"Multi-label thoracic disease image classification with cross-attention" by Congbo MA, Hu WANG et al.
 

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2019

Abstract

Automated disease classification of radiology images has been emerging as a promising technique to support clinical diagnosis and treatment planning. Unlike generic image classification tasks, a real-world radiology image classification task is significantly more challenging as it is far more expensive to collect the training data where the labeled data is in nature multi-label; and more seriously samples from easy classes often dominate; training data is highly class-imbalanced problem exists in practice as well. To overcome these challenges, in this paper, we propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images, which can effectively excavate more meaningful representation from data to boost the performance through cross-attention by only image-level annotations. We also design a new loss function that beyond cross entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class. The proposed method achieves state-of-the-art results.

Keywords

Multi-label, Imbalanced, Medical image classification, Cross-Attention Networks

Discipline

Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 22nd International Conference, Shenzhen, China, 2019 October 13–17

First Page

730

Last Page

738

ISBN

9783030322250

Identifier

10.1007/978-3-030-32226-7_81

Publisher

Springer

City or Country

Cham

Additional URL

https://doi.org/10.1007/978-3-030-32226-7_81

Download

Share

COinS