Multi-Instance Learning by Utilizing Structural Relationship among Instances
This work provides an incremental improvement for medical image classification by better utilizing structural relationships in MIL.
This paper proposes a Multi-Instance Learning (MIL) algorithm that leverages structural relationships among instances within a bag by constructing a graph and employing Graph Convolutional Networks (GCN) with an attention mechanism. The method achieved better results than previous methods on five benchmark MIL datasets and four medical image datasets, demonstrating its suitability for high-resolution medical image classification.
Multi-Instance Learning(MIL) aims to learn the mapping between a bag of instances and the bag-level label. Therefore, the relationships among instances are very important for learning the mapping. In this paper, we propose an MIL algorithm based on a graph built by structural relationship among instances within a bag. Then, Graph Convolutional Network(GCN) and the graph-attention mechanism are used to learn bag-embedding. In the task of medical image classification, our GCN-based MIL algorithm makes full use of the structural relationships among patches(instances) in an original image space domain, and experimental results verify that our method is more suitable for handling medical high-resolution images. We also verify experimentally that the proposed method achieves better results than previous methods on five bechmark MIL datasets and four medical image datasets.