Histopathological image classification using random binary hashing based PCANet and bilinear classifier
Jinjie Wu, Jun Shi, Yan Li, Jingfeng Suo, Qi Zhang · 2016
The computer-aided histopathological image diagnosis has attracted considerable attention. Principal component analysis network (PCANet) is a novel deep learning algorithm with a simple network architecture and parameters. In this work, we propose a random binary hashing (RBH) based PCANet (RBH-PCANet), which can generate multiple randomly encoded binary codes to provide more information. Moreover, we rearrange the local features derived from PCANet to the matrix-form features in order to reduce feature dimensionality, and then we apply the low-rank bilinear classifier (LRBC) to perform effective classification for matrix features. The proposed classification framework using RBH-PCANet and LRBC (RBH-PCANet-LRBC) is adopted for histopathological image classification. The experimental results on both a hepatocellular carcinoma image dataset and a breast cancer image dataset show that the RBH-PCANet-LRBC algorithm achieves best performance compared with other unsupervised deep learning algorithms.