Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

Abstract

As a major cause of leading female death, breast cancer is often diagnosed by histological images which has been resolved by many deep learning methods with the assistance of large amounts of annotated data. However, their performances are severely limited by the lack of sufficient labeled data in clinical practice. This paper aims to relieve the annotating workload by a semi-supervised transfer learning algorithm to conduct knowledge distillation from a completely labeled source domain. To achieve this goal, we propose a node-attention graph transfer network to exploit the inherent correlation between individual samples by graph convolutional network, along with a cross-domain graph learning module to stimulate the graph construction in target domain. In the meanwhile, we design a node-attention mechanism to learn the individual contribution of each source image for target domain, which can further leverage the domain-gap by our node-attention transfer learning. Results of semi-supervised breast histological image classification with various scales of annotated training images are performable and further experiments demonstrate the significant contributions of each component we proposed.

A Novel Feature Fusion for the Classification of Histopathological Carcinoma Images

“…The different data partition and composition-based models were assembled to enhance the model's ability to classify the data. The graph convolutional network developed by Gong et al [34] uses the node-attention graph transfer network (NaGTN) to take advantage of the innate correlation between labeled and unlabeled data. In order to undertake the extraction of knowledge for the target domain, this approach uses a fully labeled source domain.…”