Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation

TL;DR

This paper introduces a deep learning model combining CNNs and RNNs to automatically detect diseases in chest X-rays and annotate their contexts, improving image annotation accuracy in medical imaging.

Contribution

The paper presents a novel recurrent neural cascade model that jointly infers image and text contexts for enhanced medical image annotation.

Findings

Significantly improved annotation accuracy over baseline models

Effective use of domain-specific image/text datasets for joint context inference

Regularization techniques mitigate class imbalance in disease detection

Abstract

Despite the recent advances in automatically describing image contents, their applications have been mostly limited to image caption datasets containing natural images (e.g., Flickr 30k, MSCOCO). In this paper, we present a deep learning model to efficiently detect a disease from an image and annotate its contexts (e.g., location, severity and the affected organs). We employ a publicly available radiology dataset of chest x-rays and their reports, and use its image annotations to mine disease names to train convolutional neural networks (CNNs). In doing so, we adopt various regularization techniques to circumvent the large normal-vs-diseased cases bias. Recurrent neural networks (RNNs) are then trained to describe the contexts of a detected disease, based on the deep CNN features. Moreover, we introduce a novel approach to use the weights of the already trained pair of CNN/RNN on the domain-specific image/text dataset, to infer the joint image/text contexts for composite image labeling. Significantly improved image annotation results are demonstrated using the recurrent neural cascade model by taking the joint image/text contexts into account.