结合加权原型和自适应张量子空间的小样本宫颈细胞分类

Few-shot cervical cell classification combining weighted prototype and adaptive tensor subspace

基于深度学习的图像分类算法通常依赖大量训练数据,然而对于医学领域中的宫颈细胞分类任务,难以实现收集大量的图像数据。为了在少量图像样本的条件下正确分类宫颈细胞,提出一种结合加权原型和自适应张量子空间的小样本分类算法(CWP-ATS)。首先,结合预训练技术和元学习,保证特征提取网络从元训练集中学习更多的先验知识;其次,在原型计算过程中采用最大均值差异算法为每个支持集样本赋予合适的权重,并采用转导学习算法修正,以获得更准确的原型;最后,利用多线性主成分分析算法将每类样本投影至各自的低维张量子空间,从而在不破坏原始张量特征自然结构的前提下,在低维空间中学习高效的自适应子空间分类器。在小样本Herlev宫颈细胞图像的2-way 10-shot和3-way 10-shot分类任务中,与DeepBDC(Deep Brownian Distance Covariance)算法相比,CWPATS的分类准确度分别提高了2.43和3.23个百分点;当元测试集中30%的样本受噪声干扰时,与原型网络相比,CWP-ATS的分类准确度有超过20个百分点的提升。实验结果表明,CWP-ATS有效提高了对小样本宫颈细胞的分类准确度和鲁棒性。

Deep learning image classification algorithms rely on a large amount of training data typically.However,for cervical cell classification tasks in the medical field,collecting large amount of image data is difficult.To accurately classify cervical cells with a limited number of image samples,a few-shot classification algorithm Combining Weighted Prototype and Adaptive Tensor Subspace(CWP-ATS)was proposed.Firstly,the pre-training technique was combined with meta-learning to ensure that the feature extraction network learned more priori knowledge from the meta-training set.Subsequently,the maximum mean discrepancy algorithm was adopted in the prototype computation procedure to assign appropriate weight to each support set sample,and the transductive learning algorithm was further employed for making corrections and obtaining more accurate prototypes.Finally,the multilinear principal component analysis algorithm was utilized to project each class of samples into their respective low-dimensional tensor subspaces,enabling efficient adaptive subspace classifiers in the lowdimensional space to be learned without compromising the natural structures of the original tensor features.In the 2-way 10-shot and 3-way 10-shot classification tasks of few-shot Herlev cervical cell images,compared with the DeepBDC(Deep Brownian Distance Covariance)algorithm,CWP-ATS improved classification accuracy by 2.43 and 3.23 percentage points,respectively;when 30%samples of the meta-test set were interfered by noise,in comparison with the prototype network,the classification accuracy of CWP-ATS was improved by more than 20 percentage points.The experimental results demonstrate that the proposed algorithm can effectively improve the classification accuracy and robustness of few-shot cervical cells.