将Dice loss与相对熵(KL散度)进行适当组合,使得网络性能有所提升。该模型在ISBI 2012数据集上的实验结果显示,其正确率、F1指标、准确度和召回率分别达到0.93043、0.95679、0.95326、0.96034,图像分割效果在整体和细节上分割相对更准确,并且细胞膜分割基本没有断裂。

A network model combining self-attentive mechanism,superposition loss function,and U-Net network was proposed to achieve accurate segmentation of neuronal images for the current defects of feature ambiguity,high complexity,and lossy edges of electron microscopy neuronal image segmentation.Firstly,the geometric transformation was performed with the original image to enlarge the data set and reduce overfitting.Secondly,the improved self-attention mechanism was used to focus on learning image details to improve the accuracy of model segmentation.Finally,the network performance was improved by appropriately combining Dice Loss with relative entropy(KL scatter).The network experimented on the ISBI 2012 dataset,and its correctness,F1 index,accuracy,and recall reached 0.93043,0.95679,0.95326,and 0.96034,respectively.The image segmentation effect was relatively more accurate in overall and detail segmentation,and the cell membrane segmentation was basically unbroken.