KGZNet:Knowledge-Guided Deep Zoom Neural Networks for Thoracic Disease Classification

Abstract

This paper aims to automatically diagnose thoracic diseases in Chest X-ray(CXR) images using deep neural net-works(DNN). However, the existing approaches generally use the global CXR images as input for training purposes. This strategy is low-efficiency, coarse, and might introduce many unnecessary noises. We believe that the deep learning, which is inherently an algebraic computation system, is not the most efficient way to acquire highly sophisticated human knowledge, for example those thoracic diseases are typically limited within the lung regions and interdependence between lesion location. In this paper, we address the above problem by proposing to explore how external medical knowledge can be injected into DNN to guide its training process. We design four feature extraction modules to construct a knowledge-guided deep zoom neural network(KGZNet), which can gradually make full use of the most medical discriminative feature information(from coarse to fine) of global, lung regions, and lesion regions. Specifically, we first learn global branch using global images. Second, learn the lung region branch using lung region images, which are identified and cropped by the Lung Region Generator(LRG-1). Then, guided by the attention heat map generated from the lung region branch learning, we inference a mask to crop a medical discriminative lesion region from the lung region images by the Lesion Region Generator(LRG-2). The lesion region images are used for training a lesion branch. Lastly, the obtained medical discriminative features knowledge are fused by the feature fusion model for disease classification. We have evaluated the proposed method on the NIH ChestX-ray 14 dataset and achieves the average AUC of 0.878, and the experiment results demonstrate the superiority and effectiveness of the proposed method, compared to other state-of-the-art methods.