An algorithm based on a deep probabilistic architecture referred to as a tree-structured sum-product network (t-SPN) is considered for cell classification. The t-SPN is constructed such that the unnormalized probability is represented as conditional probabilities of a subset of most similar cell classes. The constructed t-SPN architecture is learned by maximizing the margin, which is the difference in the conditional probability between the true and the most competitive false label. To enhance the generalization ability of the architecture, L2-regularization (REG) is considered along with the maximum margin (MM) criterion in the learning process. To highlight cell features, this paper investigates the effectiveness of two generic high-pass filters: ideal high-pass filtering and the Laplacian of Gaussian (LOG) filtering. On both HEp-2 and Feulgen benchmark datasets, the t-SPN architecture learned based on the max-margin criterion with regularization produced the highest accuracy rate compared to other state-of-the-art algorithms that include convolutional neural network (CNN) based algorithms. The ideal high-pass filter was more effective on the HEp-2 dataset, which is based on immunofluorescence staining, while the LOG was more effective on the Feulgen dataset, which is based on Feulgen staining.
翻译:本文考虑了一种基于深度随机架构的算法,称为树状和积网络(t-SPN),用于细胞分类。 t-SPN 是如此构建的,以至于未归一化的概率被表示为一些最相似细胞类别的条件概率。构建的 t-SPN 架构是通过最大化边际来学习的,该边际是真实标签和最有竞争力的假标签之间的条件概率差。为增强架构的泛化能力,在学习过程中考虑了 L2-正则化(REG)与最大边际(MM)标准一起使用。为了突出细胞形态,本文研究了两种通用的高通滤波器的有效性:理想高通滤波和高斯-拉普拉斯算子(LOG)滤波。在 HEp-2 和 Feulgen 基准数据集上,基于正则化的最大边际标准所学习的 t-SPN 构架产生了相对于包括卷积神经网络(CNN)在内的其他现有算法的最高准确率。在基于免疫荧光染色的 HEp-2 数据集上,理想高通滤波器更加有效,而在基于费尔根染色的 Feulgen 数据集上,LOG 滤波器更加有效。