Second‐order asymmetric convolution network for breast cancer histopathology image classification. Issue 5 (9th February 2022)

• Record Type: Journal Article
• Authors: Hou, Cunqiao; Li, Jiasen; Wang, Wei; Sun, Lin; Zhang, Jianxin
• Is Part Of: Journal of biophotonics. Volume 15:Issue 5(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-02-09
• Subjects: asymmetric convolution -- breast cancer histopathology image classification -- convolutional neural network -- covariance pooling -- second‐order statistics; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.202100370
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Recently, convolutional neural networks (CNNs) have been widely utilized for breast cancer histopathology image classification. Besides, research works have also convinced that deep high‐order statistic models obviously outperform corresponding first‐order counterparts in vision tasks. Inspired by this, we attempt to explore global deep high‐order statistics to distinguish breast cancer histopathology images. To further boost the classification performance, we also integrate asymmetric convolution into the second‐order network and propose a novel second‐order asymmetric convolution network (SoACNet). SoACNet adopts a series of asymmetric convolution blocks to replace each stand square‐kernel convolutional layer of the backbone architecture, followed by a global covariance pooling to compute second‐order statistics of deep features, leading to a more robust representation of histopathology images. Extensive experiments on the public BreakHis dataset demonstrate the effectiveness of SoACNet for breast cancer histopathology image classification, which achieves competitive performance with the state‐of‐the‐arts. Abstract : We propose a novel second‐order asymmetric convolution network (SoACNet) for breast cancer histopathology image classification, which simultaneously integrates the second‐order pooling and asymmetric convolution into a single plain CNN stream. It adopts asymmetric convolution blocks to replace stand square‐kernel convolutional layers of the backbone network, followed by a global covariance pooling to compute second‐order statistics of deep features, leading to a more robust representation of histopathology images. Extensive experiments demonstrate the competitive performance of SoACNet compared with the state‐of‐the‐arts.