Cross-modal Memory Networks for Radiology Report Generation

TL;DR

This paper introduces a cross-modal memory network that improves radiology report generation by explicitly modeling image-text alignments, achieving state-of-the-art results on benchmark datasets and enhancing report accuracy.

Contribution

It proposes a novel cross-modal memory network that explicitly captures image-text alignments to improve report generation in medical imaging.

Findings

Achieves state-of-the-art performance on IU X-Ray and MIMIC-CXR datasets.

Better alignment of radiology images and texts for more accurate reports.

Model enhances cross-modal interaction for improved clinical indicator accuracy.

Abstract

Medical imaging plays a significant role in clinical practice of medical diagnosis, where the text reports of the images are essential in understanding them and facilitating later treatments. By generating the reports automatically, it is beneficial to help lighten the burden of radiologists and significantly promote clinical automation, which already attracts much attention in applying artificial intelligence to medical domain. Previous studies mainly follow the encoder-decoder paradigm and focus on the aspect of text generation, with few studies considering the importance of cross-modal mappings and explicitly exploit such mappings to facilitate radiology report generation. In this paper, we propose a cross-modal memory networks (CMN) to enhance the encoder-decoder framework for radiology report generation, where a shared memory is designed to record the alignment between images and texts so as to facilitate the interaction and generation across modalities. Experimental results illustrate the effectiveness of our proposed model, where state-of-the-art performance is achieved on two widely used benchmark datasets, i.e., IU X-Ray and MIMIC-CXR. Further analyses also prove that our model is able to better align information from radiology images and texts so as to help generating more accurate reports in terms of clinical indicators.