TinyCheXReport: Compressed deep neural network for Chest X-ray report generation

Abstract

Increase in Chest X-ray (CXR) imaging tests has burdened radiologists, thereby posing significant challenges in writing radiological reports on time. Although several deep learning-based automatic report generation methods have been developed, most are over-parameterized. For deployment on edge devices with constrained processing power or limited resources, over-parameterized models are often too large. This article presents a compressed deep learning-based model that is 30% space efficient compared to the non-compressed base model, while both have comparable performance. The model comprising VGG19 and hierarchical long short-term memory equipped with a contextual word embedding layer is used as the base model. The redundant weight parameters are removed from the base model using unstructured one-shot pruning. To overcome the performance degradation, the lightweight pruned model is fine-tuned over publicly available OpenI dataset. The quantitative evaluation metric scores demonstrate that proposed model surpasses the performance of state-of-the-art models. Additionally, the proposed model, being 30% space efficient, is easily deployable in resource-limited settings. Thus, this study serves as baseline for development of compressed models to generate radiological reports from CXR images.